SPATIAL ECONOMETRIC DATA ANALYSIS: MOVING BEYOND TRADITIONAL MODELS

Size: px
Start display at page:

Download "SPATIAL ECONOMETRIC DATA ANALYSIS: MOVING BEYOND TRADITIONAL MODELS"

Transcription

1 INTERNATIONAL REGIONAL SCIENCE REVIEW 26, 3: (July 2003) / Florax, van der Vlist / SPATIAL INTERNATIONAL ECONOMETRIC REGIONAL DATA ANALYSIS SCIENCE REVIEW (Vol. 26, No. 3, 2003) ARTICLE SPATIAL ECONOMETRIC DATA ANALYSIS: MOVING BEYOND TRADITIONAL MODELS RAYMOND J. G. M. FLORAX Department of Spatial Economics, Free University, Amsterdam, The Netherlands, and Regional Economics Applications Laboratory (REAL), University of Illinois at Urbana-Champaign, Urbana, [email protected] ARNO J. VAN DER VLIST Department of Spatial Economics, Free University, Amsterdam, The Netherlands, [email protected] This article appraises recent advances in the spatial econometric literature. It serves as the introduction to a collection of new papers on spatial econometric data analysis brought together in this special issue, dealing specifically with new extensions to the spatial econometric modeling perspective. Although the initial development of the field of spatial econometrics has been rather slow, the Dixit-Stiglitz revolution and the emergence of the New Economy Geography have been instrumental in uplifting the significance and the use of spatial data analysis techniques. Concurrent developments in other social sciences parallel this situation in economics. The upsurge in spatial econometrics is, among other things, driven by the recognition that traditional spatial econometric models are insufficient to capture modern theoretical developments. Therefore, this issue brings together a collection of articles on space-time and discrete choice modeling, spatial nonstationarity, and the methodology and empirics of regional economic growth models. Keywords: spatial econometrics; data analysis; spatial regression models It is difficult not to notice the upsurge in the advancement of econometric theory for spatial cross-section models, the availability of easy-to-use software for spatial data, and the use of spatial econometric techniques in applied research. In 1988, Anselin and Griffith pointed out the negligence of regional science scholars toward incorporating spatial data analysis techniques in applied research. In the early 1990s, Anselin and Rey (1991) reiterated this point, but they had already observed indications of a gradual change. Ever since, the situation has altered radically, and it is fair to say that nowadays, spatial data analysis techniques abound. Recent conferences of constituent organizations of the Regional Science Association International (RSAI) have programmed special sessions on spatial econometrics. This was the case at the Western Regional Science Association meeting in Palm Springs, California, in 2001; the North American meeting in San Juan, Puerto DOI: / Sage Publications

2 224 INTERNATIONAL REGIONAL SCIENCE REVIEW (Vol. 26, No. 3, 2003) Rico, in 2002; and the European meeting in Dortmund, Germany, in A series of special issues of journals and edited volumes reveals the progress that is being made in the area of spatial econometrics (Anselin 1992a; Anselin and Florax 1995a; Anselin and Rey 1997; Pace 1998; Nelson 2002; Getis, Mur, and Zoller forthcoming; Pace, Tiefelsdorf, and LeSage forthcoming). Theoretical advances with respect to spatial econometric modeling are increasingly also published in some of the topnotch journals in economics and econometrics (Dubin 1988; Pinkse and Slade 1998; Conley 1999; Kelejian and Prucha 2001; Lee 2002). Funding organizations, such as the American National Science Foundation, finance programs in which the integration of the spatial dimension in social science research forms essentially the core of the program (i.e., the initiative to establish the Center for Spatially Integrated Social Sciences [CSISS]) (see Goodchild et al. 2000; As we will show below, the number of applied papers using spatial statistical and econometric techniques is rapidly increasing as well. We continue this article by discussing some of the history of spatial econometrics. Although the history dates back to the 1940s and 1950s, with subsequent sizable pushes in the 1970s and 1980s, the path of development remains rather flat until the 1990s. We argue that recent theoretical developments in economics and other social sciences induce a reorientation that includes spatial effects among the main determinants of real-world processes. The reorientation is accompanied by an increase in available spatially referenced data, which are usually easy to attain through the Internet. We discuss several consequences of changes in data availability, such as lowerspatial scale, computational aspects, and visualization. Apart from theory and data, the accessibility of appropriate software definitely goes a long way in explaining the current upsurge in the use of spatial econometric techniques. Subsequently, we provide an overview of the main methodological contributions to spatial econometrics, and we review applications of spatial econometric techniques according to areas demarcated in the subject index of the International Regional Science Review (IRSR). 2 We go on to argue that the above-mentioned theoretical developments and the increased data availability are starting to drive the field of spatial econometrics away from the traditional spatial error and spatial lag model and toward different and much broader directions now (see also Anselin 2002). The proliferation of spatial econometrics into different directions motivated the first author of this article to organize special sessions on spatial econometrics for the 42nd European conference of the RSAI, which took place in Dortmund (Germany) from August Some fifteen papers, organized in six special sessions, were presented. 3 After the conference, we invited the participants to submit their papers for this special issue. Two external reviewers per manuscript scrutinized the papers, following standard peer review procedures of IRSR. We now have a series of articles that illustrates the recent proliferation of spatial econometrics to very diverse areas of methodological concern and application. The articles cover

3 Florax, van der Vlist / SPATIAL ECONOMETRIC DATA ANALYSIS 225 the areas of space-time models, spatial hazard modeling, vector autoregressive models with spatial interaction effects, and spatial nonstationarity. The issue concludes with contributions to the empirics of regional economic growth using exploratory spatial data analysis techniques, Markov chain modeling, and a simultaneous dynamic least squares estimator for a generalized spatial convergence model. More detail about the individual contributions and promising avenues for future research on spatial econometrics conclude our contribution. SOME HISTORY The history of spatial statistical and econometric data analysis goes back to the work of statisticians such as Moran, Geary, and Whittle in the late 1940s and early 1950s. Initially, developments were rather slow, but they were decisively influenced by the publication of three seminal books (Florax and Nijkamp forthcoming). In 1973, Cliff and Ord devoted a monograph to spatial autocorrelation. Their book primarily focuses on the statistical analysis of spatial data series, although there is some attention for modeling as well. The modeling context is much more pronounced in the work of the Dutch-Belgian economist Jean Paelinck, who coined the term spatial econometrics in the early 1970s. Paelinck and Klaassen jointly wrote the first monograph on spatial econometrics in 1979, stressing the need to explicitly model spatial relations, epitomizing the asymmetry in spatial interrelations and the role of spatial interdependence. The field was in those days pushed ahead mainly by Dutch regional economists and British geographers and economists (e.g., Bartels, Brandsma, Hordijk, Ketellapper, and Nijkamp, in The Netherlands, and Fingleton, Haining, Ord, and Upton, in the United Kingdom). Later, the center of activity shifted to the United States, where both economists and geographers concentrated on introducing new statistical tests and specifying and estimating spatial regression models. The modeling perspective was pondered and comprehensively treated in Luc Anselin s (1988) book on methods and models in spatial econometrics. He defined spatial econometrics as the collection of techniques that deal with the peculiarities caused by space in the statistical analysis of regional science models (p. 7). The modeling perspective distinguishes spatial econometrics from the broader field of spatial statistics, the progress of which is documented in, for instance, Cressie (1993). Several reasons come to mind when trying to explain the initial lack of consideration of spatial effects and the subsequent upsurge in the development and use of spatial analysis tools. First, going back to classical economists such as Marshall, economists have been preoccupied with the temporal rather than the spatial dimension of economic phenomena. This was a majornuisance pushing WalterIsard to establish the interdisciplinary field of regional science, maintaining that (neo)classical economists are confined to analyzing a wonderland of no spatial dimensions (Isard 1956, 24-25). This did contribute to the establishment of spatial econometrics some twenty years later but, in itself, was not sufficient to lead to a widespread

4 226 INTERNATIONAL REGIONAL SCIENCE REVIEW (Vol. 26, No. 3, 2003) use of spatial econometric techniques. Although spatial econometrics is definitely one of the perks of the Isard push for a regional science, the Dixit-Stiglitz revolution has had a pervasive influence as well (Florax and Nijkamp forthcoming). It raised attention for imperfect competition and increasing returns to scale, which later became prominent elements in the New Economic Geography, next to the concept of spatial externalities (Fujita, Krugman, and Venables 1999; Fujita and Krugman forthcoming). In other social sciences, similar attention shifts have occurred. Increasingly, the popularity of neighborhood effects in sociology, associated with the Chicago school, and the revival of social interaction theory have caused researchers to think about spatial interaction, spatial spillovers, and spatial dependence (see Anselin 2003 and the references therein). Second, the availability of georeferenced data has increased considerably over the past two decades. The Internet obviously contributes to easy access and thus stimulates the use of spatial data with concurrent use of specialized technology, such as Geographic Information Systems (GIS) and Global Positioning Systems (GPS) and remote sensing technology (Goodchild et al. 2000; see also the examples in Nelson 2002). The increased availability of geographical data has several implications for the substance of spatial econometric techniques. First, the restriction to one spatial scale determined by data availability is relaxed. This creates the opportunity to experiment with models at different levels of spatial aggregation. The relevance of the scale aspect is well known. Straightforward aggregation over space is only warranted if the phenomenon at stake is homogeneously distributed over space (Anselin 1988, 26-27) and the effect of spatial scale on test statistics is pervasive (Griffith, Wong, and Whitfield forthcoming). The aspects of spatial scale and identification come together in the modifiable areal unit problem (Arbia 1989; Amrhein 1995; Amrhein and Reynolds 1996). Identification issues are particularly severe if limited data are available, and this is one of the reasons why spatial process models, which provide exogenous spatial structure through the spatial weights matrix to avoid the incidental parameter problem, have been used so intensively. With more data, it becomes feasible to use direct representation models, which are characterized by estimable distance decay functions rather than exogenously provided spatial structure. 4 The latter type of models provides a much more detailed and data-driven approach to model specification. An additional advantage is that direct representation models circumvent the computational problems associated with large-scale spatial process models, such as computational efficiency, accuracy, and storage, although progress has been made to solve these computational problems (Pace 1997; Pace and Barry 1997a, 1997b; Smirnov and Anselin 2001). Third, for a long time, the freestanding SpaceStat computer program (Anselin 1992b, 2000) was the only full-blown package forspatial econometric analysis. It was complemented by computercode documenting routines to estimate spatial models in mainstream software packages, such as Limdep and Shazam (Griffith 1988; Anselin and Hudak 1992). Slightly later, extensions such as S+SpatialStats (Kaluzny et al. 1997), INFO-MAP (Bailey and Gatrell 1995), and SAGE (Haining,

5 Florax, van der Vlist / SPATIAL ECONOMETRIC DATA ANALYSIS 227 Wise, and Signoretta 2000) were introduced. The improvement in the availability of easy-to-use software obviously contributes to the proliferation of spatial econometric applications. Nowadays, the two most complete software packages are SpaceStat (Anselin 1992b, 2000; see specs.html) and James LeSage s extensive spatial econometrics toolkit developed in MATLAB (see Anselin s package stands out for its combination of exploratory tools, linked to ESRI s ArcView software through a freely available extension, and misspecification tests and estimators for spatial models. LeSage s toolkit is slightly more oriented toward modeling and contains an array of Bayesian routines in addition to the classical tests and estimators. 5 The development of software tools has been very rapid over the past decade. On the CSISS Web site, Luc Anselin presents a spatial tools search engine that indexes a list of URLs and software archives of already more than 700 individual software titles. A spatial tool listing of links to portals (i.e., collections of links) is available as well. The development of software is expected to continue to proceed rapidly now. So-called open-source projects are promising. These projects are typically Web based, and they essentially constitute a platform and a common language for anybody who can credibly contribute to the development of software tools. Platform-independent software that is currently being developed in the context of the CSISS project (see Goodchild et al. 2000) will further facilitate and boost the application of spatial data analysis techniques. HIGHLIGHTS AND THE PROLIFERATION OF SPATIAL ECONOMETRIC TECHNIQUES It is virtually impossible to give a detailed account of the development and the achievements of spatial econometrics in the space-constrained context of a single section of an article. What follows is therefore by far not comprehensive but instead deals with some highlights of the methodological spatial econometric literature as well as a series of examples showing the proliferation of applying spatial econometric techniques to different areas in regional science. The consideration of spatial effects in applied research involves a series of logical steps in the analysis. We highlight some of the important methodological developments by means of these steps, distinguishing exploratory data analysis, misspecification testing in spatial regression models, and the estimation of spatial regression models. 6 Spatial effects is a catchall term referring to both spatial dependence and spatial heterogeneity. Spatial dependence (or autocorrelation) and heterogeneity are usually not easily discernable in an empirical sense (Anselin 2001b). They compete as meaningful but mutually exclusive interpretations of the spatial distribution of realworld phenomena. In the spatial statistical and econometric literature, however, substantially more attention has been given to testing for spatial autocorrelation as compared to spatial heterogeneity because the extent of heterogeneity can be

6 228 INTERNATIONAL REGIONAL SCIENCE REVIEW (Vol. 26, No. 3, 2003) assessed using standard statistical tools (Cliff and Ord 1981). Currently, several statistics measuring the extent of spatial autocorrelation are available, and their asymptotics and small sample behavior are well documented. Moran s I and the G statistic of Getis and Ord (1992) are the most commonly used statistics. The statistics have been disaggregated to investigate heterogeneity by means of local versions of the statistics. 7 The payoff of exploiting the above cross-correlation statistics is maximized if theiruse is embedded in a more extensive exploratory spatial data analysis, typically referred to as ESDA. A proper ESDA tool uses generally available statistical functionalities, such as box plots, charts, and histograms, but it typically focuses in particular on the detection of spatial patterns through maps and scatterplots (specifically, the Moran scatterplot) (see Anselin 1996), preferably in a setting with dynamically linked windows. The visualization of spatial relations is the subject of a voluminous literature and obviously bears close ties to geographic information systems (see Haining, Wise, and Ma 1998; Wise, Haining, and Signoretta 1999). Typically, the next step in applied spatial data analysis focuses on confirmatory orexplanatory modeling 8 and starts with misspecification testing in a regression context. Except for a limited number of direct representation cases, most spatial econometric models are spatial process models. The development of misspecification tests in a maximum likelihood framework, the derivation of their asymptotic properties, and the associated small sample properties have been a longstanding interest of various researchers in the field. The toolbox of misspecification tests includes the regression variant of Moran s I (see Cliff and Ord 1981; Kelejian and Prucha 2001) and large sample tests derived by Kelejian and Robinson (1992, 1998). Furthermore, a battery of unidirectional, multidirectional, and robust Lagrange multiplier (LM) tests is on hand (see Anselin and Griffith 1988; Anselin 1988, 2001c; Anselin and Rey 1991; Anselin and Florax 1995b; Anselin et al. 1996; Kelejian and Robinson 1998; de Graaff et al. 2001; Anselin and Moreno forthcoming; Florax and de Graaff forthcoming; Saavedra 2003). 9 The tests focus on detecting spatially correlated residuals due to any cause (i.e., a spatially autoregressive or moving average error structure, erroneously omitted spatially correlated variables, ora nonlinearrelationship), orthey test forwell-defined misspecifications such as a spatial autoregressive error process or an erroneously omitted spatially lagged dependent variable. It may be difficult to reconcile potentially conflicting results of a series of tests. The results of simulation experiments on specification searches indicate, however, that the classical approach, relying on the probability values of the different tests in a model without spatial effects, performs well in terms of finding the correct model (see Florax and Folmer 1992; Florax, Folmer, and Rey forthcoming). Once spatial effects are discovered, there is obviously a need to specify a spatial regression model accounting for such spatial effects and to use an appropriately spatially adapted estimator. A first approach, which recently regained attention, centers on spatial filtering of the existing variables in such a way that one can, in the

7 Florax, van der Vlist / SPATIAL ECONOMETRIC DATA ANALYSIS 229 end, resort to the use of ordinary least squares (see Getis 1995; and, more recently, Griffith and Tiefelsdorf 2002; Getis and Aldstadt forthcoming). A second approach builds on the work by Casetti (1997) and focuses primarily on the specification of spatial heterogeneity by means of geographically weighted regression (Fotheringham, Brunsdon, and Charlton 1998). Most of the work in this area, however, deals with the derivation of maximum likelihood, instrumental variables, and general methods of moments estimators for the model with spatially autoregressive errors, the so-called spatial lag model that contains a spatially lagged dependent variable, or the spatial error component model introduced by Kelejian and Robinson (1995). The use of Bayesian approaches is advocated and applied in LeSage (1997). The early work dealing with the derivation of properties of estimators is reviewed in Cliff and Ord (1981) and Anselin (1988). More recently, Kelejian and Prucha (1998, 1999), Bell and Bockstael (2000), and Lee (2001a, 2001b, 2002) have provided further theoretical results. Results of simulation experiments revealing the small sample properties of various estimators are scarce (see Anselin 1980; Florax 1992; Das, Kelejian, and Prucha 2003), but they invariably show that relying on ordinary least squares is not an adequate estimation procedure. Where do these theoretical advances in spatial econometrics lead us? Does the theoretical work translate into applications of spatial econometric techniques in diverse areas of regional science? To show the proliferation of the use of spatial econometric techniques in applied research, we tie on to the subject index published in each winteredition of the IRSR. The subject index, covering more than sixty major journals in regional science, indicates a broad array of topics, ranging from natural resources, human resources, economic growth and development, and urban and regional issues to social and political issues, as well as other policy and applications. Without aiming to be comprehensive, the review below shows that, particularly in the areas of housing and real estate, as well as economic growth and development, the utilization of spatial econometric data analysis diffuses rapidly. The area of environmental economics and natural resource management is a major growth area that has been catching up recently. Fora long time, the use of spatial data analysis techniques was underused in applications dealing with agricultural, environmental, and natural resource topics. Many of the subjects in this area are, however, inherently spatial. The spread of contaminated water, the diffusion of air pollution (both point- and non-point-source pollution), the location of waste management and otherhazardous facilities, the effect of environmental policy on foreign direct investment and the potential of environmental dumping, contamination patterns of animal disease, land use, and the valuation of nature areas and pollution all constitute subjects to which spatial econometric techniques can be fruitfully applied. Following, among others, the pleas of Bockstael (1996) and Anselin (2001a) to explicitly incorporate space in the analysis of environmental and agricultural topics, a small literature is now emerging. Lark (2000) is one of the first to use spatial econometric techniques dealing with soil organic matter, and recently, Nelson (2002, 197) has brought together a

8 230 INTERNATIONAL REGIONAL SCIENCE REVIEW (Vol. 26, No. 3, 2003) collection of articles to introduce agricultural economists to new analytical approaches involving spatial data. Florax, Voortman, and Brouwer (2002) apply the traditional spatial econometric models to precision agriculture and review the fast-growing literature dealing with variable rate application. Fewer works are available that deal with environmental issues. Rupasingha and Goetz (2001) incorporate space in the analysis of the environmental Kuznets curve, and Eliste and Fredriksson (forthcoming) pay attention to environmental stringency. The spatial econometric analysis of natural resources is gradually starting off by considering deforestation (e.g., Nelson and Hellerstein 1997) and air quality (Arbia and Lafratta 1997; Murdoch, Sandler, and Sargent 1997; Guldman and Kim 2001; Kim, Phipps, and Anselin forthcoming). It should be noted that the spatial econometric techniques used in agri-environmental applications typically boil down to rather straightforward applications of misspecification testing using LM tests and subsequent estimation of the traditional spatial error or spatial lag model. The same applies to the field of human resources. This is a broad area of studies, among other things, including studies on labor markets and unemployment. Molho (1995), Buettner(1999), and Haughton et al. (forthcoming) are good examples of studies dealing with the traditional spatial econometric modeling perspective, although Buettner (1999) adds an interesting example of block bootstrapping for statistical inference in a space-time context. The literature on population-employment dynamics is a second example of studies belonging to the field of human resources. Boarnet s (1994) well-known contribution to this literature broadens the traditional Carlino-Mills model by including spatial spillover effects. Many replications for different regions and time periods are subsequently published. Henry et al. (1999) include an interesting application because it also allows for spatial heterogeneity, and Rey and Boarnet (forthcoming) supply a taxonomic framework to classify different types of spatial simultaneous equation models and discuss problems of identification. Finally, we like to mention the area considering knowledge spillovers of academic institutions as an area where traditional spatial econometric models have been applied. Interesting examples of studies using spatial econometric techniques to model local spatial spillovers of knowledge production include Florax (1992); Anselin, Varga, and Acs (1997); Varga (1998); and Acs (2002), among others. Departures from the more traditional models are more frequent in the areas of economic growth and development, as well as urban and regional issues. Initially, the regional analysis of economic growth and development began by merely incorporating spatial effects (heterogeneity in the form of so-called spatial clubs, as well as spatial dependence) using traditional spatial econometric modeling techniques in a neoclassical theoretical setup (Chatterji and Dewhurst 1996; Rey and Montouri 1999; Fingleton 2003). Subsequently, exploratory spatial data analysis techniques have gained popularity (Rey and Montouri 1999; Le Gallo and Ertur 2003; Mossi et al [this issue]). Interestingly enough, however, considerable effort is now being put into adapting Markov chain analysis to a setting that includes spatial

9 Florax, van der Vlist / SPATIAL ECONOMETRIC DATA ANALYSIS 231 interaction effects (Fingleton 1999a; Rey 2001; Bickenbach and Bode 2003 [this issue]). Finally, the last area for which we note some interesting applications is concerned with the analysis of urban and regional issues. The application of spatial econometric techniques is not limited to one specific topic but again extends to a whole range of topics. First, some studies deal with the inclusion of neighborhood effects in explaining the spatial distribution of indicators related to, for instance, wages (Ioannides forthcoming), crime (Messner and Anselin 2003), health (Ellen, Mijanovich, and Dillman 2001), or schooling (Fotheringham, Charlton, and Brunsdon 2001). Second, there is an extensive literature on housing and real estate. It is obvious that for the assessment of price variation, neighborhood spillovers in prices or rents are likely to be relevant. The empirical analysis of this type goes back to Can (1992) and shows clear evidence of substantial spatial autocorrelation in transaction prices across housing markets, mainly because neighborhoods tend to have similar structural characteristics and share location amenities (see Basu and Thibodeau 1998). Employing spatially referenced estimators in housing and real estate substantially improves the quality of predictions and statistical inferences (Dubin 1998; Gelfand 1998; Clapp, Kim, and Gelfand 2002). The special issue on spatial statistics and real estate (Pace 1998) particularly the articles by Pace, Barry, and Sirmans (1998); Pace, Barry, Clapp, et al. (1998); and Dubin, Pace, and Thibodeau (1999) provides useful overviews of this literature. Recently, Hwang and Quigley (2003) analyzed the time course development of condominium prices in Singapore. Their approach is different from the habitual hedonic pricing model considered almost throughout the literature, in the sense that they use a wideranging time series of georeferenced data to explain the temporal development of prices, taking into account spatial spillovers in an intricate econometric model. Their model has an explicit link to theory. Linking up theory with spatial econometric specifications is also at the heart of the final area that we like to mention. This is the area dealing with interacting agents (Anselin 2002). The interaction among agents is modeled using spatial correlation across jurisdictions. For instance, Bivand and Szymanski (2000) specify the competition among municipalities in a compulsory competitive tendering system for waste management, and Case, Rosen, and Hines (1993) and Brueckner (1998) test for strategic interaction among governments with respect to budget spillovers and fiscal policy interdependence, respectively. The above concise review of applications evidently shows the rapid proliferation of spatial econometric techniques in various subject areas. Many of these applications are still strongly data driven rather than theory driven (Anselin 2002) and commonly use a relatively simple framework of exploratory spatial data analysis, followed by spatial regression modeling extended with misspecification tests. Gradually, however, things are changing, and we are moving beyond the stage where the traditional spatial modeling approach suffices.

10 232 INTERNATIONAL REGIONAL SCIENCE REVIEW (Vol. 26, No. 3, 2003) MOVING BEYOND TRADITIONAL MODELS The articles brought together in this special issue go beyond applying the traditional spatial econometric framework consisting of exploratory spatial data analysis and subsequent model fitting using spatial misspecification tests. They deal with several interesting extensions and new modeling approaches. In this section, we provide some detail on the relevant context for each contribution, and we summarize some of the main results of the articles. The contribution by Paul Elhorst (2003 [this issue]) offers a comprehensive treatment of the specification and estimation of four spatial panel data models that are developed by adapting the familiar traditional panel data specifications. 10 Relatively little work is available on spatial panel data models (Anselin 1988, 2001b; Elhorst 2001), although the relevance of these models is getting more and more evident because of increased data availability as well as the greater potential to model interaction behavior of agents with a firm theoretical basis. The increasing use of panel data sets in applied research in spatial settings necessitates the incorporation of spatial dependence and/or spatial heterogeneity. Elhorst discusses four widely used models: the spatial fixed and random effect models, as well as the fixed and random coefficient spatial error models. He summarizes what can be learned from the general econometric literature on panel data models and adapts the general models to the spatial context. He presents the respective likelihoods and discusses estimation strategies that are useful in applied research. Moreover, he treats potential problems of the spatially adapted versions of the traditional panel data models and suggests workable solutions to these problems. The literature on spatial effects in limited dependent variable models is getting increasingly rich. Kelejian and Prucha (2001), Fleming (forthcoming), and Pinkse (forthcoming) cover misspecification testing in spatial discrete choice models, and McMillen (1992, 1995), Dubin (1995), Pinkse and Slade (1998), Beron and Vijverberg (forthcoming), and LeSage (2000) present classical as well as Bayesian solutions to the estimation of spatial probit and logit models. A model that has received attention in applications rather than in the theoretical spatial econometric literature is the spatial counterpart of the hazard model. Brigitte Waldorf (2003 [this issue]) opens up this area by considering the spatial hazard model from a conceptual point of view. She explores the analogy between duration in time and space and concludes that, notwithstanding the mathematical analogy between time orduration and space ordistance, conceptual problems evoke substantial difficulties in the interpretation of spatial duration models. Following a concise introduction to duration models, she carries out limited experiments demonstrating how spatial hazard models can be used in empirical spatial research. She concludes that the modeling perspective should change from the static to the dynamic perspective to be able to fruitfully analyze spatial phenomena in a hazard framework. Jesús Murand JavierTrívez (2003 [this issue]) take up the discussion on spatial unit roots and spatial cointegration originally initiated by Fingleton (1999b). They

11 Florax, van der Vlist / SPATIAL ECONOMETRIC DATA ANALYSIS 233 argue that spatial dynamics are so much different from temporal dynamics that it is difficult to implement the notions of integration and unit roots in the multivariate spatial case as compared to the univariate time context. For example, the spatial data-generating process that allows for the inclusion of a unit root bears little resemblance to a mechanism of accumulating shocks in time series. The relevance of integration in a spatial setting is therefore still in need of further theoretical guidance and conceptual development. Mur and Trívez use Monte Carlo experiments to show that the risk of obtaining spurious regression results when using integrated variables remains. The symptoms related to unit roots can be identified, but these symptoms may also be caused by other factors. Their experimental results show anomalies, such as unexpected loss of statistical power, for spatial autocorrelation tests. This leads the authors to suggest that much more emphasis should be put on exploratory spatial data analysis, and in applied research, one should be vigilantly aware of the risk of attaining spurious regressions in spatial econometric models. ValterDi Giacinto (2003 [this issue]) argues that measuring the output effect of monetary policy decisions in structural vector autoregression (SVAR) models that neglect spatial feedback orspillovereffects results in serious misspecification. Building on the earlier work by Carlino and DeFina (1999), he carefully treats spatial interdependencies arising through different spatial propagation mechanisms that smooth out across space. Three mechanisms, related to trade channels, financial transmissions, and what he calls other mechanisms (i.e., mainly driven by commuting), are considered. As an extension to existing modeling approaches, Di Giacinto argues that simultaneous propagation between regions occurs, and he therefore suggests accounting for spatial interaction effects in SVAR models by incorporating information on geographical proximity. He considers three different VAR approaches: a model with no interdependencies, a second model with a oneperiod time lag interaction, and a model with contemporaneous feedback allowing for simultaneous propagation of effects across regions. He derives the appropriate maximum likelihood estimators, and in an application using data that have been used before in this literature, he shows that contemporaneous feedback effects of monetary policy decisions should not be ignored. Giuseppe Arbia and Jean Paelinck (2003 [this issue]) present a new approach to the traditional neoclassical growth convergence modeling. In the preceding section, we already indicated various contributions that explicitly incorporate spatial effects in neoclassical growth models, but Arbia and Paelinck take a different route. They propose a Lotka-Volterra predator-prey system to model regional convergence in a continuous-time framework that also allows for the inclusion of geographical effects. They generalize the traditional predator-prey model to a multiregional system and show that the concept of convergence implied in such a model differs from the classical convergence concept. In particular, they demonstrate that each region or system may follow its own trajectory, leading to a series of distinct convergence paths. The classical β-convergence model can be seen as a special case of their Lotka-Volterra model. The parameters of a discrete analogue of

12 234 INTERNATIONAL REGIONAL SCIENCE REVIEW (Vol. 26, No. 3, 2003) the generalized model are estimated using a simultaneous dynamic least squares estimator. Arbia and Paelinck illustrate their approach with a comparison of the empirical results generated for a traditional convergence equation, a spatially conditioned convergence equation, and the Lotka-Volterra model for 119 European regions over the time period from 1980 to The empirical results are satisfactory and point in the same direction for all models considered. The obvious advantage of the Lotka-Volterra model is, however, that it allows for much more flexibility across space. Markov chain theory offers another approach to modeling income convergence. In a spatial setting, this approach has been explored in Fingleton (1999a) and Rey (2001). Bickenbach and Bode (2003) follow up on this work, but they focus on statistical testing. They propose tests of homogeneity and independence over time and across space to counteract the tendency in most Markov chain studies to ignore checking the validity of the statistical assumptions of homogeneity and independence of the transition probabilities underlying the approach. This is a serious omission because the estimated transition probabilities, and hence the limiting income distribution, will be misleading if regions follow different processes. Furthermore, if the income dynamics of one system depends on the dynamics of its neighbors, the transition probabilities should be estimated conditional upon the income class for neighboring regions. Bickenbach and Bode illustrate the importance of testing for the homogeneity and independence using panel data of relative per capita income of U.S. states during the period from 1929 to They find that for both the first half and the second half of the twentieth century, homogeneity over time, as well as spatial homogeneity, is rejected. Their test results also indicate the relevance of considering dependence over space and time. The contribution of Mossi et al. (2003) demonstrates the usefulness of using spatial exploratory techniques in analyzing the spatial distribution of economic growth and perfectly illustrates the value of the testing framework outlined by Bickenbach and Bode (2003). Mossi and his colleagues investigate regional growth dynamics in Brazil during the time period from 1939 to 1998 and empirically establish the relevance of spatial heterogeneity and spatial dependence. Initially, they follow the traditional spatial exploratory data analysis approach, using global and local Moran s I, scatterplots, and choropleth maps. This analysis reveals the existence of two spatial clusters: a low-income cluster in northeast Brazil and a high-income cluster in southeast Brazil. Subsequently, they investigate the dynamics of regional economic growth using Quah s transitional dynamics framework. Following Bickenbach and Bode s work on statistical testing, they assess whether the transition probabilities are constant over time and across space. Their results indicate that time stationarity cannot be rejected during the period from 1939 to 1998, but the transition probabilities are not constant over space.

13 Florax, van der Vlist / SPATIAL ECONOMETRIC DATA ANALYSIS 235 CONCLUSION In this introductory article to the special issue Spatial Econometric Data Analysis: Models, Extensions, and Applications, we have shown the upsurge in the theoretical development and the use of spatial econometric techniques. Arguably, this is related to an intensified interest in spatial dimensions in theoretical research and to the availability of easy-to-use software for visualization, exploratory data analysis, and the estimation of spatial econometric models. We have documented that numerous case studies using spatial econometric techniques are becoming available. They cover such diverse areas as environmental and natural resources (including agriculture), the functioning of labor markets and unemployment, populationemployment dynamics, spatial externalities of various kinds, economic growth models, housing and real estate, and interacting agents. Much of this work is still using rather traditional spatial econometric techniques, particularly exploratory spatial data analysis techniques (Moran s I, the G statistic, scatterplots, and maps), and model fitting with misspecification tests geared toward verifying whether a spatially correlated error structure is applicable or if spatially lagged variables have erroneously been omitted. Things are starting to change, however. The developments in theory and the desirability of having theory rather than data driving the modeling process are gradually steering spatial econometrics away from the traditional techniques. The contributions to this special issue illustrate this development. They focus on space-time modeling, spatial hazard models, structural vector autoregressive models, spatial nonstationarity, and new methods for the specification, testing, and estimation of regional economic growth processes. Most of the articles indicate elements for future research, but we would like to highlight some promising avenues for future research in this introduction as well. First, much more work is needed on space-time modeling. In particular, the extension to general models incorporating spatial, temporal, and space-time correlations would be useful. This holds forpanel data models in general but also formodels focusing on diffusion. Temporal and spatial diffusion models are well established, but their integration into one modeling framework still needs further work. Moreover, the development of misspecification tests is still lagging behind in this area. It would be interesting to bring together a toolbox of unidirectional and multidirectional misspecification tests along the spatial and temporal dimensions. Second, we have a better view now of the conceptual implications of transforming duration in temporal hazard models to distance in spatial hazard models. An interesting further development could be to derive the associated likelihoods with a subsequent focus on estimation issues. In particular, it may be useful to see whether the use of the traditional spatial weights matrix is feasible and simplifies the intricate specification problem. 11 Third, we are starting to better understand the translation of the unit root and cointegration concepts from the time-series literature to the spatial perspective. The concurrent chance of obtaining spurious spatial regressions has been

14 236 INTERNATIONAL REGIONAL SCIENCE REVIEW (Vol. 26, No. 3, 2003) demonstrated in experimental simulation work. Applied empirical work is still lagging behind and may be fruitful to further underpin and demonstrate the relevance of this topic. Fourth, the structural vector autoregressive approach deserves more application in a spatial setting as well. The derivation of the associated likelihoods in this special issue may contribute to increasing its future usage in applied work, but also in this case, further work on the development of misspecification tests is desirable (the only sources to date that deal with multiple-equation models are Anselin and Kelejian 1997; Rey and Boarnet forthcoming). Finally, the contributions focusing on economic growth show that interesting generalizations of the traditional convergence model, epitomizing the relevance of space, are possible. Obviously, further empirical work is necessary, particularly concentrating on conditioning the growth equation in a regional setting and hence solving some of the data availability problems at this spatial scale. Furthermore, in the growth literature, generalized methods of moments estimation is advocated to account for omitted variable bias and endogeneity, and it has been shown to have a substantial influence on the estimated convergence rates (Abreu, Florax, and de Groot forthcoming). Exploring the use of such an estimator in models accounting for spatial effects is an interesting avenue for further research, as is broadening the analysis of economic growth to space-time models, which may eventually help to circumvent the use of a spatial process specification. NOTES 1. See for an overview of Regional Science Association International (RSAI) conferences and access to local Web sites. The results of these special sessions are in Getis, Mur, and Zoller (forthcoming) and Pace, Tiefelsdorf, and LeSage (forthcoming). This special issue contains some of the papers presented at the Dortmund conference. Although this overview focuses on regional science, concurrent developments take place in (quantitative) geography, sociology, agricultural economics, real estate economics and housing, and slowly but steadily also in environmental and natural resource economics. 2. Details about the subject index of the International Regional Science Review (IRSR) ar e pr o- vided in issue number 4 of each volume (see also below). 3. See for an overview of the program. Two papers on spatial econometrics were presented in the Young Scientists session. 4. See, forinstance, Anselin and Bera (1998) and Anselin (2001c, 2003) foran explanation of the distinction between spatial process models and direct representation models. 5. Some of the more popular online spatial econometric software resources are the spatial statistical toolbox of Kelly Pace (see containing MATLAB routines and programs for large spatial samples; SPDEP Spatial Analysis Tools, designed by Roger Bivand (see with spatial autocorrelation and regression routines written in R; and the commercial package Winbugs-Geobugs (see comprising routines for spatial models using the Gibbs sampler and Markov chain Monte Carlo estimation.

15 Florax, van der Vlist / SPATIAL ECONOMETRIC DATA ANALYSIS We discard interesting but more specialized issues such as the specification of weights, edge effects and the modifiable areal unit problem, infill asymptotics, spatial nonstationarity, limited dependent variable models, and so forth. 7. Anselin (1995) refers to the disaggregated statistics as local indicators of spatial association (LISA, for short). Strictly speaking, the local G i statistic does not belong to the LISA class because the overall or global statistic is not equal to the (scaled) sum of the local statistics. 8. Unless the model specification is strongly guided by theory, the distinction between the exploratory and the explanatory phase is much more blurred in the actual research process, and the researcher usually iterates back and forth using tools from each realm (Haining, Wise, and Signoretta 2000). 9. Florax and de Graaff (forthcoming) give a taxonomy of the different misspecification tests and an assessment of their small sample performance in a comparative response surface setting. 10. The term panel data is not used in a strict sense here. It would be more precise to use the term time series of spatial cross-section data, but we want to avoid its wordiness. 11. This goes back to an observation of Jim LeSage, who discussed a conference presentation of the paper on spatial hazard models. REFERENCES Abreu, M., R. J. G. M. Florax, and H. L. F. de Groot A meta-analysis of the speed of convergence in growth regressions. Discussion paper, Tinbergen Institute, Amsterdam. Acs, Z. J Innovation and the growth of cities. Cheltenham, UK: Edward Elgar. Amrhein, C. G Searching for the elusive aggregation effect: Evidence from statistical simulation. Environment and Planning A 27: Amrhein, C. G., and H. Reynolds Using spatial statistics to assess aggregation effects. Geographical Systems 3: Anselin, L Estimation methods for spatial autoregressive structures. Regional Science Dissertation and Monograph Series No. 8. Ithaca, NY: Cornell University Press Spatial econometrics: Methods and models. Boston: Kluwer Academic., ed. 1992a. Space and applied econometrics [Special issue]. Regional Science and urban Economics b. SpaceStat: A program for the analysis of spatial data. Santa Barbara: National Center for Geographic Information and Analysis, University of California Local indicators of spatial association LISA. Geographical Analysis 27: The Moran scatterplot as an ESDA tool to assess local instability in spatial association. In Spatial analytical perspectives on GIS, edited by M. Fischer, H. Scholten, and D. Unwin, London: Taylor & Francis Computing environments for spatial data analysis. Journal of Geographical Systems 2: a. Spatial effects in econometric practice in environmental and resource economics. American Journal of Agricultural Economics 83: b. Spatial econometrics. In Companion to theoretical econometrics, edited by B. Baltagi, Oxford, UK: Blackwell Scientific c. Rao s score test in spatial econometrics. Journal of Statistical Planning and Inference 97: Under the hood: Issues in the specification and interpretation of spatial regression models. Agricultural Economics 27: Spatial externalities. International Regional Science Review 26:

16 238 INTERNATIONAL REGIONAL SCIENCE REVIEW (Vol. 26, No. 3, 2003) Anselin, L., and A. Bera Spatial dependence in linear regression models with an introduction to spatial econometrics. In Handbook of applied economic statistics, edited by A. Ullah and D. E. Giles, New York: Marcel Dekker. Anselin, L., A. Bera, R. Florax, and M. Yoon Simple diagnostic tests for spatial dependence. Regional Science and Urban Economics 26: Anselin, L., and R. J. G. M. Florax, eds. 1995a. New directions in spatial econometrics. Berlin: Springer- Verlag b. Small sample properties of tests for spatial dependence in regression models: Some furtherresults. In New directions in spatial econometrics, edited by L. Anselin and R. J. G. M. Florax, Berlin: Springer-Verlag. Anselin, L., and D. Griffith Do spatial effects really matter in regression analysis? Papers of the Regional Science Association 65: Anselin, L., and S. Hudak Spatial econometrics in practice: A review of software options. Regional Science and Urban Economics 22: Anselin, L., and H. H. Kelejian Testing for spatial error autocorrelation in the presence of endogenous regressors. International Regional Science Review 20: Anselin, L., and R. Moreno. Forthcoming. Properties of tests for spatial error components. Regional Science and Urban Economics 33. Anselin, L., and S. Rey Properties of tests for spatial dependence in linear regression models. Geographical Analysis 23: , eds Spatial econometrics [Special issue]. International Regional Science Review 20. Anselin, L., A. Varga, and Z. Acs Local geographic spillovers between university research and high technology innovations. Journal of Urban Economics 42: Arbia, G Spatial data configuration in statistical analysis of regional economic and related problems. Dordrecht, The Netherlands: Kluwer Academic. Arbia, G., and G. Lafratta Evaluating and updating the sample design in repeated environmental surveys: Monitoring air quality in Padua. Journal of Agricultural, Biological and Environmental Statistics 2: Arbia, G., and J. H. P. Paelinck Spatial econometric modeling of regional convergence in continuous time. International Regional Science Review 26: Bailey, T. C., and A. C. Gatrell Interactive spatial data analysis. Harlow, UK: Longman. Basu, S., and T. G. Thibodeau Analysis of spatial autocorrelation in house prices. Journal of Real Estate Finance and Economics 17: Bell, K., and N. Bockstael Applying generalized moments estimation approach to spatial problems involving micro-level data. Review of Economics and Statistics 82: Beron, K. J., and W. P. M. Vijverberg. Forthcoming. Probit in a spatial context: A Monte Carlo analysis. In Advances in spatial econometrics: Methodology, tools and applications, edited by L. Anselin, R. J. G. M. Florax, and S. J. Rey. Berlin: Springer-Verlag. Bickenbach, F., and E. Bode Evaluating the Markov property in studies of economic convergence. International Regional Science Review 26: Bivand, R., and S. Szymanski Modeling the spatial impact of the introduction of compulsory competitive tendering. Regional Science and Urban Economics 30: Boarnet, M. G An empirical model of intrametropolitan population and employment growth. Papers in Regional Science 73: Bockstael, N. E Modeling economics and ecology: The importance of a spatial perspective. American Journal of Agricultural Economics 78: Brueckner, J. K Testing for strategic interaction among local governments: The case of growth controls. Journal of Urban Economics 44: Buettner, T The effect of unemployment, aggregate wages, and spatial contiguity on local wages: An investigation with German district level data. Papers in Regional Science 78:

17 Florax, van der Vlist / SPATIAL ECONOMETRIC DATA ANALYSIS 239 Can, A Specification and estimation of hedonic housing price models. Regional Science and Urban Economics 22: Carlino, G. A., and R. DeFina The differential regional effects of monetary policy: Evidence from the U.S. states. Journal of Regional Science 80: Case, A., H. S. Rosen, and J. R. Hines Budget spillovers and fiscal policy interdependence: Evidence from the states. Journal of Public Economics 52: Casetti, E The expansion method, mathematical modeling and spatial econometrics. International Regional Science Review 20: Chatterji, M., and J. Dewhurst Convergence clubs and relative economic performance in Great Britain. Regional Studies 30: Clapp, J. M., H.-J. Kim, and A. E. Gelfand Predicting spatial patterns of house prices using LPR and Bayesian smoothing. Real Estate Economics 30: Cliff, A. D., and J. K. Ord Spatial autocorrelation. London: Pion Spatial processes: Models and applications. London: Pion. Conley, T. G GMM estimation with cross-sectional dependence. Journal of Econometrics 92: Cressie, N Statistics for spatial data. Rev. ed. New York: John Wiley. Das, D., H. Kelejian, and I. Prucha Finite sample properties of estimators of spatial autoregressive models with autoregressive disturbances. Papers in Regional Science 82: de Graaff, T., R. J. G. M. Florax, P. Nijkamp, and A. Reggiani A general misspecification test for spatial regression models: Heteroskedasticity, dependence, and nonlinearity. Journal of Regional Science 41: Di Giacinto, V Differential regional effects of monetary policy: A geographical SVAR approach. International Regional Science Review 26: Dubin, R Estimation of regression coefficients in the presence of spatially autocorrelated errors. Review of Economics and Statistics 70: Estimating logit models with spatial dependence. In New directions in spatial econometrics, edited by L. Anselin and R. J. G. M. Florax. Berlin: Springer-Verlag Predicting house prices using multiple listings data. Journal of Real Estate Finance and Economics 17: Dubin, R., R. Pace, and T. Thibodeau Spatial autoregression techniques for real estate data. Journal of Real Estate Literature 7: Elhorst, J. P Dynamic models in space and time. Geographical Analysis 33: Specification and estimation of spatial panel data models. International Regional Science Review 26: Eliste, P., and P. G. Fredriksson. Forthcoming. Does trade liberalization cause a race to the bottom in environmental policies? A spatial econometric analysis. In Advances in spatial econometrics: Methodology, tools and applications, edited by L. Anselin, R. J. G. M. Florax, and S. J. Rey. Berlin: Springer-Verlag. Ellen, I., T. Mijanovich, and K. Dillman Neighborhood effects on health. Journal of Urban Affairs 23: Fingleton, B. 1999a. Estimates of time to economic convergence: An analysis of regions of the European Union. International Regional Science Review 22: b. Spurious spatial regression: Some Monte Carlo results with a spatial unit root and spatial cointegration. Journal of Regional Science 39: Equilibrium and economic growth: Spatial econometric models and simulations. Journal of Regional Science 41: , ed European regional growth. Berlin: Springer-Verlag. Fleming, M. Forthcoming. Techniques for estimating spatially dependent discrete choice models. In Advances in spatial econometrics: Methodology, tools and applications, edited by L. Anselin, R. J. G. M. Florax, and S. J. Rey. Berlin: Springer-Verlag.

18 240 INTERNATIONAL REGIONAL SCIENCE REVIEW (Vol. 26, No. 3, 2003) Florax, R. J. G. M The university: A regional booster? Economic impacts of academic knowledge infrastructure. Aldershot, UK: Avebury. Florax, R. J. G. M., and T. de Graaff. Forthcoming. The performance of diagnostic tests for spatial dependence in linear regression models: A meta-analysis of simulation studies. In Advances in spatial econometrics: Methodology, tools and applications, edited by L. Anselin, R. J. G. M. Florax, and S. J. Rey. Berlin: Springer-Verlag. Florax, R. J. G. M., and H. Folmer Specification and estimation of spatial linear regression models. Regional Science and Urban Economics 22: Florax, R. J. G. M., H. Folmer, and S. J. Rey. Forthcoming. Specification searches in spatial econometrics: The relevance of Hendry s methodology. Regional Science and Urban Economics 33. Florax, R. J. G. M., and P. Nijkamp. Forthcoming. Misspecification in linear spatial regression models. In Encyclopedia of social measurement, edited by K. Kempf-Leonard. San Diego: Academic Press. Florax, R. J. G. M., R. L. Voortman, and J. Brouwer Spatial dimensions of precision agriculture: A spatial econometric analysis of millet yield on Sahelian coversands. Agricultural Economics 27: Fotheringham, A., C. Brunsdon, and M. Charlton Geographically weighted regression: A natural evolution of the expansion method forspatial data analysis. Environment and Planning A 30: Fotheringham, A., M. Charlton, and C. Brunsdon Spatial variation in school performance. Geographical and Environmental Modelling 5: Fujita, M., and P. Krugman. Forthcoming. The new economic geography: Where now, and to where. Papers in Regional Science 83. Fujita, M., P. Krugman, and A. J. Venables The spatial economy. Cambridge, MA: MIT Press. Gelfand, A. E Spatio-temporal modeling of residential sales data. Journal of Business & Economic Statistics 16: Getis, A Spatial filtering in a regression framework: Examples using data on urban crime, regional inequality, and government expenditures. In New directions in spatial econometrics, edited by L. Anselin and R. J. G. M. Florax, Berlin: Springer-Verlag. Getis, A., and J. Aldstadt. Forthcoming. On the specification of the spatial weights matrix. Geographical Analysis 35. Getis, A., J. Mur, and H. G. Zoller, eds. Forthcoming. Spatial econometrics and spatial statistics. Basingstoke, UK: Palgrave Macmillan. Getis, A., and K. J. Ord The analysis of spatial association by means of distance statistics. Geographical Analysis 24: Goodchild, M. F., L. Anselin, R. Appelbaum, and B. Harthorn Toward spatially integrated social science. International Regional Science Review 23: Griffith, D. A Advanced spatial statistics. Dordrecht, The Netherlands: Kluwer. Griffith, D. A., and M. Tiefelsdorf Semi-parametric filtering of spatial autocorrelation: The eigenvector approach. Paper presented at the North American meetings of the Regional Science Association International, November, San Juan, Puerto Rico. Griffith, D., D. Wong, and T. Whitfield. Forthcoming. Exploring relationships between the global and regional measures of spatial autocorrelation. Journal of Regional Science 43. Guldman, J., and H. Kim Modeling air quality in urban areas. Geographical Analysis 33: Haining, R., S. Wise, and J. Ma Exploratory spatial data analysis in a geographical information system environment. The Statistician 47: Haining, R., S. Wise, and P. Signoretta Providing scientific visualization for spatial data analysis: Criteria and an assessment of SAGE. Journal of Geographical Systems 2: Haughton, J., Y. Aragon, D. Jaughton, E. Leconte, E. Malin, A. Ruiz-Gazen, and C. Thomas-Agnan. Forthcoming. Explaining the pattern of regional unemployment: The case of the Midi-Pyrénées. Papers in Regional Science 82.

19 Florax, van der Vlist / SPATIAL ECONOMETRIC DATA ANALYSIS 241 Henry, M. S., B. Schmitt, K. Kristensen, D. L. Barkley, and S. Bao Extending Carlino-Mills models to examine urban size and growth impacts on proximate rural areas. Growth and Change 30: Hwang, M., and J. M. Quigley Price discovery in time and space: The course of condominium prices in Singapore. Paper presented at the meetings of the Western Regional Science Association, November, Rio Rico, AZ. Ioannides, Y. M. Forthcoming. Economic geography and the spatial evolution of wages in the United States. In Advances in spatial econometrics: Methodology, tools and applications, edited by L. Anselin, R. J. G. M. Florax, and S. J. Rey. Berlin: Springer-Verlag. Isard, W Location and space economy: A general theory relating to industrial location, market areas, land use, trade, and urban structure. Cambridge, MA: MIT Press. Kaluzny, S. P., S. C. Vega, T. P. Cardoso, and A. A. Shelly S+SpatialStats user s manual. New York: Springer-Verlag. Kelejian, H. H., and I. Prucha A generalized spatial two stage least square procedure for estimating a spatial autoregressive model with autoregressive disturbances. Journal of Real Estate Finance and Economics 17: A generalized moments estimator for the autoregressive parameter in a spatial model. International Economic Review 40: On the asymptotic distribution of the Moran I test statistic with applications. Journal of Econometrics 104: Kelejian, H. H., and D. P. Robinson Spatial autocorrelation: A new computationally simple test with an application to percapita county policy expenditures. Regional Science and Urban Economics 22: Spatial correlation: A suggested alternative to the autoregressive model. In New directions in spatial econometrics, edited by L. Anselin and R. J. G. M. Florax, Berlin: Springer- Verlag A suggested test for spatial autocorrelation and/or heteroskedasticity and corresponding Monte Carlo results. Regional Science and Urban Economics 28: Kim, C.-W., T. T. Phipps, and L. Anselin. Forthcoming. Measuring the benefits of air quality improvement: A spatial hedonic approach. Journal of Environmental Economics and Management. Lark, R Regression analysis with spatially autocorrelated error: A simulation studies and application to mapping of soil organic matter. International Journal of Geographical Information Science 14: Le Gallo, J., and C. Ertur Exploratory spatial data analysis of the distribution of regional per capita GDP in Europe, Papers in Regional Science 82. Lee, L.-F. 2001a. Asymptotic distributions of quasi-maximum likelihood estimators for spatial econometric models: I. Spatial autoregressive processes: Mixed regressive, spatial autoregressive models. Working paper, Department of Economics, The Ohio State University, Columbus, OH b. Asymptotic distributions of quasi-maximum likelihood estimators for spatial econometric models: II. Mixed regressive, spatial autoregressive models. Working paper, Department of Economics, The Ohio State University, Columbus, OH Consistency and efficiency of least squares estimation for mixed regressive, spatial autoregressive models. Econometric Theory 18: LeSage, J. P Bayesian estimation of spatial autoregressive models. International Regional Science Review 20: Bayesian estimation of limited dependent variable spatial autoregressive models. Geographical Analysis 32: McMillen, D. P Probit with spatial autocorrelation. Journal of Regional Science 32: Spatial effects in probit models: A Monte Carlo investigation. In New directions in spatial econometrics, edited by L. Anselin and R. J. G. M. Florax. Berlin: Springer-Verlag.

20 242 INTERNATIONAL REGIONAL SCIENCE REVIEW (Vol. 26, No. 3, 2003) Messner, S., and L. Anselin Spatial analyses of homicide with areal data. In Spatially integrated social science, edited by M. Goodchild and D. Janelle. New York: Oxford University Press. Molho, I Spatial autocorrelation in British unemployment. Journal of Regional Science 35: Mossi, M. B., P. Aroca, I. J. Fernandez, and C. R. Azzoni Growth dynamics and space in Brazil. International Regional Science Review 26: Mur, J., and F. J. Trívez Unit roots and deterministic trends in spatial econometric models. International Regional Science Review 26: Murdoch, J. C., T. Sandler, and K. Sargent A tale of two collectives: Sulfur versus nitrogen oxides emission reduction in Europe. Economica 64: Nelson, G. C., ed Spatial analysis for agricultural economists [Special issue]. Agricultural Economics 27. Nelson, G. C., and D. Hellerstein Do roads cause deforestation? Using satellite images in econometric analysis of land use. American Journal of Agricultural Economics 79: Pace, R. K Performing large spatial regressions and autoregressions. Economics Letters 54: , ed Spatial statistics and real estate [Special issue]. Journal of Real Estate Finance and Economics 17. Pace, R. K., and R. Barry. 1997a. Sparse spatial autoregressions. Statistics and Probability Letters 33: b. Quick computation of spatial autoregressive estimators. Geographical Analysis 29: Pace, R. K., R. Barry, J. M. Clapp, and M. Rodiquez Spatiotemporal autoregressive models of neighborhood effects. Journal of Real Estate Finance and Economics 17: Pace, R. K., R. Barry, and C. F. Sirmans Spatial statistics and real estate. Journal of Real Estate Finance and Economics 17: Pace, R. K., M. Tiefelsdorf, and J. P. LeSage, eds. Forthcoming. Spatial econometrics [Special issue]. Geographical Analysis 35. Paelinck, J. H. P., and L. H. Klaassen Spatial econometrics. Farnborough, UK: Saxon House. Pinkse, J. Forthcoming. Moran-flavored tests with nuisance parameter. In Advances in spatial econometrics: Methodology, tools and applications, edited by L. Anselin, R. J. G. M. Florax, and S. J. Rey. Berlin: Springer-Verlag. Pinkse, J., and M. E. Slade Contracting in space: An application of spatial statistics to discretechoice models. Journal of Econometrics 85: Rey, S. J Spatial empirics for economic growth and convergence. Geographical Analysis 33: Rey, S. J., and M. G. Boarnet. Forthcoming. A taxonomy of spatial econometric models for simultaneous equations systems. In Advances in spatial econometrics: Methodology, tools and applications, edited by L. Anselin, R. J. G. M. Florax, and S. J. Rey. Berlin: Springer-Verlag. Rey, S. J., and B. D. Montouri U.S. regional income convergence: A spatial econometric perspective. Regional Studies 33: Rupasingha, A., and S. J. Goetz The environmental Kuznets curve for US counties: A spatial analysis. Paper presented at the North American meetings of the Regional Science Association International, November, Charleston, SC. Saavedra, L. A Tests for spatial lag dependence based on method of moments estimation. Regional Science and Urban Economics 33: Smirnov, O., and L. Anselin Fast maximum likelihood estimation of very large spatial autoregressive models: A characteristic polynomial approach. Computational Statistics and Data Analysis 35: Varga, A University research and regional innovation: A spatial econometric analysis of academic technology transfers. Dordrecht, The Netherlands: Kluwer Academic.

21 Florax, van der Vlist / SPATIAL ECONOMETRIC DATA ANALYSIS 243 Waldorf, B Spatial patterns and processes in a longitudinal framework. International Regional Science Review 26: Wise, S. M., R. P. Haining, and P. Signoretta Scientific visualization and the exploratory analysis of area-based data. Environment and Planning A 31:

The primary goal of this thesis was to understand how the spatial dependence of

The primary goal of this thesis was to understand how the spatial dependence of 5 General discussion 5.1 Introduction The primary goal of this thesis was to understand how the spatial dependence of consumer attitudes can be modeled, what additional benefits the recovering of spatial

More information

COURSES: 1. Short Course in Econometrics for the Practitioner (P000500) 2. Short Course in Econometric Analysis of Cointegration (P000537)

COURSES: 1. Short Course in Econometrics for the Practitioner (P000500) 2. Short Course in Econometric Analysis of Cointegration (P000537) Get the latest knowledge from leading global experts. Financial Science Economics Economics Short Courses Presented by the Department of Economics, University of Pretoria WITH 2015 DATES www.ce.up.ac.za

More information

New Tools for Spatial Data Analysis in the Social Sciences

New Tools for Spatial Data Analysis in the Social Sciences New Tools for Spatial Data Analysis in the Social Sciences Luc Anselin University of Illinois, Urbana-Champaign [email protected] edu Outline! Background! Visualizing Spatial and Space-Time Association!

More information

Master of Mathematical Finance: Course Descriptions

Master of Mathematical Finance: Course Descriptions Master of Mathematical Finance: Course Descriptions CS 522 Data Mining Computer Science This course provides continued exploration of data mining algorithms. More sophisticated algorithms such as support

More information

Marketing Mix Modelling and Big Data P. M Cain

Marketing Mix Modelling and Big Data P. M Cain 1) Introduction Marketing Mix Modelling and Big Data P. M Cain Big data is generally defined in terms of the volume and variety of structured and unstructured information. Whereas structured data is stored

More information

Fairfield Public Schools

Fairfield Public Schools Mathematics Fairfield Public Schools AP Statistics AP Statistics BOE Approved 04/08/2014 1 AP STATISTICS Critical Areas of Focus AP Statistics is a rigorous course that offers advanced students an opportunity

More information

Spatial Dependence in Commercial Real Estate

Spatial Dependence in Commercial Real Estate Spatial Dependence in Commercial Real Estate Andrea M. Chegut a, Piet M. A. Eichholtz a, Paulo Rodrigues a, Ruud Weerts a Maastricht University School of Business and Economics, P.O. Box 616, 6200 MD,

More information

Better decision making under uncertain conditions using Monte Carlo Simulation

Better decision making under uncertain conditions using Monte Carlo Simulation IBM Software Business Analytics IBM SPSS Statistics Better decision making under uncertain conditions using Monte Carlo Simulation Monte Carlo simulation and risk analysis techniques in IBM SPSS Statistics

More information

INDIRECT INFERENCE (prepared for: The New Palgrave Dictionary of Economics, Second Edition)

INDIRECT INFERENCE (prepared for: The New Palgrave Dictionary of Economics, Second Edition) INDIRECT INFERENCE (prepared for: The New Palgrave Dictionary of Economics, Second Edition) Abstract Indirect inference is a simulation-based method for estimating the parameters of economic models. Its

More information

Analysis of Financial Time Series

Analysis of Financial Time Series Analysis of Financial Time Series Analysis of Financial Time Series Financial Econometrics RUEY S. TSAY University of Chicago A Wiley-Interscience Publication JOHN WILEY & SONS, INC. This book is printed

More information

GeoDa: An Introduction to Spatial Data Analysis

GeoDa: An Introduction to Spatial Data Analysis Geographical Analysis ISSN 0016-7363 GeoDa: An Introduction to Spatial Data Analysis Luc Anselin 1, Ibnu Syabri 2, Youngihn Kho 1 1 Spatial Analysis Laboratory, Department of Geography, University of Illinois,

More information

Geographically Weighted Regression

Geographically Weighted Regression Geographically Weighted Regression CSDE Statistics Workshop Christopher S. Fowler PhD. February 1 st 2011 Significant portions of this workshop were culled from presentations prepared by Fotheringham,

More information

WATER INTERACTIONS WITH ENERGY, ENVIRONMENT AND FOOD & AGRICULTURE Vol. II Spatial Data Handling and GIS - Atkinson, P.M.

WATER INTERACTIONS WITH ENERGY, ENVIRONMENT AND FOOD & AGRICULTURE Vol. II Spatial Data Handling and GIS - Atkinson, P.M. SPATIAL DATA HANDLING AND GIS Atkinson, P.M. School of Geography, University of Southampton, UK Keywords: data models, data transformation, GIS cycle, sampling, GIS functionality Contents 1. Background

More information

ID: U000060. Abstract. Urban growth

ID: U000060. Abstract. Urban growth 1 ID: U000060 Abstract Urban growth refers to the process of growth and decline of economic agglomerations. The pattern of concentration of economic activity and its evolution have been found to be an

More information

Geostatistics Exploratory Analysis

Geostatistics Exploratory Analysis Instituto Superior de Estatística e Gestão de Informação Universidade Nova de Lisboa Master of Science in Geospatial Technologies Geostatistics Exploratory Analysis Carlos Alberto Felgueiras [email protected]

More information

Is the Forward Exchange Rate a Useful Indicator of the Future Exchange Rate?

Is the Forward Exchange Rate a Useful Indicator of the Future Exchange Rate? Is the Forward Exchange Rate a Useful Indicator of the Future Exchange Rate? Emily Polito, Trinity College In the past two decades, there have been many empirical studies both in support of and opposing

More information

Local outlier detection in data forensics: data mining approach to flag unusual schools

Local outlier detection in data forensics: data mining approach to flag unusual schools Local outlier detection in data forensics: data mining approach to flag unusual schools Mayuko Simon Data Recognition Corporation Paper presented at the 2012 Conference on Statistical Detection of Potential

More information

Service courses for graduate students in degree programs other than the MS or PhD programs in Biostatistics.

Service courses for graduate students in degree programs other than the MS or PhD programs in Biostatistics. Course Catalog In order to be assured that all prerequisites are met, students must acquire a permission number from the education coordinator prior to enrolling in any Biostatistics course. Courses are

More information

Location matters. 3 techniques to incorporate geo-spatial effects in one's predictive model

Location matters. 3 techniques to incorporate geo-spatial effects in one's predictive model Location matters. 3 techniques to incorporate geo-spatial effects in one's predictive model Xavier Conort [email protected] Motivation Location matters! Observed value at one location is

More information

CHAPTER 11. AN OVEVIEW OF THE BANK OF ENGLAND QUARTERLY MODEL OF THE (BEQM)

CHAPTER 11. AN OVEVIEW OF THE BANK OF ENGLAND QUARTERLY MODEL OF THE (BEQM) 1 CHAPTER 11. AN OVEVIEW OF THE BANK OF ENGLAND QUARTERLY MODEL OF THE (BEQM) This model is the main tool in the suite of models employed by the staff and the Monetary Policy Committee (MPC) in the construction

More information

How To Understand The Theory Of Probability

How To Understand The Theory Of Probability Graduate Programs in Statistics Course Titles STAT 100 CALCULUS AND MATR IX ALGEBRA FOR STATISTICS. Differential and integral calculus; infinite series; matrix algebra STAT 195 INTRODUCTION TO MATHEMATICAL

More information

REAL BUSINESS CYCLE THEORY METHODOLOGY AND TOOLS

REAL BUSINESS CYCLE THEORY METHODOLOGY AND TOOLS Jakub Gazda 42 Jakub Gazda, Real Business Cycle Theory Methodology and Tools, Economics & Sociology, Vol. 3, No 1, 2010, pp. 42-48. Jakub Gazda Department of Microeconomics Poznan University of Economics

More information

Obesity in America: A Growing Trend

Obesity in America: A Growing Trend Obesity in America: A Growing Trend David Todd P e n n s y l v a n i a S t a t e U n i v e r s i t y Utilizing Geographic Information Systems (GIS) to explore obesity in America, this study aims to determine

More information

Spatial Analysis of Five Crime Statistics in Turkey

Spatial Analysis of Five Crime Statistics in Turkey Spatial Analysis of Five Crime Statistics in Turkey Saffet ERDOĞAN, M. Ali DERELİ, Mustafa YALÇIN, Turkey Key words: Crime rates, geographical information systems, spatial analysis. SUMMARY In this study,

More information

Course Descriptions Master of Science in Finance Program University of Macau

Course Descriptions Master of Science in Finance Program University of Macau Course Descriptions Master of Science in Finance Program University of Macau Principles of Economics This course provides the foundation in economics. The major topics include microeconomics, macroeconomics

More information

Fractionally integrated data and the autodistributed lag model: results from a simulation study

Fractionally integrated data and the autodistributed lag model: results from a simulation study Fractionally integrated data and the autodistributed lag model: results from a simulation study Justin Esarey July 1, 215 Abstract Two contributions in this issue, Grant and Lebo (215) and Keele, Linn

More information

South Carolina College- and Career-Ready (SCCCR) Probability and Statistics

South Carolina College- and Career-Ready (SCCCR) Probability and Statistics South Carolina College- and Career-Ready (SCCCR) Probability and Statistics South Carolina College- and Career-Ready Mathematical Process Standards The South Carolina College- and Career-Ready (SCCCR)

More information

The consumer purchase journey and the marketing mix model

The consumer purchase journey and the marketing mix model Dynamic marketing mix modelling and digital attribution 1 Introduction P.M Cain Digital media attribution aims to identify the combination of online marketing activities and touchpoints contributing to

More information

REFERENCES. Anderson, T.W., (1958) Introduction to Multivariate Statistical Analysis, Wiley: New York.

REFERENCES. Anderson, T.W., (1958) Introduction to Multivariate Statistical Analysis, Wiley: New York. REFERENCES Anderson, T.W., (1958) Introduction to Multivariate Statistical Analysis, Wiley: New York. Anselin, L. (1988) Spatial Econometrics, Kluwer: Dordrecht Anselin, L. (1995) Local measures of spatial

More information

The Macroeconomic Effects of Tax Changes: The Romer-Romer Method on the Austrian case

The Macroeconomic Effects of Tax Changes: The Romer-Romer Method on the Austrian case The Macroeconomic Effects of Tax Changes: The Romer-Romer Method on the Austrian case By Atila Kilic (2012) Abstract In 2010, C. Romer and D. Romer developed a cutting-edge method to measure tax multipliers

More information

Handling attrition and non-response in longitudinal data

Handling attrition and non-response in longitudinal data Longitudinal and Life Course Studies 2009 Volume 1 Issue 1 Pp 63-72 Handling attrition and non-response in longitudinal data Harvey Goldstein University of Bristol Correspondence. Professor H. Goldstein

More information

Why Taking This Course? Course Introduction, Descriptive Statistics and Data Visualization. Learning Goals. GENOME 560, Spring 2012

Why Taking This Course? Course Introduction, Descriptive Statistics and Data Visualization. Learning Goals. GENOME 560, Spring 2012 Why Taking This Course? Course Introduction, Descriptive Statistics and Data Visualization GENOME 560, Spring 2012 Data are interesting because they help us understand the world Genomics: Massive Amounts

More information

Curriculum - Doctor of Philosophy

Curriculum - Doctor of Philosophy Curriculum - Doctor of Philosophy CORE COURSES Pharm 545-546.Pharmacoeconomics, Healthcare Systems Review. (3, 3) Exploration of the cultural foundations of pharmacy. Development of the present state of

More information

Time series analysis as a framework for the characterization of waterborne disease outbreaks

Time series analysis as a framework for the characterization of waterborne disease outbreaks Interdisciplinary Perspectives on Drinking Water Risk Assessment and Management (Proceedings of the Santiago (Chile) Symposium, September 1998). IAHS Publ. no. 260, 2000. 127 Time series analysis as a

More information

Calculating the Probability of Returning a Loan with Binary Probability Models

Calculating the Probability of Returning a Loan with Binary Probability Models Calculating the Probability of Returning a Loan with Binary Probability Models Associate Professor PhD Julian VASILEV (e-mail: [email protected]) Varna University of Economics, Bulgaria ABSTRACT The

More information

Teaching Multivariate Analysis to Business-Major Students

Teaching Multivariate Analysis to Business-Major Students Teaching Multivariate Analysis to Business-Major Students Wing-Keung Wong and Teck-Wong Soon - Kent Ridge, Singapore 1. Introduction During the last two or three decades, multivariate statistical analysis

More information

Java Modules for Time Series Analysis

Java Modules for Time Series Analysis Java Modules for Time Series Analysis Agenda Clustering Non-normal distributions Multifactor modeling Implied ratings Time series prediction 1. Clustering + Cluster 1 Synthetic Clustering + Time series

More information

SYSTEMS OF REGRESSION EQUATIONS

SYSTEMS OF REGRESSION EQUATIONS SYSTEMS OF REGRESSION EQUATIONS 1. MULTIPLE EQUATIONS y nt = x nt n + u nt, n = 1,...,N, t = 1,...,T, x nt is 1 k, and n is k 1. This is a version of the standard regression model where the observations

More information

Data Isn't Everything

Data Isn't Everything June 17, 2015 Innovate Forward Data Isn't Everything The Challenges of Big Data, Advanced Analytics, and Advance Computation Devices for Transportation Agencies. Using Data to Support Mission, Administration,

More information

Chapter 1. Vector autoregressions. 1.1 VARs and the identi cation problem

Chapter 1. Vector autoregressions. 1.1 VARs and the identi cation problem Chapter Vector autoregressions We begin by taking a look at the data of macroeconomics. A way to summarize the dynamics of macroeconomic data is to make use of vector autoregressions. VAR models have become

More information

Current Standard: Mathematical Concepts and Applications Shape, Space, and Measurement- Primary

Current Standard: Mathematical Concepts and Applications Shape, Space, and Measurement- Primary Shape, Space, and Measurement- Primary A student shall apply concepts of shape, space, and measurement to solve problems involving two- and three-dimensional shapes by demonstrating an understanding of:

More information

Digital Cadastral Maps in Land Information Systems

Digital Cadastral Maps in Land Information Systems LIBER QUARTERLY, ISSN 1435-5205 LIBER 1999. All rights reserved K.G. Saur, Munich. Printed in Germany Digital Cadastral Maps in Land Information Systems by PIOTR CICHOCINSKI ABSTRACT This paper presents

More information

Currency Unions and Irish External Trade. Christine Dwane Trinity College Dublin. Philip R. Lane, IIIS, Trinity College Dublin & CEPR

Currency Unions and Irish External Trade. Christine Dwane Trinity College Dublin. Philip R. Lane, IIIS, Trinity College Dublin & CEPR Institute for International Integration Studies IIIS Discussion Paper No.189 / November 2006 Currency Unions and Irish External Trade Christine Dwane Trinity College Dublin Philip R. Lane, IIIS, Trinity

More information

Time Series Analysis

Time Series Analysis JUNE 2012 Time Series Analysis CONTENT A time series is a chronological sequence of observations on a particular variable. Usually the observations are taken at regular intervals (days, months, years),

More information

Masters in Financial Economics (MFE)

Masters in Financial Economics (MFE) Masters in Financial Economics (MFE) Admission Requirements Candidates must submit the following to the Office of Admissions and Registration: 1. Official Transcripts of previous academic record 2. Two

More information

Bootstrapping Big Data

Bootstrapping Big Data Bootstrapping Big Data Ariel Kleiner Ameet Talwalkar Purnamrita Sarkar Michael I. Jordan Computer Science Division University of California, Berkeley {akleiner, ameet, psarkar, jordan}@eecs.berkeley.edu

More information

Geographically weighted visualization interactive graphics for scale-varying exploratory analysis

Geographically weighted visualization interactive graphics for scale-varying exploratory analysis Geographically weighted visualization interactive graphics for scale-varying exploratory analysis Chris Brunsdon 1, Jason Dykes 2 1 Department of Geography Leicester University Leicester LE1 7RH [email protected]

More information

DATA QUALITY AND SCALE IN CONTEXT OF EUROPEAN SPATIAL DATA HARMONISATION

DATA QUALITY AND SCALE IN CONTEXT OF EUROPEAN SPATIAL DATA HARMONISATION DATA QUALITY AND SCALE IN CONTEXT OF EUROPEAN SPATIAL DATA HARMONISATION Katalin Tóth, Vanda Nunes de Lima European Commission Joint Research Centre, Ispra, Italy ABSTRACT The proposal for the INSPIRE

More information

Geographical Information Systems (GIS) and Economics 1

Geographical Information Systems (GIS) and Economics 1 Geographical Information Systems (GIS) and Economics 1 Henry G. Overman (London School of Economics) 5 th January 2006 Abstract: Geographical Information Systems (GIS) are used for inputting, storing,

More information

MSc Finance and Economics detailed module information

MSc Finance and Economics detailed module information MSc Finance and Economics detailed module information Example timetable Please note that information regarding modules is subject to change. TERM 1 TERM 2 TERM 3 INDUCTION WEEK EXAM PERIOD Week 1 EXAM

More information

MASTER IN ECONOMICS AND FINANCE

MASTER IN ECONOMICS AND FINANCE MASTER IN ECONOMICS AND FINANCE The document presents the structure of the master program (and the professors in charge of each course) in 2014 2015. Courses, workshops, etc. are ordered primarily by the

More information

A STATISTICS COURSE FOR ELEMENTARY AND MIDDLE SCHOOL TEACHERS. Gary Kader and Mike Perry Appalachian State University USA

A STATISTICS COURSE FOR ELEMENTARY AND MIDDLE SCHOOL TEACHERS. Gary Kader and Mike Perry Appalachian State University USA A STATISTICS COURSE FOR ELEMENTARY AND MIDDLE SCHOOL TEACHERS Gary Kader and Mike Perry Appalachian State University USA This paper will describe a content-pedagogy course designed to prepare elementary

More information

Curriculum Doctoral Program in Business Administration Curriculum Amended in Academic Year 2004

Curriculum Doctoral Program in Business Administration Curriculum Amended in Academic Year 2004 Curriculum Doctoral Program in Business Administration Curriculum Amended in Academic Year 2004 1. Curriculum Name : Doctoral Program in Business Administration 2. The Degree : Doctor of Business Administration

More information

A Trading Strategy Based on the Lead-Lag Relationship of Spot and Futures Prices of the S&P 500

A Trading Strategy Based on the Lead-Lag Relationship of Spot and Futures Prices of the S&P 500 A Trading Strategy Based on the Lead-Lag Relationship of Spot and Futures Prices of the S&P 500 FE8827 Quantitative Trading Strategies 2010/11 Mini-Term 5 Nanyang Technological University Submitted By:

More information

NTC Project: S01-PH10 (formerly I01-P10) 1 Forecasting Women s Apparel Sales Using Mathematical Modeling

NTC Project: S01-PH10 (formerly I01-P10) 1 Forecasting Women s Apparel Sales Using Mathematical Modeling 1 Forecasting Women s Apparel Sales Using Mathematical Modeling Celia Frank* 1, Balaji Vemulapalli 1, Les M. Sztandera 2, Amar Raheja 3 1 School of Textiles and Materials Technology 2 Computer Information

More information

Adaptive Demand-Forecasting Approach based on Principal Components Time-series an application of data-mining technique to detection of market movement

Adaptive Demand-Forecasting Approach based on Principal Components Time-series an application of data-mining technique to detection of market movement Adaptive Demand-Forecasting Approach based on Principal Components Time-series an application of data-mining technique to detection of market movement Toshio Sugihara Abstract In this study, an adaptive

More information

Do Commodity Price Spikes Cause Long-Term Inflation?

Do Commodity Price Spikes Cause Long-Term Inflation? No. 11-1 Do Commodity Price Spikes Cause Long-Term Inflation? Geoffrey M.B. Tootell Abstract: This public policy brief examines the relationship between trend inflation and commodity price increases and

More information

Imputing Values to Missing Data

Imputing Values to Missing Data Imputing Values to Missing Data In federated data, between 30%-70% of the data points will have at least one missing attribute - data wastage if we ignore all records with a missing value Remaining data

More information

On Correlating Performance Metrics

On Correlating Performance Metrics On Correlating Performance Metrics Yiping Ding and Chris Thornley BMC Software, Inc. Kenneth Newman BMC Software, Inc. University of Massachusetts, Boston Performance metrics and their measurements are

More information

This article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research and

This article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research and This article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research and education use, including for instruction at the authors institution

More information

MASTER OF SCIENCE FINANCIAL ECONOMICS ABAC SCHOOL OF MANAGEMENT ASSUMPTION UNIVERSITY OF THAILAND

MASTER OF SCIENCE FINANCIAL ECONOMICS ABAC SCHOOL OF MANAGEMENT ASSUMPTION UNIVERSITY OF THAILAND MASTER OF SCIENCE FINANCIAL ECONOMICS ABAC SCHOOL OF MANAGEMENT ASSUMPTION UNIVERSITY OF THAILAND ECO 5001 Mathematics for Finance and Economics The uses of mathematical argument in extending the range,

More information

Introduction to Regression and Data Analysis

Introduction to Regression and Data Analysis Statlab Workshop Introduction to Regression and Data Analysis with Dan Campbell and Sherlock Campbell October 28, 2008 I. The basics A. Types of variables Your variables may take several forms, and it

More information

Doctor of Philosophy in Economics (English Program) Curriculum 2006

Doctor of Philosophy in Economics (English Program) Curriculum 2006 Doctor of Philosophy in Economics (English Program) Curriculum 2006 1. Program Title Doctor of Philosophy Program in Economics (English Program) 2. Degree Title Doctor of Philosophy (Economics) Ph.D. (Economics)

More information

16 : Demand Forecasting

16 : Demand Forecasting 16 : Demand Forecasting 1 Session Outline Demand Forecasting Subjective methods can be used only when past data is not available. When past data is available, it is advisable that firms should use statistical

More information

Using GIS to Identify Pedestrian- Vehicle Crash Hot Spots and Unsafe Bus Stops

Using GIS to Identify Pedestrian- Vehicle Crash Hot Spots and Unsafe Bus Stops Using GIS to Identify Pedestrian-Vehicle Crash Hot Spots and Unsafe Bus Stops Using GIS to Identify Pedestrian- Vehicle Crash Hot Spots and Unsafe Bus Stops Long Tien Truong and Sekhar V. C. Somenahalli

More information

Spatial Data Analysis

Spatial Data Analysis 14 Spatial Data Analysis OVERVIEW This chapter is the first in a set of three dealing with geographic analysis and modeling methods. The chapter begins with a review of the relevant terms, and an outlines

More information

Hello, my name is Olga Michasova and I present the work The generalized model of economic growth with human capital accumulation.

Hello, my name is Olga Michasova and I present the work The generalized model of economic growth with human capital accumulation. Hello, my name is Olga Michasova and I present the work The generalized model of economic growth with human capital accumulation. 1 Without any doubts human capital is a key factor of economic growth because

More information

Chapter 1 Introduction. 1.1 Introduction

Chapter 1 Introduction. 1.1 Introduction Chapter 1 Introduction 1.1 Introduction 1 1.2 What Is a Monte Carlo Study? 2 1.2.1 Simulating the Rolling of Two Dice 2 1.3 Why Is Monte Carlo Simulation Often Necessary? 4 1.4 What Are Some Typical Situations

More information

Alison Hayes November 30, 2005 NRS 509. Crime Mapping OVERVIEW

Alison Hayes November 30, 2005 NRS 509. Crime Mapping OVERVIEW Alison Hayes November 30, 2005 NRS 509 Crime Mapping OVERVIEW Geographic data has been important to law enforcement since the beginning of local policing in the nineteenth century. The New York City Police

More information

Retirement routes and economic incentives to retire: a cross-country estimation approach Martin Rasmussen

Retirement routes and economic incentives to retire: a cross-country estimation approach Martin Rasmussen Retirement routes and economic incentives to retire: a cross-country estimation approach Martin Rasmussen Welfare systems and policies Working Paper 1:2005 Working Paper Socialforskningsinstituttet The

More information

Spatial Statistics Chapter 3 Basics of areal data and areal data modeling

Spatial Statistics Chapter 3 Basics of areal data and areal data modeling Spatial Statistics Chapter 3 Basics of areal data and areal data modeling Recall areal data also known as lattice data are data Y (s), s D where D is a discrete index set. This usually corresponds to data

More information

TEACHING OF STATISTICS IN NEWLY INDEPENDENT STATES: THE CASE OF KAZAKSTAN

TEACHING OF STATISTICS IN NEWLY INDEPENDENT STATES: THE CASE OF KAZAKSTAN TEACHING OF STATISTICS IN NEWLY INDEPENDENT STATES: THE CASE OF KAZAKSTAN Guido Ferrari, Dipartimento di Statistica G. Parenti, Università di Firenze, Italy The aim of this report is to discuss the state

More information

Testing The Quantity Theory of Money in Greece: A Note

Testing The Quantity Theory of Money in Greece: A Note ERC Working Paper in Economic 03/10 November 2003 Testing The Quantity Theory of Money in Greece: A Note Erdal Özmen Department of Economics Middle East Technical University Ankara 06531, Turkey [email protected]

More information

The Decline of the U.S. Labor Share. by Michael Elsby (University of Edinburgh), Bart Hobijn (FRB SF), and Aysegul Sahin (FRB NY)

The Decline of the U.S. Labor Share. by Michael Elsby (University of Edinburgh), Bart Hobijn (FRB SF), and Aysegul Sahin (FRB NY) The Decline of the U.S. Labor Share by Michael Elsby (University of Edinburgh), Bart Hobijn (FRB SF), and Aysegul Sahin (FRB NY) Comments by: Brent Neiman University of Chicago Prepared for: Brookings

More information

Data Visualization Techniques and Practices Introduction to GIS Technology

Data Visualization Techniques and Practices Introduction to GIS Technology Data Visualization Techniques and Practices Introduction to GIS Technology Michael Greene Advanced Analytics & Modeling, Deloitte Consulting LLP March 16 th, 2010 Antitrust Notice The Casualty Actuarial

More information

Chapter 4 Technological Progress and Economic Growth

Chapter 4 Technological Progress and Economic Growth Chapter 4 Technological Progress and Economic Growth 4.1 Introduction Technical progress is defined as new, and better ways of doing things, and new techniques for using scarce resources more productively.

More information

Healthcare Measurement Analysis Using Data mining Techniques

Healthcare Measurement Analysis Using Data mining Techniques www.ijecs.in International Journal Of Engineering And Computer Science ISSN:2319-7242 Volume 03 Issue 07 July, 2014 Page No. 7058-7064 Healthcare Measurement Analysis Using Data mining Techniques 1 Dr.A.Shaik

More information

Chapter 4: Vector Autoregressive Models

Chapter 4: Vector Autoregressive Models Chapter 4: Vector Autoregressive Models 1 Contents: Lehrstuhl für Department Empirische of Wirtschaftsforschung Empirical Research and und Econometrics Ökonometrie IV.1 Vector Autoregressive Models (VAR)...

More information

Statistics Graduate Courses

Statistics Graduate Courses Statistics Graduate Courses STAT 7002--Topics in Statistics-Biological/Physical/Mathematics (cr.arr.).organized study of selected topics. Subjects and earnable credit may vary from semester to semester.

More information

Panel Data Econometrics

Panel Data Econometrics Panel Data Econometrics Master of Science in Economics - University of Geneva Christophe Hurlin, Université d Orléans University of Orléans January 2010 De nition A longitudinal, or panel, data set is

More information

ADVANCED FORECASTING MODELS USING SAS SOFTWARE

ADVANCED FORECASTING MODELS USING SAS SOFTWARE ADVANCED FORECASTING MODELS USING SAS SOFTWARE Girish Kumar Jha IARI, Pusa, New Delhi 110 012 [email protected] 1. Transfer Function Model Univariate ARIMA models are useful for analysis and forecasting

More information

Markups and Firm-Level Export Status: Appendix

Markups and Firm-Level Export Status: Appendix Markups and Firm-Level Export Status: Appendix De Loecker Jan - Warzynski Frederic Princeton University, NBER and CEPR - Aarhus School of Business Forthcoming American Economic Review Abstract This is

More information

Teaching model: C1 a. General background: 50% b. Theory-into-practice/developmental 50% knowledge-building: c. Guided academic activities:

Teaching model: C1 a. General background: 50% b. Theory-into-practice/developmental 50% knowledge-building: c. Guided academic activities: 1. COURSE DESCRIPTION Degree: Double Degree: Derecho y Finanzas y Contabilidad (English teaching) Course: STATISTICAL AND ECONOMETRIC METHODS FOR FINANCE (Métodos Estadísticos y Econométricos en Finanzas

More information

for an appointment, e-mail [email protected]

for an appointment, e-mail j.adda@ucl.ac.uk M.Sc. in Economics Department of Economics, University College London Econometric Theory and Methods (G023) 1 Autumn term 2007/2008: weeks 2-8 Jérôme Adda for an appointment, e-mail [email protected] Introduction

More information

FACULTY OF ECONOMICS AND BUSINESS SCIENCE Elviña Campus, A Coruña Updated: october 2005 GRADUATE IN BUSINESS ADMINISTRATION AND MANAGEMENT

FACULTY OF ECONOMICS AND BUSINESS SCIENCE Elviña Campus, A Coruña Updated: october 2005 GRADUATE IN BUSINESS ADMINISTRATION AND MANAGEMENT FACULTY OF ECONOMICS AND BUSINESS SCIENCE Elviña Campus, A Coruña Updated: october 2005 Address Campus de Elviña 15071 A Coruña Tel.: +34.981.167000 (Ext.: 2409) Fax.: +34. 981.167070 Webpage: www.udc.es

More information

Causes of Inflation in the Iranian Economy

Causes of Inflation in the Iranian Economy Causes of Inflation in the Iranian Economy Hamed Armesh* and Abas Alavi Rad** It is clear that in the nearly last four decades inflation is one of the important problems of Iranian economy. In this study,

More information

Realestate online information systems

Realestate online information systems Realestate online information systems Yuri Martens, Alexander Koutamanis Faculty of Architecture, Delft University of Technology http://www.re-h.nl Abstract. Several commercial real-estate sites provide

More information

Executive Summary. Summary - 1

Executive Summary. Summary - 1 Executive Summary For as long as human beings have deceived one another, people have tried to develop techniques for detecting deception and finding truth. Lie detection took on aspects of modern science

More information

Threshold Autoregressive Models in Finance: A Comparative Approach

Threshold Autoregressive Models in Finance: A Comparative Approach University of Wollongong Research Online Applied Statistics Education and Research Collaboration (ASEARC) - Conference Papers Faculty of Informatics 2011 Threshold Autoregressive Models in Finance: A Comparative

More information

Relational Learning for Football-Related Predictions

Relational Learning for Football-Related Predictions Relational Learning for Football-Related Predictions Jan Van Haaren and Guy Van den Broeck [email protected], [email protected] Department of Computer Science Katholieke Universiteit

More information

STATISTICA. Clustering Techniques. Case Study: Defining Clusters of Shopping Center Patrons. and

STATISTICA. Clustering Techniques. Case Study: Defining Clusters of Shopping Center Patrons. and Clustering Techniques and STATISTICA Case Study: Defining Clusters of Shopping Center Patrons STATISTICA Solutions for Business Intelligence, Data Mining, Quality Control, and Web-based Analytics Table

More information

The Economic Impact of Texas State University

The Economic Impact of Texas State University The Economic Impact of Texas State University James P. LeSage 1 Fields Endowed Chair for Urban and Regional Economics McCoy College of Business Administration Department of Finance and Economics Texas

More information