DEPARTMENT OF ECONOMICS. Effect of oil price changes on the price of Russian and Chinese oil shares
|
|
- Clemence Richard
- 7 years ago
- Views:
Transcription
1 DEPARTMENT OF ECONOMICS Effect of ol prce changes on the prce of Russan and Chnese ol shares Stephen G. Hall, Unversy of Lecester, UK Amangeld Kenjegalev, Unversy of Lecester, UK Workng Paper No. 09/4 September 009
2 UNIVERSITY OF LEICESTER Effect of ol prce changes on the prce of Russan and Chnese ol shares Stephen G. Hall and Amangeld Kenjegalev
3 Effect of ol prce changes on the prce of Russan and Chnese ol shares Stephen G. Hall * Unversy of Lecester, Natonal Instute of Economc and Socal Research Amangeld Kenjegalev Unversy of Lecester 7/4/009 Abstract Do changes of ol prces have an effect on the stocks of ol companes n emergng markets? Do the shares of ol companes of emergng markets react to the prce news n a smlar way as those of the Western companes? Ths paper ams to answer these questons utlsng varous event study technques. As expected, the results of both parametrc and nonparametrc tests suggest that the fluctuatons of ol prce have an effect on the stock prces. However, an nterestng result s that the responses of stocks of Chnese and Russan ol companes are consderably dfferent from the shares of ther Western counterparts. Keywords: Event studes, abnormal return, parametrc t-test, non-parametrc rank test, ol companes. * Department of Economcs, Unversy of Lecester, Unversy Road, Lecester, LE 7RH, UK. Tel.: +44 (0)6 5 87, fax: +44 (0) , e-mal: s.g.hall@le.ac.uk (Correspondng author), Department of Economcs, Unversy of Lecester, Unversy Road, Lecester, LE 7RH, UK. e-mal: aak0@le.ac.uk
4 Introducton Do changes of ol prces have an effect on the stocks of major emergng economy ol companes? The answer to ths queston seems rather obvous. Yes, there must be a connecton between the ol prce changes and stock returns of ol companes shares. However, do the shares of ol companes of emergng markets react to the prce news n a smlar way as Western companes? Ths study ntends to provde answers for both questons wh partcular emphass on the latter utlsng event study methodology. The event study methodology nvestgates the mpact of news on secury prces. Dependng on the type of nformaton, announcements ncrease or decrease the value of stock on the market. It nvolves estmatng the normal return for a secury and calculatng the drecton and sze of the excess return attrbutable to unantcpated nformaton. Econometrc technques used n event studes are provded by Ball and Tourus (988), Bartholdy et al (007), Brown and Warner (980, 985), Campbell et al (997), Corrado (989), Corrado and Zvney (99), Dyckman et al (984), Jan (986), Krzman (994) and McWllams and Segel (997). The theory s stll growng and the number of economsts researchng n ths area s ncreasng, along wh the sophstcaton of studes. However, despe ths development, to the best of our knowledge, there are no emprcal event study nvestgatons on ol companes of Western and emergng markets and ol prces. Our paper ams to fll ths gap. The analyss s thus performed on twelve major ol companes. The companes represent the four key markets: (a) those n well establshed western economes such as the USA and Europe; and (b) those n emergng economes such as Russa and Chna. The remander of ths artcle s organsed as follows. Secton presents the desgn for the dervaton of abnormal returns and cumulatve abnormal returns. In ths Secton, two tests are presented: the parametrc t-test and the nonparametrc rank test. The results of ths research and an explanaton are gven n Secton 3. Fnally, Secton 4 concludes. 3
5 Theoretcal Backgrounds There are a large number of models that can be used to nvestgate event studes. These models consst of dentfyng the event and testng for excess prof. Tests are constructed n such a way that they detect abnormal performance. There are two broad approaches n conductng the tests: parametrc and non-parametrc. The former approach s usually based on a standard t-test. In the case of event studes, standard t- tests check whether the resduals are statstcally dfferent from the normal student t- dstrbuton. The numerator of the t-test represents the abnormal returns for a partcular date whle the denomnator scales the top part by the level of dsperson or the standard devaton of a gven tme seres. The parametrc test used n the paper s based on a tradonal t-test (Brown and Warner, 980, 985). Ths test s conducted for cumulatve abnormal return (MacKnley, 997) of ndvdual companes. In addon, a hypothetcal portfolo consstng of ol companes has been extensvely analyzed. The parametrc test deals drectly wh the resduals. However, the non-parametrc test has a dfferent approach to detect abnormal performances. Despe that, the test has a parametrc dstrbuton does not assume that the returns have a normal dstrbuton. For example, the nonparametrc sgn test, unlke the standard t-test, does not check the abnormal returns but the respectve sgns of ther resduals. The probably of a negatve and a posve sgn n ths test s assumed to be equal. Another approach to testng the presence or lack thereof of abnormal performances of stocks s the nonparametrc rank test. Ths test ranks the resduals n the tme seres and tests the rank of the return for abnormal performance. To measure the abnormal return, we use two statstcal models. These are the constant mean model and the market model. As prevously mentoned, despe ther relatve smplcy, these models can be effectvely used n the event studes methodology. These two models are presented below. R = µ + ε 4
6 E( ε ) = 0 and Var ( ε ) = σ where R represents the returns of secury at tme t, µ s the mean return for asset and ε s the error term for secury at tme t wh mean equal to zero and varance, σ. The second model utlsed n ths artcle s that of the market model. Ths model s a statstcal model relatng secury returns to market movements and s popular due to s ably to capture market movement n secury returns. R = α + β R + ε mt E( ε ) = 0 and Var ( ε ) = σ where R and R mt are secury and market returns at tme t, respectvely. α and are the coeffcents of the market model. Followng MacKnley, (997), the Standard & Poor s Index s used. β To detect the abnormal return, one needs to defne the event tme t,. In ths study, the event date s defned, as t = 0, the event wndow s represented by t = T + to t = T and, fnally, t = T + 0 to t = T s the estmaton wndow. The length of the event wndow and the estmaton wndow s gven by the followng equatons: L = T T and L = T T0, respectvely. The post event wndow s t = T + to t = T3.The length of the post event wndow s L3 = T3 T. Ths can be shown by the followng fgure: The dervaton of an estmaton perod.e., estmaton wndow, the event wndow and the post event wndow, s taken from MacKnley (997, p. 9). 5
7 The estmaton of the parameters of the market model (MacKnley, 997) for the th frm at the event tme nvolves dentfyng the beta, alpha and varance of the model. Computaton of the abnormal return n the case of the constant mean model s gven by the followng equaton AR = µ 3 R where AR s the abnormal return of the th secury at tme t, secury at tme t and µ s the mean return of the analysed secury. R s the return of the th Usng the parameters obtaned by OLS from the market model, s possble to estmate the abnormal return. Resduals n such cases represent excess returns. The expected return accordng to Bartholdy et al s gven by the followng equaton E( R ) = µ = ˆ α ˆ β R 4 mt The dscrepancy between the actual return and the expected return, adjusted for market movements over the analysed perod, s the abnormal return. AR = R ˆ α ˆ β R 5 mt In the above, the AR s the abnormal return or, n other words, the resdual for secury at tme t. R s the return for secury a tme t, R mt s the market return 6
8 and α and β are parameters of the OLS regresson. The abnormal return s thus the surprse term of the market model. In both cases, the constant mean model and the market model, the test statstc reles on the assumpton of a normal dstrbuton for returns. Under the null hypothess the dstrbuton of the abnormal returns s gven by: AR ~ N(0, σ ( )) 6 AR The null hypothess, H 0, tests that the event does not have an mpact on the abnormal return. To detect that the event has an mpact on the abnormal performance n the case of the secures portfolo, the excess returns of secures have to be aggregated. Aggregaton for abnormal returns of the secures can be made through secures and then through tme (MacKnlay, 997). In ths paper, the aggregaton s made through the secures at the same event dates. Dong ths, one obtans the average abnormal return across secures. Ths aggregaton s gven by the followng: AR = N N AR = 7 And the varance of the aggregated abnormal returns n ths case s: Var N ( AR) = ε N = σ 8 After calculatng the abnormal return for the secures, one can aggregate over the event wndow to fnd the overall mpact of the event. Cumulatng the abnormal returns through the event tme s needed n order to detect the excess returns. The cumulatve abnormal return (CAR) s the sum of the secures abnormal returns. In order to fnd the CAR, the followng equaton s used: 7
9 CAR t, t ) 9 ( t = AR t= t where T < t t T. The varance of the CAR s: ( t, t ) = ( t t ) σ ε σ + 0 It s assumed that the dstrbuton of the cumulatve abnormal return under the null hypothess s: CAR ( t, t ) ~ N(0, σ ( t, t )) The aggregaton of cumulatve abnormal return can be also done across secures and has smlar stages: t = CAR t, t ) AR t ( t= t The varance for above equaton n such condon s: t = Var CAR( t, t )) var( AR t ) 3 ( t= t The cumulatve abnormal return for the portfolo of secures s: N CAR( t, t ) = AR 4 N = and varance s: 8
10 Var( CAR( t 5 N, t )) = var( AR ) N = Testng for the sgnfcance of the abnormal returns can be performed along two broad avenues: parametrc and nonparametrc. The parametrc tests rely on the assumpton of normal dstrbuton. Lehman, (Hggns, 998) states that the t-test s optmal when the dstrbuton of the returns s normal. Thus, assumng that the resduals are normally dstrbuted, s possble to conduct a t-test such that under the null hypothess, the test statstc shows no abnormal return,.e., AR I = 6 var( AR ) where AR s the average abnormal return at a partcular event and var( AR ) s the varance of the abnormal return at ths event date. In addon, usng the cumulatve abnormal return and the varance of the cumulatve return, one can test for the null hypothess. CAR( t, t ) I CAR = ~ N(0, ) 7 var( CAR( t, t )) The prmary dsadvantage of parametrc tests s that they heavly rely on partcular dstrbutonal assumptons. Hence many studes (Bartholdy et al, 007; Brown and Warner, 985; Corrado, 989; Corrado and Zvney, 99; Cowan, 99; Cowan and Sergeant, 996) have utlzed nonparametrc tests. We use the nonparametrc rank test specfed n Corrado (989). Corrado employ a nonparametrc rank test for excess performance. Ths test has smlares wh the standard t-test. However, as opposed to the standard t-test, the rank of the abnormal return s used. 9
11 Consder a sample of observatons of abnormal returns n the event wndow for each of N frms. As stated above, to apply the nonparametrc rank test, the rank of the abnormal returns for the analysed perod for each secury s needed. The hghest rank s gven to the hghest prce of the secury for the analysed perod and vce versa for the lowest rank (Lehman, 975). The rank test transforms the secures excess returns nto a unform dstrbuton across ranks. Thus, n the case of the nonparametrc rank test, one should convert the gven tme seres nto s respectve ranks. Denotng K as the rank of the excess return, AR of the th frm and wh an estmaton wndow of 6 days, the event wndow comprsng 4 days, the followng defnon holds: K = rank( AR ), t = 46,..., The frst 6 days are used as the estmaton wndow and 0 days on each sde of day 0 as the event wndow. Corrado (989) reports that the average rank s obtaned by dvdng the number of observed returns by two. Thus, n ths case the average rank s The test statstc for the null hypothess s gven by the followng equaton: I = N N = ( K 83.5) SD( K) 9 where, ( K 83.5) s a proxy for the abnormal return (Corrado,989). The standard devaton of the rank test s determned by usng a sample perod of 67 days and follows as: + 0 N SD ( K) = ( K 83.5) 0 67 t= 46 N = Tests of the null hypothess can be mplemented usng the result that the asymptotc null dstrbuton s standard normal. The man feature of rank test conssts of rankng each observaton n order to brng them nto a unform dstrbuton. The rest of the procedure of the test does not consderably dffer from the t-test statstcs. 0
12 Emprcal Data and Results Ths artcle focuses on the twelve ol companes. These are companes of the USA - Chevron and Exxon Mobl; Western Europe - Brsh Petroleum, En, Total and Royal Dutch Shell; Russa - GazProm, LukOl and SurgutNefteGaz; and Chna - Chna Petroleum and Chemcals, Petrochna and Snopek. The tme seres s taken from DataStream. The ol prces are represented by crude ol prces whch are extracted from the Energy Informaton Admnstraton ( The tme seres of consst of the daly data for the perod spannng from the st January, 000 to the 8 th March, 008. The frst analysed event date starts n 00. The events are dvded nto types of news: good news and bad news. The followng creron was used to defne the news and s type. If the prce of ol on a partcular day was greater by 4.5% than the prce of the prevous day, then the news s classfed as good news. If, on the other hand, the day s ol prce s less than the prevous day s prce by 4.5% then the news s classfed as bad news. In addon, s nsured that there are at least 30 days between the consdered events (see Fgure ). The next analyss conssts of smulatng the random event dates. To do ths, we follow Brown and Warner (985). The dfference from Brown and Warner s experment s, however, that we do not ntroduce abnormal returns. The smulaton comprses of randomly generated events for each type of news. We defned them as news one and news two, respectvely. Thus on average, all two types of randomly generated news should reflect the absence of abnormal returns.
13
14 Two models of abnormal return are used,.e., the constant mean model and the market model. In the frst part, the cumulatve abnormal return s analysed based on the parametrc t-test. In the second part, the abnormal return are analysed usng the nonparametrc rank test. In the last part the results for the random events are presented. Accordng to the t-test derved by constant mean model on the date zero there s no sgnfcant abnormal return for the good news. The abnormal return for that date s CAR 0. and varance s equal to The value of I s low, 034. However, at the event date the sgn of the cumulatve abnormal return changes from negatve to posve. In addon, the level of sgnfcance on the 5 th, 4 th and 3 th days pror the event accordng to I CAR s -3.0, -4.3 and -3.5 respectvely. The next sgnfcant negatve abnormal return s occurred a week before the event date wh -.7 for that date. CAR I equal to For the case of the bad news, the t-test does not show sgnfcance of abnormal return. Despe ths, one day before the event abnormal return was 0.3 whle at the CAR event date the level of cumulatve abnormal return fell to The I for the day before the event s.7. Statstcally sgnfcant abnormal return s observed from dates -8 and - wh statstcal sgnfcance rangng from 0.5% to 5%. The hghest level of cumulatve abnormal return s observed on the 4 th day before the event wh CAR I beng equal to 3.6. After the event date the paths for cumulatve abnormal return both for the bad news and the good news are strkngly smlar. 3
15 4
16 Fgure 3 and Fgure 4 show that the constant mean and the market models show smlar trends. Moreover, the market model results are not markedly dfferent from those of constant mean model. It also shows the hgh level of abnormal return on the 4 th day pror the event for the bad news. The value of the t-test s -4.. The dssmlary n the cumulatve abnormal return can be attrbuted to the market movement. In other words, the dvergence s potentally caused by the changes n market preferences of nvestors after the sharp ncrease or decrease n ol prces. Accordng to the t-test, computed by the constant mean model, averaged abnormal return for ndvdual companes s nsgnfcant for the event date. The CAR I for the good news at the event date for the stocks of Brsh Petroleum, Chevron, Exxon Mobl, Total, En and Royal Dutch Shell are 0.7, 0.09, 0.75, -0.4, 0.63 and and the values of abnormal returns for that day are 0.4, 0.8, 0.8, 0.4, 0.9 and 0.4 respectvely. Despe that the t-test shows an exstence of abnormal returns two weeks before the event for ndvdual companes, s not sgnfcant. However, the value of the t-test s hgher for the 5 th, 4 th and 3 th days pror the event than those of other dates. The hghest but stll nsgnfcant level of the t-test s observed at the date -4. For the shares of Brsh Petroleum the value of the t-test s -.5, for Chevron s stock the t-test s -.4, for the secures of Exxon Mobl the t-test s equal to -.. The t-test for the stocks of Total s -.6, for the shares of En -.0 and -. for the stocks of Royal Dutch Shell. The sgn of the cumulated abnormal return for the most of the Western companes s negatve before the event. However, after the event the cumulatve return s posve. Exceptons are Total and Royal Dutch Shell. The secures of these two companes have negatve sgn all throughout perod. The t-test calculated by the market model at the event date s lower than the t-test computed by the constant mean model. The t-test for the stock s of Brsh Petroleum s -., for the share s of Chevron t-test s equal to -.6 and for secury s of Exxon Mobl s -.3. The values of the t-test for the stocks of the companes from the Contnental Europe at ths date are as follows: -.5, -.38 and -.77 for Total, En and Royal Dutch Shell secures, respectvely. The sgns of the cumulatve abnormal returns are roughly smlar to the ones obtaned by the constant mean model wh sporadc negatve sgns after the event date. 5
17 For the case of the bad news, the t-test does not show sgnfcance of abnormal return after the event date. The t-test ndcates statstcally sgnfcant posve abnormal returns for Total, En and Royal Dutch Shell s stocks two weeks before the event. The values of the t-test are.89,.4 and.70, respectvely. However, the market model does not report sgnfcant results for ths date. After the event the sgns of the cumulatve abnormal returns change to the negatve, although the tmng of ths change s dfferent for dfferent stocks. For Chnese s and Russan companes the t-test shows some surprsng outcomes whch are dffcult to explan by the changes n the ol prces. For example, Snopek s stocks have sgnfcant abnormal returns both for the good news and bad news. However, the cumulated abnormal return of good news s negatve, whle for the bad news the sgn of cumulated abnormal returns s posve. Accordng to the t- test, for the rest of the stocks the event date does not have any mpact. We conducted the second test, rank test, whch s nonparametrc n nature and does not rely on the assumpton of the normaly of the tme seres. Examnaton of the cumulatve abnormal return showed that the plot of the proxy of cumulatve abnormal return n case of the constant mean model has a smlar movement smlar to the actual abnormal returns for portfolo of companes. However, the test was conducted whout cumulatng proxy of the abnormal return both for constant mean model and market model. The proxy for the abnormal return for the event date s equal to and the varance s 6.6 for the good news. The rank test for the day zero (event day) s 3.5. The bad news show that the cumulatve abnormal return s -5.9 and the standard devaton s 7.4. The rank test n case of bad news s -9.. Another sgnfcant negatve abnormal return s observed 9 days before the event. The rank test for that day s -6.. Interestngly, bad news also ncludes posve abnormal returns. Sgnfcant posve abnormal returns are observed on the 5 th and 8 th days before the event. The abnormal returns for these days are 36. and 36.4 for date -5 and -8 respectvely. The rank test s equal to 5. for the date -5 and 8. for the date -8. The rank test based on the market model reveals the same trend n cumulatve abnormal return as prevous tests. The proxy for the abnormal return s and - 6
18 83.3 for the good news and bad news respectvely. The rank tests are 3.3 and - 6., respectvely and the null hypothess that the event has no mpact s strongly rejected. For the good news there s sgnfcant level of negatve abnormal return two weeks pror the event date. The rank tests are -5.0 and 5.3 for the 4 th day and th day before the event, respectvely. Another sgnfcant negatve abnormal return observed on the 8 th and 7 th days before the event, however on the 6 th day the sgn of abnormal return changes to posve one. The rank tests for those days are -7.9, -5.3 and 6.0 respectvely. The bad news has posve abnormal return 8 days before the event. The rank test showed that wh value 5.. The fgures for the cumulatve e abnormal returns and the proxy for the cumulatve abnormal return show smlares. The plots of proxy for cumulatve abnormal returns presented n Fgures 5 and 6. 7
19 8
20 Yet agan, the tests undertaken for ndvdual companes showed mxed results. That s, the event date has consderable effect on Western companes. In case of Russan and Chnese ol companes, the effects of changes n ol prces do not changes the abnormal return markedly or, even, have an nverse effect. Compared wh the parametrc test, the nonparametrc test ndcates the strong sgnfcance for all Western stocks. The value of the rank test for the good news ranges from 5.9 for Royal Dutch Shell s stock to.79 for En s stocks on the event date. In addon, the rank test shows hgh negatve abnormal return approxmately two weeks before the event. However, a week before the event there are sgnfcant posve abnormal return for most of the secures. These are, especally, notceable wh stocks of Chevron and Exxon Mobl. The rank test for these secures are 8.5 and 6.38 respectvely. On the event date the rank test showed 8.9 for Chevron s stocks and 9.3 for the stocks of Exxon Mobl. Another sgnfcant date s 9 days after the event. The rank test detects consderable negatve abnormal returns on that date. For nstance, the value of the average proxy for abnormal returns of Brsh Petroleum s -8.4 whle on the 8 th day was equal to 3.5. For the rest of the secures the pcture s somewhat smlar to those of the shares of Brsh Petroleum. The bad news also affects the share prces. The lowest level of the rank test observed for the stocks of Royal Dutch Shell s -.78 and the greatest s for the shares of Exxon Mobl, whch s equal to The average rank test for all sx Western companes s Yet agan, the rank test ndcates statstcally sgnfcant posve abnormal returns 5 days before the event. The market model for the rank test supports the constant mean model. It ndcates the sgnfcance of abnormal returns at the event date and sgnfcant posve abnormal returns are observed 5 days before the event. The pcture s not clear for secures of Russan and Chnese companes. Overall, the changes n ol prces seem to have some effect on the share prces. However, n comparson wh the Western companes, s neglgble. For nstance good news s statstcally sgnfcant for the shares of followng companes: Lukol, Gazprom, Surgutneftegaz and Petrochna. Sgnfcance for the bad news observed for the stocks of Petrochna and Chna Petroleum and Chemcals. Despe ths, the level of 9
21 sgnfcance s much lower then those observed for the stocks of the Western companes. Interestngly, Chna Petroleum and Chemcals shares have sgnfcant negatve abnormal return ffteen days before the event for the good news. Whle at the same date for the most of the secures of the Western companes posve abnormal returns are observed. The rank test for the shares of Chna Petroleum and Chemcals s -9.5 and for the constant mean model and the market model, respectvely. Fnally, the nonparametrc rank test shows that overall the abnormal returns of ol companes shares for the analysed perod s affected by ol prce change. In addon, there are sgnfcant abnormal returns before and after the event. The results obtaned under the constant mean and the market models do not greatly dffer. Based on the rank test the outcome s dfferent from tradonal parametrc t-test. Whle the nonparametrc rank test strongly ndcates the exstence of abnormal returns, the parametrc test rejects the possbly of abnormal return. Bartholdy et al (007) pont out that n some nstances the test may show dfferent results. In such suatons, the nonparametrc test s more relable n detectng the abnormal return. Thus takng nto account the results obtaned by the nonparametrc rank test s possble to say that ol prce change affects the shares of Western ol companes. However, s mpact on Chnese and Russan companes s weak. The experment proves that on average random event dates do not show abnormal return and both the parametrc t-test and the nonparametrc rank test ndcate ths. Both tests show an absence of abnormal return. In the case of the constant mean model, the t-test shows 0.0 for news one and -0.0 for the news two. The market model ndcates the value of the t-test value for day zero equal to for news one and 0.00 for news two. For ndvdual companes the t-test shows a sporadc outcome. However these do not change the overall pcture of the test. The rank test as expected supports the t-test n ths experment. The value of the rank test for the proxy for the cumulatve abnormal return s 0.05 and for news one and news two respectvely. For the proxy obtaned by the market model, the value of the rank test s 0. and for the news one and news two respectvely. For the rest of the event wndow, the rank test does not ndcate any 0
22 abnormal return as well. Thus, ths experment confrms that randomly generated events on average should not show abnormal return. The analyss of ndvdual companes showed that the reactons on the ol prce news of shares of emergng and Western ol companes are dfferent. For nstance, the abnormal returns of most Western companes are negatve, rrespectve of news. The exceptons are Exxon Mobl and, to some extent, Chevron and En. In contrast, the nvestments nto Russan and Chnese ol companes generate posve abnormal return regardless of the type of news. The possble explanaton of ths result s that the ol companes are consdered as strategc companes n Chna and Russa and n many nstances prone to polcal nfluences. The experment wh random event dates ndcates a smlar outcome for ths experment both for the parametrc t-test and the nonparametrc rank test. They show that one cannot reject the null hypothess of no abnormal return. Concluson Ths analyss amed to fll the gap n the emprcal research of event studes of ol companes. It s focused on the queston of whether the changes n ol prces have an mpact on share prces of emergng and Western ol companes. The methodology s n lne, wh that of other researchers. The nonparametrc rank test results reveal consderable abnormal returns for ol companes. However, the tests also show the dscrepancy among the companes from dfferent economc areas. For example, whle ol prce change effects stock prces of Amercan and European ol companes as expected, the most atypcal behavour s observed for the secures of Chnese and Russan companes. A smulaton experment was addonally conducted based on the same tests but wh randomly generated event dates. Ths experment had the expected results both under the parametrc t-test and the nonparametrc rank test. Vz., one can not reject the null hypothess of no abnormal returns n the case of random event dates for the stock prces of ol companes.
23 It s also nterestng to note, and further research s requred n the future, to explan why the Russan and Chnese ol companes behave dfferently. Potental causes of such performances of the shares are, perhaps, nsde nformaton, polcal nfluences and corrupton.
24 References Ball, C.A., and Taurus, W.N., (988), Investgatng secury-prce performance n the presence of event date uncertanty, Journal of Fnancal Economcs, Vol., pp Bartholdy, J., Olson D., and Peare, P., (007), Conductng event studes on a small stock exchange, The European Journal of Fnance, Vol. 3, pp Brown, S. and Warner, J., (980), Measurng secury prce performance, Journal of Fnancal Economcs, Vol. 8, pp Brown, S. and Warner, J., (985), Usng daly stock returns: The case of event studes, Journal of Fnancal Economcs, Vol. 4, pp Campbell, Y., Lo, A., and MacKnlay, A., (997), The Econometrc of Fnancal Markets, Prnceton Unversy press, Prnceton. Corrado, C.J., (989), A nonparametrc test for abnormal secury-prce performance n event studes, Journal of Fnancal Economcs, Vol. 3, pp Corrado, C.J., and Zvney, T.L., (99), The specfcaton and power of the sgn test n event study hypothess tests usng daly stock returns, The Journal of Fnancal and Quantatve Analyss, Vol. 7, pp Cowan, A.R., (99), Nonparametrc Event Study Tests, Revew of Quantatve Fnance and Accountng, Vol., pp Cowan, A.R., and Sergeant, A.M.A., (996), Tradng frequency and event study test specfcaton, Journal of Bankng and Fnance, Vol. 0, pp Dyckman, T., Phlbrck, D. and Stephean, J., (984), A comparson of event study methodologes usng daly stock returns: a smulaton approach, Journal of Accountng Research, Vol., pp Hggns, E. J., and Peterson, D. R., (998), The power of one and two sample t- statstcs gven event-nduced varance ncreases and nonnormal stock returns: A comparatve study, The Quarterly Journal of Fnance and Accountng, Vol. 37, pp Jan, P.C., (986), Analyses of the dstrbuton of secury market model predcton errors for daly returns data, Journal of Accountng Research, Vol. 4, pp
25 Krzman, M.P., (994), What Practoners Need to Know About Event Studes, Fnancal Analysts Journal, Vol. 50, pp MacKnlay, A.C., (997), Event studes n economcs and fnance, Journal of Economc Lerature, Vol. 35, pp McWllams, A., and Segel, D., (997), Event studes n management research: theoretcal and emprcal ssues, Academy of Management Journal, Vol. 40, No. 3, pp Lehman, E.L., and D Abrera, H.J.M., (975), Nonparametrcs: Statstcal Methods Based on Ranks, Holden-day Inc., San-Francsco. 4
HOUSEHOLDS DEBT BURDEN: AN ANALYSIS BASED ON MICROECONOMIC DATA*
HOUSEHOLDS DEBT BURDEN: AN ANALYSIS BASED ON MICROECONOMIC DATA* Luísa Farnha** 1. INTRODUCTION The rapd growth n Portuguese households ndebtedness n the past few years ncreased the concerns that debt
More informationQuestion 2: What is the variance and standard deviation of a dataset?
Queston 2: What s the varance and standard devaton of a dataset? The varance of the data uses all of the data to compute a measure of the spread n the data. The varance may be computed for a sample of
More informationDay-of-the-Week Trading Patterns of Individual and Institutional Investors
Day-of-the-Week Tradng Patterns of Indvdual and Instutonal Investors Joel N. Morse, Hoang Nguyen, and Hao M. Quach Ths study examnes the day-of-the-week tradng patterns of ndvdual and nstutonal nvestors.
More informationHow To Calculate The Accountng Perod Of Nequalty
Inequalty and The Accountng Perod Quentn Wodon and Shlomo Ytzha World Ban and Hebrew Unversty September Abstract Income nequalty typcally declnes wth the length of tme taen nto account for measurement.
More informationCan Auto Liability Insurance Purchases Signal Risk Attitude?
Internatonal Journal of Busness and Economcs, 2011, Vol. 10, No. 2, 159-164 Can Auto Lablty Insurance Purchases Sgnal Rsk Atttude? Chu-Shu L Department of Internatonal Busness, Asa Unversty, Tawan Sheng-Chang
More informationPSYCHOLOGICAL RESEARCH (PYC 304-C) Lecture 12
14 The Ch-squared dstrbuton PSYCHOLOGICAL RESEARCH (PYC 304-C) Lecture 1 If a normal varable X, havng mean µ and varance σ, s standardsed, the new varable Z has a mean 0 and varance 1. When ths standardsed
More informationSIMPLE LINEAR CORRELATION
SIMPLE LINEAR CORRELATION Smple lnear correlaton s a measure of the degree to whch two varables vary together, or a measure of the ntensty of the assocaton between two varables. Correlaton often s abused.
More informationAn Alternative Way to Measure Private Equity Performance
An Alternatve Way to Measure Prvate Equty Performance Peter Todd Parlux Investment Technology LLC Summary Internal Rate of Return (IRR) s probably the most common way to measure the performance of prvate
More informationCHOLESTEROL REFERENCE METHOD LABORATORY NETWORK. Sample Stability Protocol
CHOLESTEROL REFERENCE METHOD LABORATORY NETWORK Sample Stablty Protocol Background The Cholesterol Reference Method Laboratory Network (CRMLN) developed certfcaton protocols for total cholesterol, HDL
More informationForecasting the Direction and Strength of Stock Market Movement
Forecastng the Drecton and Strength of Stock Market Movement Jngwe Chen Mng Chen Nan Ye cjngwe@stanford.edu mchen5@stanford.edu nanye@stanford.edu Abstract - Stock market s one of the most complcated systems
More informationThe impact of hard discount control mechanism on the discount volatility of UK closed-end funds
Investment Management and Fnancal Innovatons, Volume 10, Issue 3, 2013 Ahmed F. Salhn (Egypt) The mpact of hard dscount control mechansm on the dscount volatlty of UK closed-end funds Abstract The mpact
More informationTHE DISTRIBUTION OF LOAN PORTFOLIO VALUE * Oldrich Alfons Vasicek
HE DISRIBUION OF LOAN PORFOLIO VALUE * Oldrch Alfons Vascek he amount of captal necessary to support a portfolo of debt securtes depends on the probablty dstrbuton of the portfolo loss. Consder a portfolo
More informationTwo Faces of Intra-Industry Information Transfers: Evidence from Management Earnings and Revenue Forecasts
Two Faces of Intra-Industry Informaton Transfers: Evdence from Management Earnngs and Revenue Forecasts Yongtae Km Leavey School of Busness Santa Clara Unversty Santa Clara, CA 95053-0380 TEL: (408) 554-4667,
More informationStatistical Methods to Develop Rating Models
Statstcal Methods to Develop Ratng Models [Evelyn Hayden and Danel Porath, Österrechsche Natonalbank and Unversty of Appled Scences at Manz] Source: The Basel II Rsk Parameters Estmaton, Valdaton, and
More informationMacro Factors and Volatility of Treasury Bond Returns
Macro Factors and Volatlty of Treasury Bond Returns Jngzh Huang Department of Fnance Smeal Colleage of Busness Pennsylvana State Unversty Unversty Park, PA 16802, U.S.A. Le Lu School of Fnance Shangha
More informationThe announcement effect on mean and variance for underwritten and non-underwritten SEOs
The announcement effect on mean and varance for underwrtten and non-underwrtten SEOs Bachelor Essay n Fnancal Economcs Department of Economcs Sprng 013 Marcus Wkner and Joel Anehem Ulvenäs Supervsor: Professor
More informationHigh Correlation between Net Promoter Score and the Development of Consumers' Willingness to Pay (Empirical Evidence from European Mobile Markets)
Hgh Correlaton between et Promoter Score and the Development of Consumers' Wllngness to Pay (Emprcal Evdence from European Moble Marets Ths paper shows that the correlaton between the et Promoter Score
More informationThe DAX and the Dollar: The Economic Exchange Rate Exposure of German Corporations
The DAX and the Dollar: The Economc Exchange Rate Exposure of German Corporatons Martn Glaum *, Marko Brunner **, Holger Hmmel *** Ths paper examnes the economc exposure of German corporatons to changes
More informationThe Development of Web Log Mining Based on Improve-K-Means Clustering Analysis
The Development of Web Log Mnng Based on Improve-K-Means Clusterng Analyss TngZhong Wang * College of Informaton Technology, Luoyang Normal Unversty, Luoyang, 471022, Chna wangtngzhong2@sna.cn Abstract.
More informationCHAPTER 14 MORE ABOUT REGRESSION
CHAPTER 14 MORE ABOUT REGRESSION We learned n Chapter 5 that often a straght lne descrbes the pattern of a relatonshp between two quanttatve varables. For nstance, n Example 5.1 we explored the relatonshp
More informationNPAR TESTS. One-Sample Chi-Square Test. Cell Specification. Observed Frequencies 1O i 6. Expected Frequencies 1EXP i 6
PAR TESTS If a WEIGHT varable s specfed, t s used to replcate a case as many tmes as ndcated by the weght value rounded to the nearest nteger. If the workspace requrements are exceeded and samplng has
More informationTraffic-light a stress test for life insurance provisions
MEMORANDUM Date 006-09-7 Authors Bengt von Bahr, Göran Ronge Traffc-lght a stress test for lfe nsurance provsons Fnansnspetonen P.O. Box 6750 SE-113 85 Stocholm [Sveavägen 167] Tel +46 8 787 80 00 Fax
More information1. Measuring association using correlation and regression
How to measure assocaton I: Correlaton. 1. Measurng assocaton usng correlaton and regresson We often would lke to know how one varable, such as a mother's weght, s related to another varable, such as a
More informationStudent Performance in Online Quizzes as a Function of Time in Undergraduate Financial Management Courses
Student Performance n Onlne Quzzes as a Functon of Tme n Undergraduate Fnancal Management Courses Olver Schnusenberg The Unversty of North Florda ABSTRACT An nterestng research queston n lght of recent
More informationIDENTIFICATION AND CORRECTION OF A COMMON ERROR IN GENERAL ANNUITY CALCULATIONS
IDENTIFICATION AND CORRECTION OF A COMMON ERROR IN GENERAL ANNUITY CALCULATIONS Chrs Deeley* Last revsed: September 22, 200 * Chrs Deeley s a Senor Lecturer n the School of Accountng, Charles Sturt Unversty,
More informationSTATISTICAL DATA ANALYSIS IN EXCEL
Mcroarray Center STATISTICAL DATA ANALYSIS IN EXCEL Lecture 6 Some Advanced Topcs Dr. Petr Nazarov 14-01-013 petr.nazarov@crp-sante.lu Statstcal data analyss n Ecel. 6. Some advanced topcs Correcton for
More informationScale Dependence of Overconfidence in Stock Market Volatility Forecasts
Scale Dependence of Overconfdence n Stoc Maret Volatlty Forecasts Marus Glaser, Thomas Langer, Jens Reynders, Martn Weber* June 7, 007 Abstract In ths study, we analyze whether volatlty forecasts (judgmental
More informationExhaustive Regression. An Exploration of Regression-Based Data Mining Techniques Using Super Computation
Exhaustve Regresson An Exploraton of Regresson-Based Data Mnng Technques Usng Super Computaton Antony Daves, Ph.D. Assocate Professor of Economcs Duquesne Unversty Pttsburgh, PA 58 Research Fellow The
More informationManagement Quality, Financial and Investment Policies, and. Asymmetric Information
Management Qualty, Fnancal and Investment Polces, and Asymmetrc Informaton Thomas J. Chemmanur * Imants Paegls ** and Karen Smonyan *** Current verson: December 2007 * Professor of Fnance, Carroll School
More informationbenefit is 2, paid if the policyholder dies within the year, and probability of death within the year is ).
REVIEW OF RISK MANAGEMENT CONCEPTS LOSS DISTRIBUTIONS AND INSURANCE Loss and nsurance: When someone s subject to the rsk of ncurrng a fnancal loss, the loss s generally modeled usng a random varable or
More informationRisk Model of Long-Term Production Scheduling in Open Pit Gold Mining
Rsk Model of Long-Term Producton Schedulng n Open Pt Gold Mnng R Halatchev 1 and P Lever 2 ABSTRACT Open pt gold mnng s an mportant sector of the Australan mnng ndustry. It uses large amounts of nvestments,
More informationWage inequality and returns to schooling in Europe: a semi-parametric approach using EU-SILC data
MPRA Munch Personal RePEc Archve Wage nequalty and returns to schoolng n Europe: a sem-parametrc approach usng EU-SILC data Marco Bagett and Sergo Sccchtano Unversty La Sapenza Rome, Mnstry of Economc
More informationCovariate-based pricing of automobile insurance
Insurance Markets and Companes: Analyses and Actuaral Computatons, Volume 1, Issue 2, 2010 José Antono Ordaz (Span), María del Carmen Melgar (Span) Covarate-based prcng of automoble nsurance Abstract Ths
More informationAnalysis of Premium Liabilities for Australian Lines of Business
Summary of Analyss of Premum Labltes for Australan Lnes of Busness Emly Tao Honours Research Paper, The Unversty of Melbourne Emly Tao Acknowledgements I am grateful to the Australan Prudental Regulaton
More informationCalendar Corrected Chaotic Forecast of Financial Time Series
INTERNATIONAL JOURNAL OF BUSINESS, 11(4), 2006 ISSN: 1083 4346 Calendar Corrected Chaotc Forecast of Fnancal Tme Seres Alexandros Leonttss a and Costas Sropoulos b a Center for Research and Applcatons
More informationSPECIALIZED DAY TRADING - A NEW VIEW ON AN OLD GAME
August 7 - August 12, 2006 n Baden-Baden, Germany SPECIALIZED DAY TRADING - A NEW VIEW ON AN OLD GAME Vladmr Šmovć 1, and Vladmr Šmovć 2, PhD 1 Faculty of Electrcal Engneerng and Computng, Unska 3, 10000
More informationEconomic Interpretation of Regression. Theory and Applications
Economc Interpretaton of Regresson Theor and Applcatons Classcal and Baesan Econometrc Methods Applcaton of mathematcal statstcs to economc data for emprcal support Economc theor postulates a qualtatve
More informationSTAMP DUTY ON SHARES AND ITS EFFECT ON SHARE PRICES
STAMP UTY ON SHARES AN ITS EFFECT ON SHARE PRICES Steve Bond Mke Hawkns Alexander Klemm THE INSTITUTE FOR FISCAL STUIES WP04/11 STAMP UTY ON SHARES AN ITS EFFECT ON SHARE PRICES Steve Bond (IFS and Unversty
More informationTHE DETERMINANTS OF THE TUNISIAN BANKING INDUSTRY PROFITABILITY: PANEL EVIDENCE
THE DETERMINANTS OF THE TUNISIAN BANKING INDUSTRY PROFITABILITY: PANEL EVIDENCE Samy Ben Naceur ERF Research Fellow Department of Fnance Unversté Lbre de Tuns Avenue Khéreddne Pacha, 002 Tuns Emal : sbennaceur@eudoramal.com
More informationIs There A Tradeoff between Employer-Provided Health Insurance and Wages?
Is There A Tradeoff between Employer-Provded Health Insurance and Wages? Lye Zhu, Southern Methodst Unversty October 2005 Abstract Though most of the lterature n health nsurance and the labor market assumes
More informationIIIS Dscusson & World Market Niche
IIIS Dscusson Paper No.136/Aprl 2006 Integraton Of Smaller European Equty Markets : A Tme-Varyng Integraton Score Analyss Gregory Brg School of Busness Studes and Insttute for Internatonal Integraton,
More informationMarginal Benefit Incidence Analysis Using a Single Cross-section of Data. Mohamed Ihsan Ajwad and Quentin Wodon 1. World Bank.
Margnal Beneft Incdence Analyss Usng a Sngle Cross-secton of Data Mohamed Ihsan Ajwad and uentn Wodon World Bank August 200 Abstract In a recent paper, Lanjouw and Ravallon proposed an attractve and smple
More informationNumber of Levels Cumulative Annual operating Income per year construction costs costs ($) ($) ($) 1 600,000 35,000 100,000 2 2,200,000 60,000 350,000
Problem Set 5 Solutons 1 MIT s consderng buldng a new car park near Kendall Square. o unversty funds are avalable (overhead rates are under pressure and the new faclty would have to pay for tself from
More informationPRIVATE SCHOOL CHOICE: THE EFFECTS OF RELIGIOUS AFFILIATION AND PARTICIPATION
PRIVATE SCHOOL CHOICE: THE EFFECTS OF RELIIOUS AFFILIATION AND PARTICIPATION Danny Cohen-Zada Department of Economcs, Ben-uron Unversty, Beer-Sheva 84105, Israel Wllam Sander Department of Economcs, DePaul
More informationTraditional versus Online Courses, Efforts, and Learning Performance
Tradtonal versus Onlne Courses, Efforts, and Learnng Performance Kuang-Cheng Tseng, Department of Internatonal Trade, Chung-Yuan Chrstan Unversty, Tawan Shan-Yng Chu, Department of Internatonal Trade,
More informationThe Probability of Informed Trading and the Performance of Stock in an Order-Driven Market
Asa-Pacfc Journal of Fnancal Studes (2007) v36 n6 pp871-896 The Probablty of Informed Tradng and the Performance of Stock n an Order-Drven Market Ta Ma * Natonal Sun Yat-Sen Unversty, Tawan Mng-hua Hseh
More informationStaff Paper. Farm Savings Accounts: Examining Income Variability, Eligibility, and Benefits. Brent Gloy, Eddy LaDue, and Charles Cuykendall
SP 2005-02 August 2005 Staff Paper Department of Appled Economcs and Management Cornell Unversty, Ithaca, New York 14853-7801 USA Farm Savngs Accounts: Examnng Income Varablty, Elgblty, and Benefts Brent
More informationImpact of Attribution Metrics on Return on Keyword Investment. in Paid Search Advertising
Impact of Attrbuton Metrcs on Return on Keyword Investment n Pad Search Advertsng Hongshuang (Alce) L 1 P. K. Kannan Sva Vswanathan Abhshek Pan June 3, 2014 1 Hongshuang (Alce) L s Assstant Professor of
More informationMomentum Trading, Mean Reversal and Overreaction in Chinese Stock Market *
Momentum Tradng, Mean Reversal and Overreacton n Chnese Stock Market * YANGRU WU Rutgers Unversty and Hong Kong Insttute for Monetary Research December 2003 (Prelmnary, Comments Welcome) ABSTRACT Whle
More informationMultiple-Period Attribution: Residuals and Compounding
Multple-Perod Attrbuton: Resduals and Compoundng Our revewer gave these authors full marks for dealng wth an ssue that performance measurers and vendors often regard as propretary nformaton. In 1994, Dens
More informationThe Investor Recognition Hypothesis:
The Investor Recognton Hypothess: the New Zealand Penny Stocks Danel JP Cha, Department of Accountng and Fnance, onash Unversty, Clayton 3168, elbourne, Australa, and Danel FS Cho, Department of Fnance,
More informationSocial Nfluence and Its Models
Influence and Correlaton n Socal Networks Ars Anagnostopoulos Rav Kumar Mohammad Mahdan Yahoo! Research 701 Frst Ave. Sunnyvale, CA 94089. {ars,ravkumar,mahdan}@yahoo-nc.com ABSTRACT In many onlne socal
More informationUnderstanding the Impact of Marketing Actions in Traditional Channels on the Internet: Evidence from a Large Scale Field Experiment
A research and educaton ntatve at the MT Sloan School of Management Understandng the mpact of Marketng Actons n Tradtonal Channels on the nternet: Evdence from a Large Scale Feld Experment Paper 216 Erc
More informationWorld currency options market efficiency
Arful Hoque (Australa) World optons market effcency Abstract The World Currency Optons (WCO) maket began tradng n July 2007 on the Phladelpha Stock Exchange (PHLX) wth the new features. These optons are
More informationManagement Quality and Equity Issue Characteristics: A Comparison of SEOs and IPOs
Management Qualty and Equty Issue Characterstcs: A Comparson of SEOs and IPOs Thomas J. Chemmanur * Imants Paegls ** and Karen Smonyan *** Current verson: November 2009 (Accepted, Fnancal Management, February
More informationECONOMICS OF PLANT ENERGY SAVINGS PROJECTS IN A CHANGING MARKET Douglas C White Emerson Process Management
ECONOMICS OF PLANT ENERGY SAVINGS PROJECTS IN A CHANGING MARKET Douglas C Whte Emerson Process Management Abstract Energy prces have exhbted sgnfcant volatlty n recent years. For example, natural gas prces
More informationAnalysis of the relationship between working capital policy and operating risk: an empirical study on Jordanian industrial companies
Investment Management and Fnancal Innovatons, Volume 7, Issue, 00 Fars Nasf Al-Shubr (Jordan) Analyss of the relatonshp between workng capal polcy and operatng rsk: an emprcal study on Jordanan ndustral
More informationGender differences in revealed risk taking: evidence from mutual fund investors
Economcs Letters 76 (2002) 151 158 www.elsever.com/ locate/ econbase Gender dfferences n revealed rsk takng: evdence from mutual fund nvestors a b c, * Peggy D. Dwyer, James H. Glkeson, John A. Lst a Unversty
More informationThe Application of Fractional Brownian Motion in Option Pricing
Vol. 0, No. (05), pp. 73-8 http://dx.do.org/0.457/jmue.05.0..6 The Applcaton of Fractonal Brownan Moton n Opton Prcng Qng-xn Zhou School of Basc Scence,arbn Unversty of Commerce,arbn zhouqngxn98@6.com
More informationCorporate Real Estate Sales and Agency Costs of Managerial Discretion
Corporate Real Estate Sales and Agency Costs of Manageral Dscreton Mng-Long Lee * Department of Fnance Natonal Yunln Unversty of Scence & Technology Yunln, Tawan Mng-Te Lee Department of Accountng Tamkang
More informationCHAPTER 5 RELATIONSHIPS BETWEEN QUANTITATIVE VARIABLES
CHAPTER 5 RELATIONSHIPS BETWEEN QUANTITATIVE VARIABLES In ths chapter, we wll learn how to descrbe the relatonshp between two quanttatve varables. Remember (from Chapter 2) that the terms quanttatve varable
More informationClay House Case Study and Comparison of Two Behemoths ofEC term
Drk Schoenmaker (Netherlands), Thjs Bosch (Netherlands) Is the home bas n equtes and bonds declnng n Europe? Abstract Fnance theory suggests that nvestors should hold an nternatonally dversfed portfolo.
More informationTESTING FOR EVIDENCE OF ADVERSE SELECTION IN DEVELOPING AUTOMOBILE INSURANCE MARKET. Oksana Lyashuk
TESTING FOR EVIDENCE OF ADVERSE SELECTION IN DEVELOPING AUTOMOBILE INSURANCE MARKET by Oksana Lyashuk A thess submtted n partal fulfllment of the requrements for the degree of Master of Arts n Economcs
More informationTHE IMPLIED VOLATILITY OF ETF AND INDEX OPTIONS
The Internatonal Journal of Busness and Fnance Research Volume 5 Number 4 2011 THE IMPLIED VOLATILITY OF ETF AND INDEX OPTIONS Stoyu I. Ivanov, San Jose State Unversty Jeff Whtworth, Unversty of Houston-Clear
More informationEvaluating credit risk models: A critique and a new proposal
Evaluatng credt rsk models: A crtque and a new proposal Hergen Frerchs* Gunter Löffler Unversty of Frankfurt (Man) February 14, 2001 Abstract Evaluatng the qualty of credt portfolo rsk models s an mportant
More informationThe timing ability of hybrid funds of funds
The tmng ablty of hybrd funds of funds Javer Rodríguez* Graduate School of Busness Admnstraton Unversty of Puerto Rco PO 23332 San Juan, PR 00931 Abstract Hybrd mutual funds are funds that nvest n a combnaton
More informationWORKING PAPER SERIES TAKING STOCK: MONETARY POLICY TRANSMISSION TO EQUITY MARKETS NO. 354 / MAY 2004. by Michael Ehrmann and Marcel Fratzscher
WORKING PAPER SERIES NO. 354 / MAY 2004 TAKING STOCK: MONETARY POLICY TRANSMISSION TO EQUITY MARKETS by Mchael Ehrmann and Marcel Fratzscher WORKING PAPER SERIES NO. 354 / MAY 2004 TAKING STOCK: MONETARY
More informationStatistical algorithms in Review Manager 5
Statstcal algorthms n Reve Manager 5 Jonathan J Deeks and Julan PT Hggns on behalf of the Statstcal Methods Group of The Cochrane Collaboraton August 00 Data structure Consder a meta-analyss of k studes
More informationThe Impact of Stock Index Futures Trading on Daily Returns Seasonality: A Multicountry Study
The Impact of Stock Index Futures Tradng on Daly Returns Seasonalty: A Multcountry Study Robert W. Faff a * and Mchael D. McKenze a Abstract In ths paper we nvestgate the potental mpact of the ntroducton
More informationESTIMATING THE MARKET VALUE OF FRANKING CREDITS: EMPIRICAL EVIDENCE FROM AUSTRALIA
ESTIMATING THE MARKET VALUE OF FRANKING CREDITS: EMPIRICAL EVIDENCE FROM AUSTRALIA Duc Vo Beauden Gellard Stefan Mero Economc Regulaton Authorty 469 Wellngton Street, Perth, WA 6000, Australa Phone: (08)
More informationOnline Appendix Supplemental Material for Market Microstructure Invariance: Empirical Hypotheses
Onlne Appendx Supplemental Materal for Market Mcrostructure Invarance: Emprcal Hypotheses Albert S. Kyle Unversty of Maryland akyle@rhsmth.umd.edu Anna A. Obzhaeva New Economc School aobzhaeva@nes.ru Table
More informationCourse outline. Financial Time Series Analysis. Overview. Data analysis. Predictive signal. Trading strategy
Fnancal Tme Seres Analyss Patrck McSharry patrck@mcsharry.net www.mcsharry.net Trnty Term 2014 Mathematcal Insttute Unversty of Oxford Course outlne 1. Data analyss, probablty, correlatons, vsualsaton
More informationCalibration and Linear Regression Analysis: A Self-Guided Tutorial
Calbraton and Lnear Regresson Analyss: A Self-Guded Tutoral Part The Calbraton Curve, Correlaton Coeffcent and Confdence Lmts CHM314 Instrumental Analyss Department of Chemstry, Unversty of Toronto Dr.
More informationThe Effects of Tax Rate Changes on Tax Bases and the Marginal Cost of Public Funds for Canadian Provincial Governments
The Effects of Tax Rate Changes on Tax Bases and the Margnal Cost of Publc Funds for Canadan Provncal Governments Bev Dahlby a and Ergete Ferede b a Department of Economcs, Unversty of Alberta, Edmonton,
More informationEditing and Imputing Administrative Tax Return Data. Charlotte Gaughan Office for National Statistics UK
Edtng and Imputng Admnstratve Tax Return Data Charlotte Gaughan Offce for Natonal Statstcs UK Overvew Introducton Lmtatons Data Lnkng Data Cleanng Imputaton Methods Concluson and Future Work Introducton
More informationWorld Economic Vulnerability Monitor (WEVUM) Trade shock analysis
World Economc Vulnerablty Montor (WEVUM) Trade shock analyss Measurng the mpact of the global shocks on trade balances va prce and demand effects Alex Izureta and Rob Vos UN DESA 1. Non-techncal descrpton
More informationDO LOSS FIRMS MANAGE EARNINGS AROUND SEASONED EQUITY OFFERINGS?
DO LOSS FIRMS MANAGE EARNINGS AROUND SEASONED EQUITY OFFERINGS? Fernando Comran, Unversty of San Francsco, School of Management, 2130 Fulton Street, CA 94117, Unted States, fcomran@usfca.edu Tatana Fedyk,
More informationWhat is Candidate Sampling
What s Canddate Samplng Say we have a multclass or mult label problem where each tranng example ( x, T ) conssts of a context x a small (mult)set of target classes T out of a large unverse L of possble
More informationForecasting the Demand of Emergency Supplies: Based on the CBR Theory and BP Neural Network
700 Proceedngs of the 8th Internatonal Conference on Innovaton & Management Forecastng the Demand of Emergency Supples: Based on the CBR Theory and BP Neural Network Fu Deqang, Lu Yun, L Changbng School
More informationWORKING PAPER. C.D. Howe Institute. The Effects of Tax Rate Changes on Tax Bases and the Marginal Cost of Public Funds for Provincial Governments
MARCH 211 C.D. Howe Insttute WORKING PAPER FISCAL AND TAX COMPETITIVENESS The Effects of Tax Rate Changes on Tax Bases and the Margnal Cost of Publc Funds for Provncal Governments Bev Dahlby Ergete Ferede
More informationReturns to Experience in Mozambique: A Nonparametric Regression Approach
Returns to Experence n Mozambque: A Nonparametrc Regresson Approach Joel Muzma Conference Paper nº 27 Conferênca Inaugural do IESE Desafos para a nvestgação socal e económca em Moçambque 19 de Setembro
More informationCausal, Explanatory Forecasting. Analysis. Regression Analysis. Simple Linear Regression. Which is Independent? Forecasting
Causal, Explanatory Forecastng Assumes cause-and-effect relatonshp between system nputs and ts output Forecastng wth Regresson Analyss Rchard S. Barr Inputs System Cause + Effect Relatonshp The job of
More informationOn the Optimal Control of a Cascade of Hydro-Electric Power Stations
On the Optmal Control of a Cascade of Hydro-Electrc Power Statons M.C.M. Guedes a, A.F. Rbero a, G.V. Smrnov b and S. Vlela c a Department of Mathematcs, School of Scences, Unversty of Porto, Portugal;
More informationInstitute of Informatics, Faculty of Business and Management, Brno University of Technology,Czech Republic
Lagrange Multplers as Quanttatve Indcators n Economcs Ivan Mezník Insttute of Informatcs, Faculty of Busness and Management, Brno Unversty of TechnologCzech Republc Abstract The quanttatve role of Lagrange
More informationTransaction Costs and Strategic Trading of German Investment Management Firms: Empirical Evidence from European Stock Markets
Transacton Costs and Strategc Tradng of German Investment Management Frms: Emprcal Evdence from European Stock Markets Lutz Johannng* Endowed Char for Asset Management European Busness School Schloß Rechartshausen
More informationAnswer: A). There is a flatter IS curve in the high MPC economy. Original LM LM after increase in M. IS curve for low MPC economy
4.02 Quz Solutons Fall 2004 Multple-Choce Questons (30/00 ponts) Please, crcle the correct answer for each of the followng 0 multple-choce questons. For each queston, only one of the answers s correct.
More informationTHE METHOD OF LEAST SQUARES THE METHOD OF LEAST SQUARES
The goal: to measure (determne) an unknown quantty x (the value of a RV X) Realsaton: n results: y 1, y 2,..., y j,..., y n, (the measured values of Y 1, Y 2,..., Y j,..., Y n ) every result s encumbered
More informationCS 2750 Machine Learning. Lecture 3. Density estimation. CS 2750 Machine Learning. Announcements
Lecture 3 Densty estmaton Mlos Hauskrecht mlos@cs.ptt.edu 5329 Sennott Square Next lecture: Matlab tutoral Announcements Rules for attendng the class: Regstered for credt Regstered for audt (only f there
More information! # %& ( ) +,../ 0 1 2 3 4 0 4 # 5##&.6 7% 8 # 0 4 2 #...
! # %& ( ) +,../ 0 1 2 3 4 0 4 # 5##&.6 7% 8 # 0 4 2 #... 9 Sheffeld Economc Research Paper Seres SERP Number: 2011010 ISSN 1749-8368 Sarah Brown, Aurora Ortz-Núñez and Karl Taylor Educatonal loans and
More informationDiscount Rate for Workout Recoveries: An Empirical Study*
Dscount Rate for Workout Recoveres: An Emprcal Study* Brooks Brady Amercan Express Peter Chang Standard & Poor s Peter Mu** McMaster Unversty Boge Ozdemr Standard & Poor s Davd Schwartz Federal Reserve
More informationDEFINING %COMPLETE IN MICROSOFT PROJECT
CelersSystems DEFINING %COMPLETE IN MICROSOFT PROJECT PREPARED BY James E Aksel, PMP, PMI-SP, MVP For Addtonal Informaton about Earned Value Management Systems and reportng, please contact: CelersSystems,
More informationForecasting Irregularly Spaced UHF Financial Data: Realized Volatility vs UHF-GARCH Models
Forecastng Irregularly Spaced UHF Fnancal Data: Realzed Volatlty vs UHF-GARCH Models Franços-Érc Raccot *, LRSP Département des scences admnstratves, UQO Raymond Théoret Département Stratége des affares,
More informationENTERPRISE RISK MANAGEMENT IN INSURANCE GROUPS: MEASURING RISK CONCENTRATION AND DEFAULT RISK
ETERPRISE RISK MAAGEMET I ISURACE GROUPS: MEASURIG RISK COCETRATIO AD DEFAULT RISK ADIE GATZERT HATO SCHMEISER STEFA SCHUCKMA WORKIG PAPERS O RISK MAAGEMET AD ISURACE O. 35 EDITED BY HATO SCHMEISER CHAIR
More informationThe role of time, liquidity, volume and bid-ask spread on the volatility of the Australian equity market.
The role of tme, lqudty, volume and bd-ask spread on the volatlty of the Australan equty market. Allster Keller* Bruno Rodrgues** Mawell Stevenson* * Dscplne of Fnance School of Busness The Unversty of
More informationEfficient Project Portfolio as a tool for Enterprise Risk Management
Effcent Proect Portfolo as a tool for Enterprse Rsk Management Valentn O. Nkonov Ural State Techncal Unversty Growth Traectory Consultng Company January 5, 27 Effcent Proect Portfolo as a tool for Enterprse
More informationSpeculative Trading and Stock Prices:
Speculatve Tradng and Stock Prces: n nalyss of Chnese - Share Prema * Janpng Me, José. Schenkman and We Xong Ths verson: June 2003 bstract In ths paper we use data from Chna s stock markets to analyze
More informationPrediction of Disability Frequencies in Life Insurance
Predcton of Dsablty Frequences n Lfe Insurance Bernhard Köng Fran Weber Maro V. Wüthrch October 28, 2011 Abstract For the predcton of dsablty frequences, not only the observed, but also the ncurred but
More informationHARVARD John M. Olin Center for Law, Economics, and Business
HARVARD John M. Oln Center for Law, Economcs, and Busness ISSN 1045-6333 ASYMMETRIC INFORMATION AND LEARNING IN THE AUTOMOBILE INSURANCE MARKET Alma Cohen Dscusson Paper No. 371 6/2002 Harvard Law School
More informationBeating the Odds: Arbitrage and Wining Strategies in the Football Betting Market
Beatng the Odds: Arbtrage and Wnng Strateges n the Football Bettng Market NIKOLAOS VLASTAKIS, GEORGE DOTSIS and RAPHAEL N. MARKELLOS* ABSTRACT We examne the potental for generatng postve returns from wagerng
More informationThe Current Employment Statistics (CES) survey,
Busness Brths and Deaths Impact of busness brths and deaths n the payroll survey The CES probablty-based sample redesgn accounts for most busness brth employment through the mputaton of busness deaths,
More information