Can There Be Infinitely Many Models Equivalent to a Given Covariance Structure Model?

Size: px
Start display at page:

Download "Can There Be Infinitely Many Models Equivalent to a Given Covariance Structure Model?"

Transcription

1 STRUCTURAL EQUATION MODELING, 8(1), Copyright 2001, Lawrence Erlbaum Associates, Inc. TEACHER S CORNER Can There Be Infinitely Many Models Equivalent to a Given Covariance Structure Model? Tenko Raykov Department of Psychology Fordham University George A. Marcoulides Management Science California State University, Fullerton The problem of equivalent models has plagued researchers since the earliest developmental stages of structural equation modeling (SEM; Marcoulides & Schumacker, 1996). Equivalent models are those that provide the same sets of statistical fit indexes (e.g., chi-square and p values) as a hypothesized model but may imply very different substantive interpretations of the data (Stelzl, 1986). As a consequence, equivalent models represent a very serious threat to behavioral and social theory development and construct validation using SEM. In fact, unless the model equivalence problem is addressed, any originally considered model regardless of how well it fits the data remains only one possible means of its explanation (e.g., MacCallum, Wegener, Uchino, & Fabrigar, 1993). Although the problem of equivalent models has received considerable methodological attention for more than a decade (e.g., Bollen, 1989; Breckler, 1990; Hayduk, 1996; Hershberger, 1994; Jöreskog & Sörbom, 1993; Lee & Requests for reprints should be sent to Tenko Raykov, Department of Psychology, Fordham University, Bronx, NY raykov@murray.fordham.edu

2 INFINITELY MANY EQUIVALENT MODELS 143 Hershberger, 1991; Luijben, 1991; MacCallum et al., 1993; Raykov, 1997; Raykov & Penev, 1999; Stelzl, 1986; Williams, Bozdogan, & Aiman-Smith, 1996), distinguishing between equivalent models cannot be achieved using currently available fit indexes. Model equivalence can only be managed via substantive considerations or considerations pertaining to design and data collection features (apart from the case of multiple-population versions of single-group equivalent models, where statistical distinction becomes possible with appropriate group constraints, if substantively correct; Raykov, 1997). MacCallum et al. (1993) indicated that equivalent models exist routinely and for essentially any structural equation model there are potentially many equivalent models that represent equally plausible means of describing the analyzed data. Once a hypothesized model is proposed, some of its equivalent models can be obtained using specifically developed rules (e.g., Hershberger, 1994; Lee & Hershberger, 1990; Stelzl, 1986), whereas others can be obtained utilizing special parameter restrictions (e.g., Raykov & Penev, 1999). From this perspective, it is important to know whether for any hypothesized model there exist only a limited (although possibly large) number of equivalent models or if there can be infinitely many such equivalent models. In the former case, the desire is to be in a position to assess the substantive meaningfulness and likelihood of each of a finite number of models that may have generated the data and possibly rule out most of them as means of data description and explanation. In the latter case, however, another level of difficulty with potentially hard to anticipate implications is added to efforts of resolving the equivalence problem. The purpose of this article is to address the question of whether there may be infinitely many models equivalent to a hypothesized one. Specifically, an example of a set of infinitely many models equivalent to an a priori hypothesized covariance structure model is presented. The intention is to demonstrate and highlight the difficulty and seriousness of the problem of equivalent models by providing what represents an unlimited host of alternatives to an understanding of how a studied phenomenon might operate as reflected in an initially considered model of it. Subsequently, issues pertaining to managing the equivalence problem are discussed. NOTATION AND BACKGROUND This article makes extensive use of notation commonly employed in the SEM literature (e.g., Bollen, 1989). The vector y =(y 1, y 2,,y p ) t denotes observed data on p manifest variables of interest (p 2), θ denotes the vector of parameters of a structural equation model M under consideration, Ω is its parameter space containing all possible values of θ, and Σ(θ) is the covariance matrix implied by M at θ.

3 144 RAYKOV AND MARCOULIDES The concern of this article is with special cases of the general linear structural relationship model (Jöreskog & Sörbom, 1993). They are contained in the so-called Submodel 3B of the comprehensive software program LISREL. Accordingly, the model is defined by the following equations: η = Bη + ζ, and y = Λη + ε (1) In Equation 1, η is the vector of latent variables (factors, constructs, latent dimensions), B is the matrix of structural regression coefficients relating the latent variables between themselves, Λ is the factor loading matrix, ζ is the structural regression residuals vector (with a covariance matrix Ψ), and ε the error terms vector (with a covariance matrix Θ). It is emphasized that Equation 1 defines the most general LISREL model that encompasses the so-called general LISREL model (Jöreskog & Sörbom, 1993). 1 Currently, the model in Equation 1 covers the vast majority of models used in routine applications of the SEM methodology in behavioral and social research. From Equation 1, with the usual assumption of invertibility of the matrix I q B (where I q is the q q identity matrix and q is the number of latent variables in the model), it follows that the covariance matrix implied by a LISREL model M has the form Σ(θ) = ΛΣ ηη Λ t + Θ = Λ(I q B) 1 Ψ(I q B t ) 1 Λ t + Θ (2) where Σ ηη is the covariance matrix of the latent variables in η. Equation 2 implies that different matrices appearing in its right-hand side may lead to identical reproduced covariance matrices in its left-hand side. Obviously, this is because due to Equation 2 the latter-reproduced matrices equal sums and products of matrices, yet from these sums and products, one cannot deduce uniquely the individual matrices on the right-hand side of Equation 2. In broad terms, this represents the essence of the phenomenon of equivalent models. For the remaining sections, the following statement that defines two models M and M as equivalent is important (e.g., Raykov & Penev, 1999; Stelzl, 1986). Definition: The structural equation models M and M are equivalent if they reproduce the same sets of corresponding covariance matrices, Σ(θ) and Σ (θ ), when their parameters θ and θ vary across their parameter spaces Ω and Ω, respectively. 1 That general LISREL model utilizes a different, but not necessary, notation for the latent independent variables and their indicators, viz. ξ and x respectively, as well as δ for the error terms associated with x (Jöreskog & Sörbom, 1993, p. 190).

4 INFINITELY MANY EQUIVALENT MODELS 145 AN EXAMPLE OF INFINITELY MANY EQUIVALENT MODELS This section considers a set of infinitely many models equivalent to an hypothesized covariance structure model, called M o.m o is the basic model used in this article and is depicted in Figure 1. As seen in Figure 1, M o is a simple, two-factors with two-indicators model, with unitary factor loadings. Although this simple model was selected for illustrative purposes, it is important to point out that the ideas presented in this article are equally applicable to the case of any number of indicators per factor. M o assumes that there is a direct positive effect of the latent variable η 1 on the latent variable η 2, each measured by indicators that act as τ-equivalent tests (i.e., measuring the same true score, in the same units of measurement, yet with potentially different error variances), and is identified. Because the replacement rule by Lee and Hershberger (1990) is applicable to model M o, it follows that M o is equivalent to model M1 depicted in Figure 2. Model M1 is identical to M o in all aspects except the one-way arrow from η 1 into η 2 (and pertinent structural residual), which is exchanged in M1 by a two-way (positive) covariance of the two constructs. M1 is also identified and, although not of main interest in this aricle, plays an auxiliary role to enable a direct demonstration of model equivalence later. The next model to be considered is equivalent to M1 and identified, as formally shown by Raykov & Penev (1999, Appendix 2), and for consistency is referred to as model M2 and depicted in Figure 3. From the equivalence of M o and M1, and the transitivity property of the model equivalence relation (i.e., from M being equivalent to M and the latter to M, it follows that M and M are equivalent; Stelzl, 1986), it is deduced that M o and M2 are equivalent. FIGURE 1 Model M o.

5 146 RAYKOV AND MARCOULIDES FIGURE 2 Model M1 (auxiliary model). FIGURE 3 Model M2 (the first member of the infinite series ϒ of models equivalent to M o ). We note that M2 has different substantive implications than those that follow from M o. Whereas M o states that η 1 causally affects η 2, no relation at all is assumed between the corresponding two constructs in M2. 2 Instead, in M2 the common source of the relation between the four observed variables y 1 to y 4 is not a relation between η 11 and η 22, but a third construct η 3 that is unmatched by a 2 The constructs η 11 and η 22 in M2 need not be identical to η 1 and η 2, respectively, in M1, as seen when writing out the definition equations of both models in terms of relations of manifest to latent variables (e.g., Raykov & Penev, in press, Appendix 2).

6 INFINITELY MANY EQUIVALENT MODELS 147 separate model term in M o. We stress that all three constructs in M2 are orthogonal to each other, whereas in M o the two underlying latent variables are correlated, with the specific earlier cause effect assumption incorporated at the latent level (as indicated in Raykov & Penev, 1999, in M2 the variance of η 3 is assumed to be less than the smaller of the variances of η 1 and η 2 in model M1). The fact that M o and M2 are equivalent means that M o and M2 reproduce the same set of implied covariance matrices (see definition of equivalence). Thus, any model that has the property of reproducing the same set of implied covariance matrices as that by M2 will by necessity be equivalent to M o as well (due to the aforementioned transitivity property of the equivalence relation). This feature will hold for any of the infinitely many models constructed next that are each equivalent to M2, and thus equivalent to M o too. This infinite series of equivalent models, denoted ϒ, is defined as follows. The first member of ϒ is model M2, which has one added construct (viz. η 3 ) that has unitary loadings on all four observed variables and is orthogonal to the remaining two unrelated constructs (η 11 and η 22 ). The kth member of the series, for k 2 (that is, k becoming larger than any finite number), has k such added constructs with the following four properties: (a) unit loadings on all manifest variables, (b) are orthogonal to the same unrelated constructs η 11 and η 22, (c) are unrelated among themselves, and (d) have the additional feature that their sum equals the construct η 3 in model M2. The kth member of ϒ is depicted in Figure 4, whereby the triple of vertically located dots stands for the intermediate added constructs η 5,,η k +2 in the general case (k 2). Given property (d) of the added constructs, it follows that the covariance matrix implied by any member of ϒ is identical to that reproduced by model M2. Thus, FIGURE 4 The kth member of the infinite series ϒ of models equivalent to M o (k 2; η η k +3 = η 3 in Model M2).

7 148 RAYKOV AND MARCOULIDES any member of ϒ is equivalent to M2 and is therefore equivalent to the basic model M o. Furthermore, because M2 is identified, the variance of η 3, σ 32 is identified. Then the variances of the added constructs in the kth member of ϒ will be identified (and thus so will be also that model, as all remaining parameters in it are obviously identified) if assumed equal to one another, that is, each having variance σ 32 /k (k 2). It is important to note that, with this final assumption, the degrees of freedom of each model in ϒ are identical. We also stress that each member of ϒ has different substantive implications from one another and from M o, because that member model has a different number of added unrelated constructs. Each of them implies an additional characteristic (i.e., unrelated to the others) source of variability in the observed variables y 1 to y 4. Thus, ϒ represents an infinite series of identified models equivalent to the basic covariance structure model M o. CONCLUSION This article addressed the problem of equivalence in structural equation modeling. In particular, it addressed the issue of whether researchers can safely assume that there are no more than a finite number of models equivalent to an initially hypothesized covariance structure model. The article provided a counterexample that highlights the difficulty and extent to which model equivalence is a very serious problem for SEM researchers. The article also illustrates the need and importance of further research into model equivalence, particularly with respect to their differentiation. Similarly, it highlights the relevance of thorough studies into the nature of latent variables so as to provide as much as possible additional information about modeled latent dimensions widely used in the behavioral, social, and educational sciences. With this additional information that could largely be of nonstatistical type, perhaps a more successful distinction between equivalent accounts of studied phenomena may be achieved. ACKNOWLEDGMENTS This research was supported in part by a faculty fellowship grant from Fordham University. We are indebted to D. Ozer for valuable discussions on model equivalence. REFERENCES Bentler, P. M. (1995). EQS: Structural equations program manual. Encino, CA: Multivariate Software. Bollen, K. A. (1989). Structural equations with latent variables. New York: Wiley.

8 INFINITELY MANY EQUIVALENT MODELS 149 Breckler, S. (1990). Applications of covariance structure modeling in psychology: Cause for concern? Psychological Bulletin, 107, Hayduk, L. A. (1996). LISREL issues, debates, and strategies. Baltimore, MD: Johns Hopkins University Press. Hershberger, S. L. (1994). The specification of equivalent models before the collection of data. In A. von Eye and C. C. Clogg (Eds.), Latent variables analysis (pp ). Thousand Oaks, CA: Sage. Jöreskog, K. G., & Sörbom, D. (1993). LISREL 8: User s guide. Chicago: Scientific Software. Lee, S., & Hershberger, S. (1990). A simple rule for generating equivalent models in covariance structure modeling. Multivariate Behavioral Research, 25, Luijben, T. C. W. (1991). Equivalent models in covariance structure analysis. Psychometrika, 56, MacCallum, R. C., Wegener, D. T., Uchino, B., N., & Fabrigar, L. R. (1993). The problem of equivalent models in applications of covariance structure analysis. Psychological Bulletin, 114, Marcoulides, G. A., & Schumacker, R. E. (Eds.). (1996). Advanced structural equation modeling: Issues and techniques. Mahwah, NJ: Lawrence Erlbaum Associates, Inc. Raykov, T. (1997). Equivalent structural equation models and group equality constraints. Multivariate Behavioral Research, 32, Raykov, T., & Penev, S. (1999). On structural equation model equivalence. Multivariate Behavioral Research, 34, Stelzl, I. (1986). Changing a causal hypothesis without changing the fit: Some rules for generating equivalent path models. Multivariate Behavioral Research, 21, Williams, L. J., Bozdogan, H., & Aiman-Smith, L. (1996). Inference problems with equivalent models. In G. A. Marcoulides and R. E. Schumacker (Eds.), Advanced structural equation modeling. Issues and techniques (pp ). Mahwah, NJ: Lawrence Erlbaum Associates, Inc.

Applications of Structural Equation Modeling in Social Sciences Research

Applications of Structural Equation Modeling in Social Sciences Research American International Journal of Contemporary Research Vol. 4 No. 1; January 2014 Applications of Structural Equation Modeling in Social Sciences Research Jackson de Carvalho, PhD Assistant Professor

More information

SEM Analysis of the Impact of Knowledge Management, Total Quality Management and Innovation on Organizational Performance

SEM Analysis of the Impact of Knowledge Management, Total Quality Management and Innovation on Organizational Performance 2015, TextRoad Publication ISSN: 2090-4274 Journal of Applied Environmental and Biological Sciences www.textroad.com SEM Analysis of the Impact of Knowledge Management, Total Quality Management and Innovation

More information

A First Course in Structural Equation Modeling

A First Course in Structural Equation Modeling CD Enclosed Second Edition A First Course in Structural Equation Modeling TENKO RAYKOV GEORGE A. MARCOULDES A First Course in Structural Equation Modeling Second Edition A First Course in Structural Equation

More information

Simple Second Order Chi-Square Correction

Simple Second Order Chi-Square Correction Simple Second Order Chi-Square Correction Tihomir Asparouhov and Bengt Muthén May 3, 2010 1 1 Introduction In this note we describe the second order correction for the chi-square statistic implemented

More information

Richard E. Zinbarg northwestern university, the family institute at northwestern university. William Revelle northwestern university

Richard E. Zinbarg northwestern university, the family institute at northwestern university. William Revelle northwestern university psychometrika vol. 70, no., 23 33 march 2005 DOI: 0.007/s336-003-0974-7 CRONBACH S α, REVELLE S β, AND MCDONALD S ω H : THEIR RELATIONS WITH EACH OTHER AND TWO ALTERNATIVE CONCEPTUALIZATIONS OF RELIABILITY

More information

Structural Equation Modelling (SEM)

Structural Equation Modelling (SEM) (SEM) Aims and Objectives By the end of this seminar you should: Have a working knowledge of the principles behind causality. Understand the basic steps to building a Model of the phenomenon of interest.

More information

Overview of Factor Analysis

Overview of Factor Analysis Overview of Factor Analysis Jamie DeCoster Department of Psychology University of Alabama 348 Gordon Palmer Hall Box 870348 Tuscaloosa, AL 35487-0348 Phone: (205) 348-4431 Fax: (205) 348-8648 August 1,

More information

Pragmatic Perspectives on the Measurement of Information Systems Service Quality

Pragmatic Perspectives on the Measurement of Information Systems Service Quality Pragmatic Perspectives on the Measurement of Information Systems Service Quality Analysis with LISREL: An Appendix to Pragmatic Perspectives on the Measurement of Information Systems Service Quality William

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

Missing Data. A Typology Of Missing Data. Missing At Random Or Not Missing At Random

Missing Data. A Typology Of Missing Data. Missing At Random Or Not Missing At Random [Leeuw, Edith D. de, and Joop Hox. (2008). Missing Data. Encyclopedia of Survey Research Methods. Retrieved from http://sage-ereference.com/survey/article_n298.html] Missing Data An important indicator

More information

Introduction to Matrix Algebra

Introduction to Matrix Algebra Psychology 7291: Multivariate Statistics (Carey) 8/27/98 Matrix Algebra - 1 Introduction to Matrix Algebra Definitions: A matrix is a collection of numbers ordered by rows and columns. It is customary

More information

Analyzing Structural Equation Models With Missing Data

Analyzing Structural Equation Models With Missing Data Analyzing Structural Equation Models With Missing Data Craig Enders* Arizona State University cenders@asu.edu based on Enders, C. K. (006). Analyzing structural equation models with missing data. In G.

More information

Introduction to General and Generalized Linear Models

Introduction to General and Generalized Linear Models Introduction to General and Generalized Linear Models General Linear Models - part I Henrik Madsen Poul Thyregod Informatics and Mathematical Modelling Technical University of Denmark DK-2800 Kgs. Lyngby

More information

Introduction to Path Analysis

Introduction to Path Analysis This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike License. Your use of this material constitutes acceptance of that license and the conditions of use of materials on this

More information

Extending the debate between Spearman and Wilson 1929: When do single variables optimally reproduce the common part of the observed covariances?

Extending the debate between Spearman and Wilson 1929: When do single variables optimally reproduce the common part of the observed covariances? 1 Extending the debate between Spearman and Wilson 1929: When do single variables optimally reproduce the common part of the observed covariances? André Beauducel 1 & Norbert Hilger University of Bonn,

More information

Overview of Violations of the Basic Assumptions in the Classical Normal Linear Regression Model

Overview of Violations of the Basic Assumptions in the Classical Normal Linear Regression Model Overview of Violations of the Basic Assumptions in the Classical Normal Linear Regression Model 1 September 004 A. Introduction and assumptions The classical normal linear regression model can be written

More information

PARTIAL LEAST SQUARES IS TO LISREL AS PRINCIPAL COMPONENTS ANALYSIS IS TO COMMON FACTOR ANALYSIS. Wynne W. Chin University of Calgary, CANADA

PARTIAL LEAST SQUARES IS TO LISREL AS PRINCIPAL COMPONENTS ANALYSIS IS TO COMMON FACTOR ANALYSIS. Wynne W. Chin University of Calgary, CANADA PARTIAL LEAST SQUARES IS TO LISREL AS PRINCIPAL COMPONENTS ANALYSIS IS TO COMMON FACTOR ANALYSIS. Wynne W. Chin University of Calgary, CANADA ABSTRACT The decision of whether to use PLS instead of a covariance

More information

Factor analysis. Angela Montanari

Factor analysis. Angela Montanari Factor analysis Angela Montanari 1 Introduction Factor analysis is a statistical model that allows to explain the correlations between a large number of observed correlated variables through a small number

More information

DISCRIMINANT FUNCTION ANALYSIS (DA)

DISCRIMINANT FUNCTION ANALYSIS (DA) DISCRIMINANT FUNCTION ANALYSIS (DA) John Poulsen and Aaron French Key words: assumptions, further reading, computations, standardized coefficents, structure matrix, tests of signficance Introduction Discriminant

More information

PSYCHOLOGY Vol. II - The Construction and Use of Psychological Tests and Measures - Bruno D. Zumbo, Michaela N. Gelin, Anita M.

PSYCHOLOGY Vol. II - The Construction and Use of Psychological Tests and Measures - Bruno D. Zumbo, Michaela N. Gelin, Anita M. THE CONSTRUCTION AND USE OF PSYCHOLOGICAL TESTS AND MEASURES Bruno D. Zumbo, Michaela N. Gelin and Measurement, Evaluation, and Research Methodology Program, Department of Educational and Counselling Psychology,

More information

A Brief Introduction to Factor Analysis

A Brief Introduction to Factor Analysis 1. Introduction A Brief Introduction to Factor Analysis Factor analysis attempts to represent a set of observed variables X 1, X 2. X n in terms of a number of 'common' factors plus a factor which is unique

More information

USING MULTIPLE GROUP STRUCTURAL MODEL FOR TESTING DIFFERENCES IN ABSORPTIVE AND INNOVATIVE CAPABILITIES BETWEEN LARGE AND MEDIUM SIZED FIRMS

USING MULTIPLE GROUP STRUCTURAL MODEL FOR TESTING DIFFERENCES IN ABSORPTIVE AND INNOVATIVE CAPABILITIES BETWEEN LARGE AND MEDIUM SIZED FIRMS USING MULTIPLE GROUP STRUCTURAL MODEL FOR TESTING DIFFERENCES IN ABSORPTIVE AND INNOVATIVE CAPABILITIES BETWEEN LARGE AND MEDIUM SIZED FIRMS Anita Talaja University of Split, Faculty of Economics Cvite

More information

Multivariate Normal Distribution

Multivariate Normal Distribution Multivariate Normal Distribution Lecture 4 July 21, 2011 Advanced Multivariate Statistical Methods ICPSR Summer Session #2 Lecture #4-7/21/2011 Slide 1 of 41 Last Time Matrices and vectors Eigenvalues

More information

Factorial Invariance in Student Ratings of Instruction

Factorial Invariance in Student Ratings of Instruction Factorial Invariance in Student Ratings of Instruction Isaac I. Bejar Educational Testing Service Kenneth O. Doyle University of Minnesota The factorial invariance of student ratings of instruction across

More information

Exploratory Factor Analysis

Exploratory Factor Analysis Exploratory Factor Analysis ( 探 索 的 因 子 分 析 ) Yasuyo Sawaki Waseda University JLTA2011 Workshop Momoyama Gakuin University October 28, 2011 1 Today s schedule Part 1: EFA basics Introduction to factor

More information

[This document contains corrections to a few typos that were found on the version available through the journal s web page]

[This document contains corrections to a few typos that were found on the version available through the journal s web page] Online supplement to Hayes, A. F., & Preacher, K. J. (2014). Statistical mediation analysis with a multicategorical independent variable. British Journal of Mathematical and Statistical Psychology, 67,

More information

Running head: MEDIATION IN DYADIC DATA 1. Assessing Mediation in Dyadic Data Using the Actor-Partner Interdependence Model.

Running head: MEDIATION IN DYADIC DATA 1. Assessing Mediation in Dyadic Data Using the Actor-Partner Interdependence Model. Running head: MEDIATION IN DYADIC DATA 1 Assessing Mediation in Dyadic Data Using the Actor-Partner Interdependence Model Thomas Ledermann University of Connecticut Siegfried Macho University of Fribourg,

More information

What is Linear Programming?

What is Linear Programming? Chapter 1 What is Linear Programming? An optimization problem usually has three essential ingredients: a variable vector x consisting of a set of unknowns to be determined, an objective function of x to

More information

UNDERSTANDING THE TWO-WAY ANOVA

UNDERSTANDING THE TWO-WAY ANOVA UNDERSTANDING THE e have seen how the one-way ANOVA can be used to compare two or more sample means in studies involving a single independent variable. This can be extended to two independent variables

More information

Indices of Model Fit STRUCTURAL EQUATION MODELING 2013

Indices of Model Fit STRUCTURAL EQUATION MODELING 2013 Indices of Model Fit STRUCTURAL EQUATION MODELING 2013 Indices of Model Fit A recommended minimal set of fit indices that should be reported and interpreted when reporting the results of SEM analyses:

More information

Least Squares Estimation

Least Squares Estimation Least Squares Estimation SARA A VAN DE GEER Volume 2, pp 1041 1045 in Encyclopedia of Statistics in Behavioral Science ISBN-13: 978-0-470-86080-9 ISBN-10: 0-470-86080-4 Editors Brian S Everitt & David

More information

How To Understand Multivariate Models

How To Understand Multivariate Models Neil H. Timm Applied Multivariate Analysis With 42 Figures Springer Contents Preface Acknowledgments List of Tables List of Figures vii ix xix xxiii 1 Introduction 1 1.1 Overview 1 1.2 Multivariate Models

More information

Mathematics (MAT) MAT 061 Basic Euclidean Geometry 3 Hours. MAT 051 Pre-Algebra 4 Hours

Mathematics (MAT) MAT 061 Basic Euclidean Geometry 3 Hours. MAT 051 Pre-Algebra 4 Hours MAT 051 Pre-Algebra Mathematics (MAT) MAT 051 is designed as a review of the basic operations of arithmetic and an introduction to algebra. The student must earn a grade of C or in order to enroll in MAT

More information

MATHEMATICAL METHODS OF STATISTICS

MATHEMATICAL METHODS OF STATISTICS MATHEMATICAL METHODS OF STATISTICS By HARALD CRAMER TROFESSOK IN THE UNIVERSITY OF STOCKHOLM Princeton PRINCETON UNIVERSITY PRESS 1946 TABLE OF CONTENTS. First Part. MATHEMATICAL INTRODUCTION. CHAPTERS

More information

Simple Linear Regression Inference

Simple Linear Regression Inference Simple Linear Regression Inference 1 Inference requirements The Normality assumption of the stochastic term e is needed for inference even if it is not a OLS requirement. Therefore we have: Interpretation

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

MATRIX ALGEBRA AND SYSTEMS OF EQUATIONS. + + x 2. x n. a 11 a 12 a 1n b 1 a 21 a 22 a 2n b 2 a 31 a 32 a 3n b 3. a m1 a m2 a mn b m

MATRIX ALGEBRA AND SYSTEMS OF EQUATIONS. + + x 2. x n. a 11 a 12 a 1n b 1 a 21 a 22 a 2n b 2 a 31 a 32 a 3n b 3. a m1 a m2 a mn b m MATRIX ALGEBRA AND SYSTEMS OF EQUATIONS 1. SYSTEMS OF EQUATIONS AND MATRICES 1.1. Representation of a linear system. The general system of m equations in n unknowns can be written a 11 x 1 + a 12 x 2 +

More information

Multivariate Analysis. Overview

Multivariate Analysis. Overview Multivariate Analysis Overview Introduction Multivariate thinking Body of thought processes that illuminate the interrelatedness between and within sets of variables. The essence of multivariate thinking

More information

Exploratory Factor Analysis Brian Habing - University of South Carolina - October 15, 2003

Exploratory Factor Analysis Brian Habing - University of South Carolina - October 15, 2003 Exploratory Factor Analysis Brian Habing - University of South Carolina - October 15, 2003 FA is not worth the time necessary to understand it and carry it out. -Hills, 1977 Factor analysis should not

More information

1 Determinants and the Solvability of Linear Systems

1 Determinants and the Solvability of Linear Systems 1 Determinants and the Solvability of Linear Systems In the last section we learned how to use Gaussian elimination to solve linear systems of n equations in n unknowns The section completely side-stepped

More information

The Effects of Parent Trust on Perceived Influence and School Involvement

The Effects of Parent Trust on Perceived Influence and School Involvement The Effects of Parent Trust on Perceived Influence and School Involvement Laura L. B. Barnes, Roxanne M. Mitchell, Patrick B.Forsyth, & Curt M. Adams Oklahoma State University A Paper Presented at the

More information

Common method bias in PLS-SEM: A full collinearity assessment approach

Common method bias in PLS-SEM: A full collinearity assessment approach Common method bias in PLS-SEM: A full collinearity assessment approach Ned Kock Full reference: Kock, N. (2015). Common method bias in PLS-SEM: A full collinearity assessment approach. International Journal

More information

Common factor analysis

Common factor analysis Common factor analysis This is what people generally mean when they say "factor analysis" This family of techniques uses an estimate of common variance among the original variables to generate the factor

More information

1 Overview and background

1 Overview and background In Neil Salkind (Ed.), Encyclopedia of Research Design. Thousand Oaks, CA: Sage. 010 The Greenhouse-Geisser Correction Hervé Abdi 1 Overview and background When performing an analysis of variance with

More information

Factor Analysis and Structural equation modelling

Factor Analysis and Structural equation modelling Factor Analysis and Structural equation modelling Herman Adèr Previously: Department Clinical Epidemiology and Biostatistics, VU University medical center, Amsterdam Stavanger July 4 13, 2006 Herman Adèr

More information

Evaluating the Fit of Structural Equation Models: Tests of Significance and Descriptive Goodness-of-Fit Measures

Evaluating the Fit of Structural Equation Models: Tests of Significance and Descriptive Goodness-of-Fit Measures Methods of Psychological Research Online 003, Vol.8, No., pp. 3-74 Department of Psychology Internet: http://www.mpr-online.de 003 University of Koblenz-Landau Evaluating the Fit of Structural Equation

More information

FEATURE. Abstract. Introduction. Background

FEATURE. Abstract. Introduction. Background FEATURE From Data to Information: Using Factor Analysis with Survey Data Ronald D. Fricker, Jr., Walter W. Kulzy, and Jeffrey A. Appleget, Naval Postgraduate School; rdfricker@nps.edu Abstract In irregular

More information

Rens van de Schoot a b, Peter Lugtig a & Joop Hox a a Department of Methods and Statistics, Utrecht

Rens van de Schoot a b, Peter Lugtig a & Joop Hox a a Department of Methods and Statistics, Utrecht This article was downloaded by: [University Library Utrecht] On: 15 May 2012, At: 01:20 Publisher: Psychology Press Informa Ltd Registered in England and Wales Registered Number: 1072954 Registered office:

More information

Measurement, Factor Analysis and Structural Equation Modelling (SEM)

Measurement, Factor Analysis and Structural Equation Modelling (SEM) JOHN MOLSON SCHOOL OF BUSINESS DEPARTMENT OF DECISION SCIENCES AND M.I.S. ADMI 820W Course Outline Winter 2008 Measurement, Factor Analysis and Structural Equation Modelling (SEM) Instructor: Dr. Jamshid

More information

Assessing a theoretical model on EFL college students

Assessing a theoretical model on EFL college students ABSTRACT Assessing a theoretical model on EFL college students Yu-Ping Chang Yu Da University, Taiwan This study aimed to (1) integrate relevant language learning models and theories, (2) construct a theoretical

More information

This chapter will demonstrate how to perform multiple linear regression with IBM SPSS

This chapter will demonstrate how to perform multiple linear regression with IBM SPSS CHAPTER 7B Multiple Regression: Statistical Methods Using IBM SPSS This chapter will demonstrate how to perform multiple linear regression with IBM SPSS first using the standard method and then using the

More information

Mehtap Ergüven Abstract of Ph.D. Dissertation for the degree of PhD of Engineering in Informatics

Mehtap Ergüven Abstract of Ph.D. Dissertation for the degree of PhD of Engineering in Informatics INTERNATIONAL BLACK SEA UNIVERSITY COMPUTER TECHNOLOGIES AND ENGINEERING FACULTY ELABORATION OF AN ALGORITHM OF DETECTING TESTS DIMENSIONALITY Mehtap Ergüven Abstract of Ph.D. Dissertation for the degree

More information

Partial Least Squares (PLS) Regression.

Partial Least Squares (PLS) Regression. Partial Least Squares (PLS) Regression. Hervé Abdi 1 The University of Texas at Dallas Introduction Pls regression is a recent technique that generalizes and combines features from principal component

More information

Manufacturing Service Quality: An Internal Customer Perspective

Manufacturing Service Quality: An Internal Customer Perspective International Conference on E-business Management and Economics IPEDR vol. () () IACSIT Press Hong Kong Manufacturing Service Quality: An Internal Customer Perspective Gyan Prakash ABV-Indian Institute

More information

How to report the percentage of explained common variance in exploratory factor analysis

How to report the percentage of explained common variance in exploratory factor analysis UNIVERSITAT ROVIRA I VIRGILI How to report the percentage of explained common variance in exploratory factor analysis Tarragona 2013 Please reference this document as: Lorenzo-Seva, U. (2013). How to report

More information

NEW YORK STATE TEACHER CERTIFICATION EXAMINATIONS

NEW YORK STATE TEACHER CERTIFICATION EXAMINATIONS NEW YORK STATE TEACHER CERTIFICATION EXAMINATIONS TEST DESIGN AND FRAMEWORK September 2014 Authorized for Distribution by the New York State Education Department This test design and framework document

More information

Missing Data: Part 1 What to Do? Carol B. Thompson Johns Hopkins Biostatistics Center SON Brown Bag 3/20/13

Missing Data: Part 1 What to Do? Carol B. Thompson Johns Hopkins Biostatistics Center SON Brown Bag 3/20/13 Missing Data: Part 1 What to Do? Carol B. Thompson Johns Hopkins Biostatistics Center SON Brown Bag 3/20/13 Overview Missingness and impact on statistical analysis Missing data assumptions/mechanisms Conventional

More information

Multivariate Analysis (Slides 13)

Multivariate Analysis (Slides 13) Multivariate Analysis (Slides 13) The final topic we consider is Factor Analysis. A Factor Analysis is a mathematical approach for attempting to explain the correlation between a large set of variables

More information

Chapter 6: Multivariate Cointegration Analysis

Chapter 6: Multivariate Cointegration Analysis Chapter 6: Multivariate Cointegration Analysis 1 Contents: Lehrstuhl für Department Empirische of Wirtschaftsforschung Empirical Research and und Econometrics Ökonometrie VI. Multivariate Cointegration

More information

RMTD 404 Introduction to Linear Models

RMTD 404 Introduction to Linear Models RMTD 404 Introduction to Linear Models Instructor: Ken A., Assistant Professor E-mail: kfujimoto@luc.edu Phone: (312) 915-6852 Office: Lewis Towers, Room 1037 Office hour: By appointment Course Content

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

A REVIEW OF CURRENT SOFTWARE FOR HANDLING MISSING DATA

A REVIEW OF CURRENT SOFTWARE FOR HANDLING MISSING DATA 123 Kwantitatieve Methoden (1999), 62, 123-138. A REVIEW OF CURRENT SOFTWARE FOR HANDLING MISSING DATA Joop J. Hox 1 ABSTRACT. When we deal with a large data set with missing data, we have to undertake

More information

Structural equation models and causal analyses in Usability Evaluation

Structural equation models and causal analyses in Usability Evaluation Structural equation models and causal analyses in Usability Evaluation δ 1 x 1 δ 1 x 1 δ 2 x 2 δ 2 x 2 δ 3 δ 3 δ 4 x 4 δ 4 x 4 δ 5 x 5 δ 5 x 5 δ 6 x 6 δ 6 x 6 δ 7 X 7 X 1 δ 7 X 7 δ 8 x 8 δ 8 x 8 δ 9 δ

More information

Multivariate Analysis of Variance (MANOVA)

Multivariate Analysis of Variance (MANOVA) Multivariate Analysis of Variance (MANOVA) Aaron French, Marcelo Macedo, John Poulsen, Tyler Waterson and Angela Yu Keywords: MANCOVA, special cases, assumptions, further reading, computations Introduction

More information

A Review of Methods. for Dealing with Missing Data. Angela L. Cool. Texas A&M University 77843-4225

A Review of Methods. for Dealing with Missing Data. Angela L. Cool. Texas A&M University 77843-4225 Missing Data 1 Running head: DEALING WITH MISSING DATA A Review of Methods for Dealing with Missing Data Angela L. Cool Texas A&M University 77843-4225 Paper presented at the annual meeting of the Southwest

More information

I n d i a n a U n i v e r s i t y U n i v e r s i t y I n f o r m a t i o n T e c h n o l o g y S e r v i c e s

I n d i a n a U n i v e r s i t y U n i v e r s i t y I n f o r m a t i o n T e c h n o l o g y S e r v i c e s I n d i a n a U n i v e r s i t y U n i v e r s i t y I n f o r m a t i o n T e c h n o l o g y S e r v i c e s Confirmatory Factor Analysis using Amos, LISREL, Mplus, SAS/STAT CALIS* Jeremy J. Albright

More information

Standard errors of marginal effects in the heteroskedastic probit model

Standard errors of marginal effects in the heteroskedastic probit model Standard errors of marginal effects in the heteroskedastic probit model Thomas Cornelißen Discussion Paper No. 320 August 2005 ISSN: 0949 9962 Abstract In non-linear regression models, such as the heteroskedastic

More information

What Are Principal Components Analysis and Exploratory Factor Analysis?

What Are Principal Components Analysis and Exploratory Factor Analysis? Statistics Corner Questions and answers about language testing statistics: Principal components analysis and exploratory factor analysis Definitions, differences, and choices James Dean Brown University

More information

Presentation Outline. Structural Equation Modeling (SEM) for Dummies. What Is Structural Equation Modeling?

Presentation Outline. Structural Equation Modeling (SEM) for Dummies. What Is Structural Equation Modeling? Structural Equation Modeling (SEM) for Dummies Joseph J. Sudano, Jr., PhD Center for Health Care Research and Policy Case Western Reserve University at The MetroHealth System Presentation Outline Conceptual

More information

UNDERSTANDING ANALYSIS OF COVARIANCE (ANCOVA)

UNDERSTANDING ANALYSIS OF COVARIANCE (ANCOVA) UNDERSTANDING ANALYSIS OF COVARIANCE () In general, research is conducted for the purpose of explaining the effects of the independent variable on the dependent variable, and the purpose of research design

More information

CHAPTER 8 FACTOR EXTRACTION BY MATRIX FACTORING TECHNIQUES. From Exploratory Factor Analysis Ledyard R Tucker and Robert C.

CHAPTER 8 FACTOR EXTRACTION BY MATRIX FACTORING TECHNIQUES. From Exploratory Factor Analysis Ledyard R Tucker and Robert C. CHAPTER 8 FACTOR EXTRACTION BY MATRIX FACTORING TECHNIQUES From Exploratory Factor Analysis Ledyard R Tucker and Robert C MacCallum 1997 180 CHAPTER 8 FACTOR EXTRACTION BY MATRIX FACTORING TECHNIQUES In

More information

Similarity and Diagonalization. Similar Matrices

Similarity and Diagonalization. Similar Matrices MATH022 Linear Algebra Brief lecture notes 48 Similarity and Diagonalization Similar Matrices Let A and B be n n matrices. We say that A is similar to B if there is an invertible n n matrix P such that

More information

Application of discriminant analysis to predict the class of degree for graduating students in a university system

Application of discriminant analysis to predict the class of degree for graduating students in a university system International Journal of Physical Sciences Vol. 4 (), pp. 06-0, January, 009 Available online at http://www.academicjournals.org/ijps ISSN 99-950 009 Academic Journals Full Length Research Paper Application

More information

Orthogonal Projections

Orthogonal Projections Orthogonal Projections and Reflections (with exercises) by D. Klain Version.. Corrections and comments are welcome! Orthogonal Projections Let X,..., X k be a family of linearly independent (column) vectors

More information

Review Jeopardy. Blue vs. Orange. Review Jeopardy

Review Jeopardy. Blue vs. Orange. Review Jeopardy Review Jeopardy Blue vs. Orange Review Jeopardy Jeopardy Round Lectures 0-3 Jeopardy Round $200 How could I measure how far apart (i.e. how different) two observations, y 1 and y 2, are from each other?

More information

Longitudinal Meta-analysis

Longitudinal Meta-analysis Quality & Quantity 38: 381 389, 2004. 2004 Kluwer Academic Publishers. Printed in the Netherlands. 381 Longitudinal Meta-analysis CORA J. M. MAAS, JOOP J. HOX and GERTY J. L. M. LENSVELT-MULDERS Department

More information

ZHIYONG ZHANG AND LIJUAN WANG

ZHIYONG ZHANG AND LIJUAN WANG PSYCHOMETRIKA VOL. 78, NO. 1, 154 184 JANUARY 2013 DOI: 10.1007/S11336-012-9301-5 METHODS FOR MEDIATION ANALYSIS WITH MISSING DATA ZHIYONG ZHANG AND LIJUAN WANG UNIVERSITY OF NOTRE DAME Despite wide applications

More information

Factor Analysis. Principal components factor analysis. Use of extracted factors in multivariate dependency models

Factor Analysis. Principal components factor analysis. Use of extracted factors in multivariate dependency models Factor Analysis Principal components factor analysis Use of extracted factors in multivariate dependency models 2 KEY CONCEPTS ***** Factor Analysis Interdependency technique Assumptions of factor analysis

More information

Number Patterns, Cautionary Tales and Finite Differences

Number Patterns, Cautionary Tales and Finite Differences Learning and Teaching Mathematics, No. Page Number Patterns, Cautionary Tales and Finite Differences Duncan Samson St Andrew s College Number Patterns I recently included the following question in a scholarship

More information

Bayesian probability theory

Bayesian probability theory Bayesian probability theory Bruno A. Olshausen arch 1, 2004 Abstract Bayesian probability theory provides a mathematical framework for peforming inference, or reasoning, using probability. The foundations

More information

15.062 Data Mining: Algorithms and Applications Matrix Math Review

15.062 Data Mining: Algorithms and Applications Matrix Math Review .6 Data Mining: Algorithms and Applications Matrix Math Review The purpose of this document is to give a brief review of selected linear algebra concepts that will be useful for the course and to develop

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

Linear Algebra Notes for Marsden and Tromba Vector Calculus

Linear Algebra Notes for Marsden and Tromba Vector Calculus Linear Algebra Notes for Marsden and Tromba Vector Calculus n-dimensional Euclidean Space and Matrices Definition of n space As was learned in Math b, a point in Euclidean three space can be thought of

More information

SPSS and AMOS. Miss Brenda Lee 2:00p.m. 6:00p.m. 24 th July, 2015 The Open University of Hong Kong

SPSS and AMOS. Miss Brenda Lee 2:00p.m. 6:00p.m. 24 th July, 2015 The Open University of Hong Kong Seminar on Quantitative Data Analysis: SPSS and AMOS Miss Brenda Lee 2:00p.m. 6:00p.m. 24 th July, 2015 The Open University of Hong Kong SBAS (Hong Kong) Ltd. All Rights Reserved. 1 Agenda MANOVA, Repeated

More information

REVIEWING THREE DECADES WORTH OF STATISTICAL ADVANCEMENTS IN INDUSTRIAL-ORGANIZATIONAL PSYCHOLOGICAL RESEARCH

REVIEWING THREE DECADES WORTH OF STATISTICAL ADVANCEMENTS IN INDUSTRIAL-ORGANIZATIONAL PSYCHOLOGICAL RESEARCH 1 REVIEWING THREE DECADES WORTH OF STATISTICAL ADVANCEMENTS IN INDUSTRIAL-ORGANIZATIONAL PSYCHOLOGICAL RESEARCH Nicholas Wrobel Faculty Sponsor: Kanako Taku Department of Psychology, Oakland University

More information

Association Between Variables

Association Between Variables Contents 11 Association Between Variables 767 11.1 Introduction............................ 767 11.1.1 Measure of Association................. 768 11.1.2 Chapter Summary.................... 769 11.2 Chi

More information

UNDERSTANDING THE DEPENDENT-SAMPLES t TEST

UNDERSTANDING THE DEPENDENT-SAMPLES t TEST UNDERSTANDING THE DEPENDENT-SAMPLES t TEST A dependent-samples t test (a.k.a. matched or paired-samples, matched-pairs, samples, or subjects, simple repeated-measures or within-groups, or correlated groups)

More information

Moderation. Moderation

Moderation. Moderation Stats - Moderation Moderation A moderator is a variable that specifies conditions under which a given predictor is related to an outcome. The moderator explains when a DV and IV are related. Moderation

More information

FACTOR ANALYSIS NASC

FACTOR ANALYSIS NASC FACTOR ANALYSIS NASC Factor Analysis A data reduction technique designed to represent a wide range of attributes on a smaller number of dimensions. Aim is to identify groups of variables which are relatively

More information

Merged Structural Equation Model of Online Retailer's Customer Preference and Stickiness

Merged Structural Equation Model of Online Retailer's Customer Preference and Stickiness Merged Structural Equation Model of Online Retailer's Customer Preference and Stickiness Sri Hastuti Kurniawan Wayne State University, 226 Knapp Building, 87 E. Ferry, Detroit, MI 48202, USA af7804@wayne.edu

More information

Applications of multiple regression analysis in social scientific

Applications of multiple regression analysis in social scientific SOCIOLOGICAL Maassen, Bakker / METHODS SUPPRESSOR & RESEARCH VARIABLES IN PATH MODELS Suppressor variables are well known in the context of multiple regression analysis. Using several examples, the authors

More information

MULTIPLE REGRESSION ANALYSIS OF MAIN ECONOMIC INDICATORS IN TOURISM. R, analysis of variance, Student test, multivariate analysis

MULTIPLE REGRESSION ANALYSIS OF MAIN ECONOMIC INDICATORS IN TOURISM. R, analysis of variance, Student test, multivariate analysis Journal of tourism [No. 8] MULTIPLE REGRESSION ANALYSIS OF MAIN ECONOMIC INDICATORS IN TOURISM Assistant Ph.D. Erika KULCSÁR Babeş Bolyai University of Cluj Napoca, Romania Abstract This paper analysis

More information

" Y. Notation and Equations for Regression Lecture 11/4. Notation:

 Y. Notation and Equations for Regression Lecture 11/4. Notation: Notation: Notation and Equations for Regression Lecture 11/4 m: The number of predictor variables in a regression Xi: One of multiple predictor variables. The subscript i represents any number from 1 through

More information

Multivariate Statistical Inference and Applications

Multivariate Statistical Inference and Applications Multivariate Statistical Inference and Applications ALVIN C. RENCHER Department of Statistics Brigham Young University A Wiley-Interscience Publication JOHN WILEY & SONS, INC. New York Chichester Weinheim

More information

1 Short Introduction to Time Series

1 Short Introduction to Time Series ECONOMICS 7344, Spring 202 Bent E. Sørensen January 24, 202 Short Introduction to Time Series A time series is a collection of stochastic variables x,.., x t,.., x T indexed by an integer value t. The

More information

Goodness of fit assessment of item response theory models

Goodness of fit assessment of item response theory models Goodness of fit assessment of item response theory models Alberto Maydeu Olivares University of Barcelona Madrid November 1, 014 Outline Introduction Overall goodness of fit testing Two examples Assessing

More information

A Beginner s Guide to Factor Analysis: Focusing on Exploratory Factor Analysis

A Beginner s Guide to Factor Analysis: Focusing on Exploratory Factor Analysis Tutorials in Quantitative Methods for Psychology 2013, Vol. 9(2), p. 79-94. A Beginner s Guide to Factor Analysis: Focusing on Exploratory Factor Analysis An Gie Yong and Sean Pearce University of Ottawa

More information

MULTIPLE REGRESSION AND ISSUES IN REGRESSION ANALYSIS

MULTIPLE REGRESSION AND ISSUES IN REGRESSION ANALYSIS MULTIPLE REGRESSION AND ISSUES IN REGRESSION ANALYSIS MSR = Mean Regression Sum of Squares MSE = Mean Squared Error RSS = Regression Sum of Squares SSE = Sum of Squared Errors/Residuals α = Level of Significance

More information

Kittipat Laisasikorn Thammasat Business School. Nopadol Rompho Thammasat Business School

Kittipat Laisasikorn Thammasat Business School. Nopadol Rompho Thammasat Business School A Study of the Relationship Between a Successful Enterprise Risk Management System, a Performance Measurement System and the Financial Performance of Thai Listed Companies Kittipat Laisasikorn Thammasat

More information

Inner Product Spaces

Inner Product Spaces Math 571 Inner Product Spaces 1. Preliminaries An inner product space is a vector space V along with a function, called an inner product which associates each pair of vectors u, v with a scalar u, v, and

More information