Latent variable modeling in heterogeneous populations

Common applications of latent variable analysis fail to recognize that data may be obtained from several populations with different sets of parameter values. This article describes the problem and gives an overview of methodology that can address heterogeneity. Artificial examples of mixtures are given, where if the mixture is not recognized, strongly distorted results occur. MIMIC structural modeling is shown to be a useful method for detecting and describing heterogeneity that cannot be handled in regular multiple-group analysis. Other useful methods instead take a random effects approach, describing heterogeneity in terms of random parameter variation across groups. These random effects models connect with emerging methodology for multilevel structural equation modeling of hierarchical data. Examples are drawn from educational achievement testing, psychopathology, and sociology of education. Estimation is carried out by the LISCOMP program.

[1]  William Meredith,et al.  Notes on factorial invariance , 1964 .

[2]  G. C. Tiao,et al.  BAYESIAN ANALYSIS OF RANDOM-EFFECT MODELS IN THE ANALYSIS OF VARIANCE. I. POSTERIOR DISTRIBUTION OF VARIANCE-COMPONENTS. , 1965 .

[3]  G. C. Tiao,et al.  Bayesian analysis of random-effect models in the analysis of variance II. Effect of autocorrelated erros , 1966 .

[4]  M. R. Novick,et al.  Statistical Theories of Mental Test Scores. , 1971 .

[5]  P. Swamy.  Efficient Inference in a Random Coefficient Regression Model , 1970 .

[6]  K. Jöreskog.  A General Method for Estimating a Linear Structural Equation System. , 1970 .

[7]  A. Goldberger,et al.  The Treatment of Unobservable Variables in Path Analysis , 1971 .

[8]  D. Lindley,et al.  Bayes Estimates for the Linear Model , 1972 .

[9]  W. R. Buckland,et al.  Distributions in Statistics: Continuous Multivariate Distributions , 1973 .

[10]  A. Goldberger,et al.  Structural Equation Models in the Social Sciences. , 1974 .

[11]  D. Sörbom.  A GENERAL METHOD FOR STUDYING DIFFERENCES IN FACTOR MEANS AND FACTOR STRUCTURE BETWEEN GROUPS , 1974 .

[12]  P. Krishnaiah,et al.  On Covariance Structures. , 1975 .

[13]  R. Owen,et al.  A Bayesian Sequential Procedure for Quantal Response in the Context of Adaptive Mental Testing , 1975 .

[14]  W. R. Buckland,et al.  Distributions in Statistics: Continuous Multivariate Distributions , 1973 .

[15]  A. Goldberger,et al.  Estimation of a Model with Multiple Indicators and Multiple Causes of a Single Latent Variable , 1975 .

[16]  Lee J. Cronbach,et al.  Research on Classrooms and Schools: Formulation of Questions, Design and Analysis. , 1976 .

[17]  Kjell H rnqvist.  Primary Mental Abilities at collective and individual levels. , 1978 .

[18]  K. Jöreskog.  Structural analysis of covariance and correlation matrices , 1978 .

[19]  Mundlak.  Models with Variable Coefficients: Integration and Extension , 1978 .

[20]  Kjell Harnqvist,et al.  Primary Mental Abilities at Collective and Individual Levels. , 1978 .

[21]  B. Muthén.  Contributions to factor analysis of dichotomous variables , 1978 .

[22]  Ulf Olsson,et al.  Maximum likelihood estimation of the polychoric correlation coefficient , 1979 .

[23]  Bengt Muthén,et al.  A Structural Probit Model with Latent Variables , 1979 .

[24]  L. Poundie Burstein.  The Analysis of Multilevel Data in Educational Research and Evaluation , 1980 .

[25]  P. Bentler.  MULTIVARIATE ANALYSIS WITH LATENT VARIABLES: CAUSAL MODELING , 1980 .

[26]  Donald B. Rubin,et al.  Using Empirical Bayes Techniques in the Law School Validity Studies , 1980 .

[27]  L. Poundie Burstein.  Chapter 4: The Analysis of Multilevel Data in Educational Research and Evaluation , 1980 .

[28]  D. Sorbom,et al.  Structural equation models with structured means , 1981 .

[29]  John P. Robinson,et al.  Questions and answers in attitude surveys , 1982 .

[30]  Bengt Muthén,et al.  Simultaneous factor analysis of dichotomous variables in several groups , 1981 .

[31]  R. Sternberg.  Advances in the psychology of human intelligence , 1982 .

[32]  A. Cohen,et al.  Finite Mixture Distributions , 1982 .

[33]  F. Drasgow,et al.  The polyserial correlation coefficient , 1982 .

[34]  G. Maddala.  Limited-dependent and qualitative variables in econometrics: Introduction , 1983 .

[35]  P. Bentler.  Some contributions to efficient statistics in structural models: Specification and estimation of moment structures , 1983 .

[36]  Barbara Entwisle,et al.  Contextual analysis through the multilevel linear model. , 1983 .

[37]  B. Muthén.  Latent variable structural equation modeling with categorical data , 1983 .

[38]  Karl G. Jöreskog,et al.  Selectivity Problems in Quasi-Experimental Studies , 1983 .

[39]  Donald B. Rubin,et al.  Some applications of Bayesian statistics to educational data , 1983 .

[40]  Donald B. Rubin,et al.  Empirical bayes estimation of coefficients in the general linear model from data of deficient rank , 1983 .

[41]  P. Schmidt,et al.  Limited-Dependent and Qualitative Variables in Econometrics. , 1984 .

[42]  B. Muthén.  A general structural equation model with dichotomous, ordered categorical, and continuous latent variable indicators , 1984 .

[43]  M. Browne.  Asymptotically distribution-free methods for the analysis of covariance structures. , 1984, The British journal of mathematical and statistical psychology.

[44]  A. Satorra,et al.  Power of the likelihood ratio test in covariance structure analysis , 1985 .

[45]  G. Y. Wong,et al.  The Hierarchical Logistic Regression Model for Multilevel Analysis , 1985 .

[46]  F. Joe Crosswhite,et al.  Second International Mathematics Study. Summary Report for the United States. Contractor's Report. , 1985 .

[47]  John B. Willett,et al.  Understanding correlates of change by modeling individual differences in growth , 1985 .

[48]  Robert J. Mislevy,et al.  Estimation of Latent Group Effects , 1985 .

[49]  M. Aitkin,et al.  Statistical Modelling Issues in School Effectiveness Studies , 1986 .

[50]  Jan de Leeuw,et al.  Random Coefficient Models for Multilevel Analysis , 1986 .

[51]  H. Goldstein.  Multilevel mixed linear model analysis using iterative generalized least squares , 1986 .

[52]  Bengt Muthen,et al.  Some uses of structural equation modeling in validity studies: Extending IRT to external variables , 1986 .

[53]  Kentaro Yamamoto,et al.  A Model That Combines IRT and Latent Class Models , 1987 .

[54]  N. Longford.  A fast scoring algorithm for maximum likelihood estimation in unbalanced mixed models with nested random effects , 1987 .

[55]  Robert D. Gibbons,et al.  Trend in correlated proportions , 1987 .

[56]  Harvey Goldstein,et al.  Multilevel Models in Education and Social Research , 1987 .

[57]  David Rogosa,et al.  Casual Models Do Not Support Scientific Conclusions: A Comment in Support of Freedman , 1987 .

[58]  Anthony S. Bryk,et al.  Methodological Advances in Analyzing the Effects of Schools and Classrooms on Student Learning , 1988 .

[59]  Harvey Goldstein,et al.  A general model for the analysis of multilevel data , 1988 .

[60]  Bengt Muthen,et al.  Instructionally Sensitive Psychometrics: Applications to the Second International Mathematics Study. Rough Draft. , 1988 .

[61]  Phillip L. Ackerman,et al.  Abilities, motivation, and methodology : the Minnesota Symposium on Learning and Individual Differences , 1989 .

[62]  H. Goldstein,et al.  Multilevel Models in Educational and Social Research. , 1989 .

[63]  Bengt Muthén,et al.  Multiple-group structural modelling with non-normal continuous variables. , 1989 .

[64]  D. Holt,et al.  Multilevel Models in Educational and Social Research. , 1988 .

[65]  B. Muthén,et al.  Dichotomous Factor Analysis of Symptom Data , 1989 .

[66]  R. Darrell Bock,et al.  Multilevel analysis of educational data , 1989 .

[67]  R. Darrell Bock,et al.  ADDENDUM: MEASUREMENT OF HUMAN VARIATION: A TWO-STAGE MODEL , 1989 .

[68]  Leigh Burstein,et al.  MULTILEVEL INVESTIGATIONS OF SYSTEMATICALLY VARYING SLOPES: ISSUES, ALTERNATIVES, AND CONSEQUENCES , 1989 .

[69]  Bengt Muthén,et al.  Using item-specific instructional information in achievement modeling , 1989 .

[70]  Harvey Goldstein,et al.  Balanced versus unbalanced designs for linear structural relations in two‐level data , 1989 .

[71]  Bengt Muthén,et al.  MULTILEVEL ASPECTS OF VARYING PARAMETERS IN STRUCTURAL MODELS , 1989 .

[72]  Bengt Muthén,et al.  Moments of the censored and truncated bivariate normal distribution , 1990 .

[73]  Leigh Burstein,et al.  Instructionally Sensitive Psychometrics: Application of a New IRT‐Based Detection Technique to Mathematics Achievement Test Items , 1991 .