Psychometrika

, 72:123

Multilevel and Latent Variable Modeling with Composite Links and Exploded Likelihoods

Article

Abstract

Composite links and exploded likelihoods are powerful yet simple tools for specifying a wide range of latent variable models. Applications considered include survival or duration models, models for rankings, small area estimation with census information, models for ordinal responses, item response models with guessing, randomized response models, unfolding models, latent class models with random effects, multilevel latent class models, models with log-normal latent variables, and zero-inflated Poisson models with random effects. Some of the ideas are illustrated by estimating an unfolding model for attitudes to female work participation.

Key words

composite link exploded likelihood unfolding multilevel model generalized linear mixed model latent variable model item response model factor model frailty zero-inflated Poisson model gllamm 

References

  1. Allison, P.D. (1982). Discrete time methods for the analysis of event histories. In S. Leinhardt (Ed.), Sociological methodology 1982. San Francisco: Jossey-Bass.Google Scholar
  2. Allison, P.D. (1987). Introducing a disturbance into logit and probit regression models. Sociological Methods & Research, 15, 355–374.CrossRefGoogle Scholar
  3. Allison, P.D., & Christakis, N.A. (1994). Logit models for sets of ranked items. In P.V. Marsden (Ed.), Sociological methodology 1994 (pp. 199–228). Oxford: Blackwell.Google Scholar
  4. Andrich, D. (1989). A probabilistic item response theory model for unfolding preference data. Applied Psychological Measurement, 13, 193–216.CrossRefGoogle Scholar
  5. Andrich, D. (1995). Hyperbolic cosine latent trait models for unfolding direct-responses and pairwise preferences. Applied Psychological Measurement, 19, 269–290.CrossRefGoogle Scholar
  6. Andrich, D. (1996). A hyperbolic cosine latent trait model for unfolding polytomous responses: Reconciling Thurstone and Likert methodologies. British Journal of Mathematical and Statistical Psychology, 49, 347–365.Google Scholar
  7. Andrich, D., & Luo, G. (1993). A hyperbolic cosine latent trait model for unfolding dichotomous single stimulus responses. Applied Psychological Measurement, 17, 253–276.CrossRefGoogle Scholar
  8. Bartholomew, D.J., & Knott, M. (1999). Latent variable models and factor analysis. London: Arnold.Google Scholar
  9. Birnbaum, A. (1968). Test scores, sufficient statistics, and the information structures of tests. In F.M. Lord, & M.R. Novick (Eds.), Statistical theories of mental test scores (pp. 425–435). Reading, MA: Addison-Wesley.Google Scholar
  10. Böckenholt, U. (2001). Mixed-effects analyses of rank-ordered data. Psychometrika, 66, 45–62.CrossRefGoogle Scholar
  11. Böckenholt, U., & van der Heijden, P.G.M. (2007). Item randomized-response models for measuring noncompliance: Risk-return perceptions, social influences, and self-protective responses. Psychometrika, 72, DOI: 10.1007/s11336-005-1495-y.Google Scholar
  12. Breslow, N.E., & Clayton, D.G. (1993). Approximate inference in generalized linear mixed models. Journal of the American Statistical Association, 88, 9–25.CrossRefGoogle Scholar
  13. Candy, S.G. (1997). Estimation in forest yield models using composite link functions with random effects. Biometrics, 53, 146–160.CrossRefGoogle Scholar
  14. Chapman, R.G., & Staelin, R. (1982). Exploiting rank ordered choice set data within the stochastic utility model. Journal of Marketing Research, 14, 288–301.CrossRefGoogle Scholar
  15. Chen, Z., & Kuo, L. (2001). A note on the estimation of the multinomial logit model with random effects. The American Statistician, 55, 89–95.CrossRefGoogle Scholar
  16. Clayton, D.G. (1988). The analysis of event history data: A review of progress and outstanding problems. Statistics in Medicine, 7, 819–841.CrossRefPubMedGoogle Scholar
  17. Clayton, D.G., Spiegelhalter, D., Dunn, G., & Pickles, A. (1998). Analysis of longitudinal binary data from multiphase sampling. Journal of the Royal Statistical Society, Series B, 60, 71–77.Google Scholar
  18. Coombs, C.H. (1964). A theory of data. New York: Wiley.Google Scholar
  19. Cox, C. (1984). Generalized linear models—The missing link. Journal of the Royal Statistical Society, Series C, 33, 18–24.Google Scholar
  20. Cox, D.R. (1972). Regression models and life tables. Journal of the Royal Statistical Society, Series B, 34, 187–203.Google Scholar
  21. Davis, J.A., Smith, T.W., & Marsden, P.V. (2003). General social surveys, 1972–2002 [Cumulative File]. Ann Arbor, MI: ICPSR [Distributor].Google Scholar
  22. Dayton, C.M., & MacReady, G.B. (1988). Concomitant variable latent class models. Journal of the American Statistical Association, 83, 173–178.CrossRefGoogle Scholar
  23. De Boeck, P., & Wilson, M. (Eds.) (2004). Explanatory item response models: A generalized linear and nonlinear approach. New York: Springer.Google Scholar
  24. DeSarbo, W.S., & Hoffman, D.L. (1986). Simple unweighted unfolding threshold models for the spatial representation of binary choice data. Applied Psychological Measurement, 10, 247–264.CrossRefGoogle Scholar
  25. Eilers, P.H.C., & Borgdorff, M.W. (2004). Modeling and correction of digit preference in tuberculin surveys. The International Journal of Tubercolosis and Lung Disease, 8, 232–239.Google Scholar
  26. Engel, R. (1993). On the analysis of grouped extreme value data with GLIM. Journal of the Royal Statistical Society, Series C, 42, 633–640.Google Scholar
  27. Espeland, M.A., & Hui, S.L. (1987). A general approach to analyzing epidemiologic data that contain misclassification errors. Biometrics, 43, 1001–1012.CrossRefPubMedGoogle Scholar
  28. Fielding, A. (2003). Ordered category responses and random effects in multilevel and other complex structures. In S.P. Reise, & N. Duan (Eds.), Multilevel modeling. Methodological advances, issues, and applications (pp. 181–208). Mahwah, NJ: Erlbaum.Google Scholar
  29. Finney, D.J. (1971). Probit analysis. Cambridge: Cambridge University Press.Google Scholar
  30. Fox, J.P. (2005). Randomized item response theory models. Journal of Educational and Behavioral Statistics, 30, 1–24.CrossRefGoogle Scholar
  31. Fox, J.P., & Glas, C.A.W. (2001). Bayesian estimation of a multilevel IRT model using Gibbs sampling. Psychometrika, 66, 271–288.CrossRefGoogle Scholar
  32. Goldstein, H. (2003). Multilevel statistical models (3rd ed.). London: Arnold.Google Scholar
  33. Goldstein, H., & McDonald, R.P. (1988). A general model for the analysis of multilevel data. Psychometrika, 53, 455–467.CrossRefGoogle Scholar
  34. Haberman, S.J. (1979). Analysis of qualitative data: New developments (Vol. 2). New York: Academic Press.Google Scholar
  35. Hall, D.B. (2000). Zero-inflated Poisson and binomial regression with random effects: A case study. Biometrics, 56, 1030–1039.CrossRefPubMedGoogle Scholar
  36. Heckman, J.J., & Singer, B. (1984). A method of minimizing the impact of distributional assumptions in econometric models for duration data. Econometrica, 52, 271–320.CrossRefGoogle Scholar
  37. Heisterkamp, S.H., van Houwelingen, J.C., & Downs, A.M. (1999). Empirical Bayesian estimators for a Poisson process propagated in time. Biometrical Journal, 41, 385–400.CrossRefGoogle Scholar
  38. Hoijtink, H. (1990). A latent trait model for dichotomous choice data. Psychometrika, 55, 641–656.CrossRefGoogle Scholar
  39. Holford, T.R. (1976). Life tables with concomitant variables. Biometrics, 32, 587–597.CrossRefPubMedGoogle Scholar
  40. Jansen, J. (1992). Statistical analysis of threshold data from experiments with nested errors. Computational Statistics & Data Analysis, 13, 319–330.CrossRefGoogle Scholar
  41. Johnson, M.S. (2006). Nonparametric estimation of item and respondent locations from unfolding-type items. Psychometrika, 71, 257–279.CrossRefGoogle Scholar
  42. Klein, A., & Moosbrugger, H. (2000). Maximum likelihood estimation of latent interaction effects with the LMS method. Psychometrika, 65, 457–474.CrossRefGoogle Scholar
  43. Läärä, E., & Matthews, J.N.S. (1985). The equivalence of two models for ordinal data. Biometrika, 72, 206–207.Google Scholar
  44. Laird, N.M. (1978). Nonparametric maximum likelihood estimation of a mixing distribution. Journal of the American Statistical Association, 73, 805–811.CrossRefGoogle Scholar
  45. Lambert, D. (1992). Zero-inflated Poisson-regression with an application to defects in manufacturing. Technometrics, 34, 1–14.CrossRefGoogle Scholar
  46. Lee, S.-Y., & Song, X.-Y. (2004). Maximum likelihood analysis of a general latent variable model with hierarchically mixed data. Biometrics, 60, 624–636.CrossRefPubMedGoogle Scholar
  47. Luce, R.D. (1959). Individual choice behavior. New York: Wiley.Google Scholar
  48. Magder, S.M., & Hughes, J.P. (1997). Logistic regression when the outcome is measured with uncertainty. American Journal of Epidemiology, 146, 195–203.PubMedGoogle Scholar
  49. McCullagh, P., & Nelder, J.A. (1989). Generalized linear models (2nd ed.). London: Chapman & Hall.Google Scholar
  50. Muthén, B.O. (1989). Latent variable modeling in heterogeneous populations. Psychometrika, 54, 557–585.CrossRefGoogle Scholar
  51. Muthén, B.O. (2002). Beyond SEM: General latent variable modeling. Behaviormetrika, 29, 81–117.CrossRefGoogle Scholar
  52. Muthén, B.O., & Masyn, K. (2005). Dicrete-time survival mixture analysis. Journal of Educational and Behavioral Statistics, 30, 27–58.CrossRefGoogle Scholar
  53. Neuhaus, J.M. (1999). Bias and efficiency loss due to misclassified responses in binary regression. Biometrika, 86, 843–855.CrossRefGoogle Scholar
  54. Noël, Y. (1999). Recovering unimodal latent patterns of change by unfolding analysis: Application to smoking cessation. Psychological Methods, 4, 173–191.CrossRefGoogle Scholar
  55. Palmgren, J. (1981). The Fisher information matrix for log linear models arguing conditionally on observed explanatory variables. Biometrika, 68, 563–566.Google Scholar
  56. Plackett, R.L. (1975). The analysis of permutations. Journal of the Royal Statistical Society, Series C, 24, 193–202.Google Scholar
  57. Qu, Y., Tan, M., & Kutner, M.H. (1996). Random effects models in latent class analysis for evaluating accuracy of diagnostic tests. Biometrics, 52, 797–810.CrossRefPubMedGoogle Scholar
  58. Rabe-Hesketh, S., & Skrondal, A. (2005). Multilevel and longitudinal modeling using Stata. College Station, TX: Stata Press.Google Scholar
  59. Rabe-Hesketh, S., & Skrondal, A. (2006). Multilevel modeling of complex survey data. Journal of the Royal Statistical Society, Series A, 116, 805–827.Google Scholar
  60. Rabe-Hesketh, S., Pickles, A., & Skrondal, A. (2003). Correcting for covariate measurement error in logistic regression using nonparametric maximum likelihood estimation. Statistical Modelling, 3, 215–232.CrossRefGoogle Scholar
  61. Rabe-Hesketh, S., Skrondal, A., & Pickles, A. (2004a). Generalized multilevel structural equation modeling. Psychometrika, 69, 167–190.CrossRefGoogle Scholar
  62. Rabe-Hesketh, S., Skrondal, A., & Pickles, A. (2004b). GLLAMM manual. Technical report 160. U.C. Berkeley Division of Biostatistics Working Paper Series. Downloadable from http://www.bepress.com/ucbbiostat/paper160/.Google Scholar
  63. Rabe-Hesketh, S., Skrondal, A., & Pickles, A. (2005). Maximum likelihood estimation of limited and discrete dependent variable models with nested random effects. Journal of Econometrics, 128, 301–323.CrossRefGoogle Scholar
  64. Rabe-Hesketh, S., Yang, S., & Pickles, A. (2001). Multilevel models for censored and latent responses. Statistical Methods in Medical Research, 10, 409–427.CrossRefPubMedGoogle Scholar
  65. Rijmen, F., Tuerlinckx, F., De Boeck, P., & Kuppens, P. (2003). A nonlinear mixed model framework for item response theory. Psychological Methods, 8, 185–205.CrossRefPubMedGoogle Scholar
  66. Rindskopf, D. (1992). A general approach to categorical data analysis with missing data, using generalized linear models with composite links. Psychometrika, 57, 29–42.CrossRefGoogle Scholar
  67. Roberts, J.S., & Laughlin, J.E. (1996). A unidimensional item response model for unfolding responses from a graded disagree–agree response scale. Applied Psychological Measurement, 20, 231–255.CrossRefGoogle Scholar
  68. Samejima, F. (1969). Estimation of latent trait ability using a response pattern of graded scores. Psychometric Monograph, Vol. 17. Bowling Green, OH: The Psychometric Society.Google Scholar
  69. Skrondal, A., & Rabe-Hesketh, S. (2003). Multilevel logistic regression for polytomous data and rankings. Psychometrika, 68, 267–287.CrossRefGoogle Scholar
  70. Skrondal, A., & Rabe-Hesketh, S. (2004a). Generalised linear latent and mixed models with composite links and exploded likelihoods. In A. Biggeri, E. Dreassi, C. Lagazio, & M. Marchi (Eds.), 19th International workshop on statistical modeling (pp. 27–29). Florence: Firenze University Press.Google Scholar
  71. Skrondal, A., & Rabe-Hesketh, S. (2004b). Generalized latent variable modeling: Multilevel, longitudinal, and structural equation models. Boca Raton, FL: Chapman & Hall/CRC.Google Scholar
  72. Takane, Y., & de Leeuw, J. (1987). On the relationship between item response theory and factor analysis of discretized variables. Psychometrika, 52, 393–408.CrossRefGoogle Scholar
  73. Terza, J.V. (1985). Ordinal probit: A generalization. Communications in Statistics, Theory and Methods, 14, 1–11.Google Scholar
  74. Thissen, D., & Steinberg, L. (1986). A taxonomy of item response models. Psychometrika, 51, 567–577.CrossRefGoogle Scholar
  75. Thompson, R., & Baker, R.J. (1981). Composite link functions in generalized linear models. Journal of the Royal Statistical Society, Series C, 30, 125–131.Google Scholar
  76. Thurstone, L.L. (1928). Attitudes can be measured. American Journal of Sociology, 33, 529–554.CrossRefGoogle Scholar
  77. Tranmer, M., Pickles, A., Fieldhouse, E., Elliot, M., Dale, A., Brown, M., Martin, D., Steel, D., & Gardiner, C. (2005). The case for small area microdata. Journal of the Royal Statistical Society, Series A, 168, 29–39.Google Scholar
  78. Verhelst, N.D., & Verstralen, H.H.F.M. (1993). A stochastic unfolding model derived from the partial credit model. Kwantitative Methoden, 42, 73–92.Google Scholar
  79. Vermunt, J.K. 1997. Log-linear models for event histories. Thousand Oaks, CA: Sage.Google Scholar
  80. Vermunt, J.K. (2001). The use of restricted latent class models for defining and testing nonparametric item response theory models. Applied Psychological Measurement, 25, 283–294.CrossRefGoogle Scholar
  81. Vermunt, J.K. (2003). Multilevel latent class models. In R.M. Stolzenberg (Ed.), Sociological methodology 2003 (Vol. 33, pp. 213–239). Oxford: Blackwell.Google Scholar
  82. Vermunt, J.K. (in press). Latent class and finite mixture models for multilevel data sets. Statistical Methods in Medical Research.Google Scholar
  83. Warner, S.L. (1965). Randomized response: A survey technique for eliminating evasive answer bias. Journal of the American Statistical Association, 60, 63–69.CrossRefPubMedGoogle Scholar
  84. Whitehead, J. (1980). Fitting Cox’s regression model to survival data using GLIM. Journal of the Royal Statistical Society, Series C, 29, 269–275.Google Scholar

Copyright information

© The Psychometric Society 2007

Authors and Affiliations

  1. 1.Graduate School of EducationUniversity of California at Berkeley and University of LondonBerkeleyUSA
  2. 2.London School of Economics and Norwegian Institute of Public HealthLondon

Personalised recommendations