, Volume 68, Issue 2, pp 267–287 | Cite as

Multilevel logistic regression for polytomous data and rankings

  • Anders Skrondal
  • Sophia Rabe-Hesketh


We propose a unifying framework for multilevel modeling of polytomous data and rankings, accommodating dependence induced by factor and/or random coefficient structures at different levels. The framework subsumes a wide range of models proposed in disparate methodological literatures. Partial and tied rankings, alternative specific explanatory variables and alternative sets varying across units are handled. The problem of identification is addressed. We develop an estimation and prediction methodology for the model framework which is implemented in the generally available gllamm software. The methodology is applied to party choice and rankings from the 1987–1992 panel of the British Election Study. Three levels are considered: elections, voters and constituencies.

Key words

multilevel models generalized linear latent and mixed models factor models random coefficient models polytomous data rankings first choice discrete choice permutations nominal data gllamm 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Allenby, G.M., & Lenk, P.J. (1994). Modelling household purchase behavior with logistic normal regression.Journal of the American Statistical Association, 89, 1218–1231.Google Scholar
  2. 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, U.K.: Blackwell.Google Scholar
  3. Arbuckle, J., & Nugent, J.H. (1973). A general procedure for parameter estimation for the law of comparative judgment.British Journal of Mathematical and Statistical Psychology, 26, 240–260.Google Scholar
  4. Beggs, S., Cardell, S., & Hausman, J. (1981). Assessing the potential demand for electric cars.Journal of Econometrics, 16, 1–19.Google Scholar
  5. Block, H.D., & Marchak, J. (1960). Random orderings and stochastic theories of responses. In I. Olkin, W. Hoeffting, S. Ghurye, W.G. Madow & H.D. Mann (Eds.),Contributions to probability and statistics: Essays in honor of Harold Hotelling (pp. 97–112). Stanford, CA: Stanford University Press.Google Scholar
  6. Bloxom, B. (1972). The simplex in pair comparisons.Psychometrika, 37, 119–136.Google Scholar
  7. Bock, R.D. (1969). Estimating multinomial response relations. In R. Bose (Ed.),Essays in probability and statistics (pp. 111–132). Chapel Hill, NC: University of North Carolina Press.Google Scholar
  8. Bock, R.D. (1972). Estimating item parameters and latent ability when responses are scored in two or more nominal categories.Psychometrika, 37, 29–51.Google Scholar
  9. Böckenholt, U. (1992). Thurstonian representation for partial ranking data.British Journal of Mathematical and Statistical Psychology, 45, 31–39.Google Scholar
  10. Böckenholt, U. (1993). Application of Thurstonian models to ranking data. In M.A. Fligner & J.S. Verducci (Eds.),Probability models and statistical analysis for ranking data (pp. 157–172). New York, NY: Springer.Google Scholar
  11. Böckenholt, U. (2001a). Mixed-effects analyses of rank-ordered data.Psychometrika, 66, 45–62.Google Scholar
  12. Böckenholt, U. (2001b). Hierarchical modeling of paired comparison data.Psychological Methods, 6, 49–66.Google Scholar
  13. Brady, H.E. (1989). Factor and ideal point analysis for interpersonally incomparable data.Psychometrika, 54, 181–202.Google Scholar
  14. Breslow, N.E. (1974). Covariance analysis of censored survival data.Biometrics, 30, 89–100.Google Scholar
  15. Brody, R.A., & Page, B.I. (1972). Comment: The assessment of policy voting.American Political Science Review, 66, 450–458.Google Scholar
  16. Bunch, D.S. (1991). Estimability in the multinomial probit model.Transportation Research, Part B: Methodological, 25, 1–12.Google Scholar
  17. Carroll, J.D. (1980). Models and methods for multidimensional analysis of preference choice (or other dominance) data. In E.D. Lantermann & H. Feger (Eds.),Similarity and choice (pp. 234–289). Bern: Huber.Google Scholar
  18. Chan, W., & Bentler, P.M. (1998). Covariance structure analysis of ordinal ipsative data.Psychometrika, 63, 369–399.Google Scholar
  19. Chapman, R.G., & Staelin, R. (1982). Exploiting rank ordered choice set data within the stochastic utility model.Journal of Marketing Research, 14, 288–301.Google Scholar
  20. Critchlow, D.E., Fligner, M.A., & Verducci, J.S. (1991). Probability models on rankings.Journal of Mathematical Psychology, 35, 294–318.Google Scholar
  21. Croon, M.A. (1989). Latent class models for the analysis of rankings. In G. De Soete & K.C. Klauer (Eds.),New developments in psychological choice modeling (pp. 99–121). Amsterdam: North-Holland.Google Scholar
  22. Daniels, M.J., & Gatsonis, C. (1997). Hierarchical polytomous regression models with applications to health services research.Statistics in Medicine, 16, 2311–2325.Google Scholar
  23. De Soete, G., & Carroll, J.D. (1983). A maximum likelihood method for fitting the wandering vector model.Psychometrika, 48, 553–566.Google Scholar
  24. Durbin, J. (1951). Incomplete blocks in ranking experiments.British Journal of Psychology, 4, 85–90.Google Scholar
  25. Elrod, T. (1988). Choice map: Inferring a product-market map from panel data.Marketing Science, 7, 21–40.Google Scholar
  26. Elrod, T., & Keane, M.P. (1995). A factor analytic probit model for representing the market structure in panel data.Journal of Marketing Research, 32, 1–16.Google Scholar
  27. Farewell, V.T., & Prentice, R.L. (1980). The approximation of partial likelihood with emphasis on case-control studies.Biometrika, 67, 273–278.Google Scholar
  28. Goldstein, H. (1995).Multilevel statistical models. London: Arnold.Google Scholar
  29. Gurland, J., Lee, I., & Dolan, P. (1960). Polychotomous quantal response in biological assay.Biometrics, 16, 382–398.Google Scholar
  30. Haaijer, M.E., Wedel, M., Vriens, M., & Wansbeek, T.J. (1998). Utility covariances and context effects in conjoint MNP models.Marketing Science, 17, 236–252.Google Scholar
  31. Hajivassiliou, V., & Ruud, P. (1994). Classical estimation methods for LDV models using simulation. In R. Engle & D. McFadden (Eds.),Handbook of econometrics IV (pp. 2384–2441). Amsterdam: North-Holland.Google Scholar
  32. Harris, K.M., & Keane, M.P. (1999). A model for health plan choice: Inferring preferences and perceptions from a combination of revealed preference and attitudinal data.Journal of Econometrics, 89, 131–157.Google Scholar
  33. Hausman, J.A., & Ruud, P.A. (1987). Specifying and testing econometric models for rank-ordered data.Journal of Econometrics, 34, 83–103.Google Scholar
  34. Hausman, J.A., & Wise, D.A. (1978). A conditional probit model for qualitative choice: Discrete decisions recognizing interdependence and heterogeneous preferences.Econometrica, 46, 403–426.Google Scholar
  35. Heath, A., Curtice, J., Jowell, R., Evans, G., Fields, J., & Witherspoon, S. (1991).Understanding political change: The British voter 1964–1987. Oxford, U.K.: Pergamon.Google Scholar
  36. Heath, A., Jowell, R., & Curtice, J. (Eds.) (1994).Labour's last chance? The 1992 election and beyond. Aldershot: Dartmouth.Google Scholar
  37. Heath, A., Jowell, R, Curtice, J.K., Brand, J.A., & Mitchell, J.C. (1993).SN2983—British Election Panel Study, 1987–1992 [Computer file]. Colchester, Essex: The Data Archive [Distributor].Google Scholar
  38. Heckman, J.J., & Sedlacek, G. (1985). Heterogeneity, aggregation, and market wage functions: An empirical model of self-selection in the labor market.Journal of Political Economy, 93, 1077–1125.Google Scholar
  39. Hedeker, D. (1999). MIXNO: A computer program for mixed-effects logistic regression.Journal of Statistical Software, 4, 1–92.Google Scholar
  40. Hosmer, D.A., & Lemeshow, S.A. (1989).Applied logistic regression. London: Wiley.Google Scholar
  41. Hsiao, C. (1985). Benefits and limitations of panel data.Econometric Review, 4, 121–174.Google Scholar
  42. Johnson, N.L., Kotz, S., & Balakrishnan, N. (1995).Continuous univariate distributions, Volume 2. New York, NY: Wiley.Google Scholar
  43. Kalbfleisch, J.D., & Prentice, R.L. (1980).The statistical analysis of failure time data. New York, NY: Wiley.Google Scholar
  44. Keane, M.P. (1992). A note on identification in the multinomial probit model.Journal of Business and Economic Statistics, 10, 193–200.Google Scholar
  45. Luce, R.D. (1959).Individual choice behavior. New York, NY: Wiley.Google Scholar
  46. Luce, R.D., & Suppes, P. (1965). Preference, utility and subjective probability. In R.D. Luce, R. Bush & E. Galanter (Eds.),Handbook of mathematical psychology III (pp. 249–410). New York, NY: Wiley.Google Scholar
  47. Maddala, G.S. (1983).Limited dependent and qualitative variables in econometrics. Cambridge, MA: Cambridge University Press.Google Scholar
  48. Marchak, J. (1960). Binary choice constraints on random utility indicators. In K.J. Arrow, S. Karlin & P. Suppes (Eds.),Mathematical methods in the social sciences, 1959 (pp. 312–329). Stanford, CA: Stanford University Press.Google Scholar
  49. McFadden, D. (1973). Conditional logit analysis of qualitative choice behavior. In P. Zarembka (Ed.),Frontiers in econometrics (pp. 105–142). New York, NY: Academic Press.Google Scholar
  50. McFadden, D., & Train, K. (2000). Mixed MLN models for discrete choice.Journal of Applied Econometrics, 15, 447–470.Google Scholar
  51. Morris, C. (1983). Parametric empirical Bayes inference, theory and applications.Journal of the American Statistical Association, 78, 47–65.Google Scholar
  52. Neuhaus, J.M. (1992). Statistical methods for longitudinal and clustered designs with binary responses.Statistical Methods in Medical Research, 1, 249–273.Google Scholar
  53. Plackett, R.L. (1975). The analysis of permutations.Applied Statistics, 24, 193–202.Google Scholar
  54. Rabe-Hesketh, S., & Skrondal, A. (2001). Parameterization of multivariate random effects models for categorical data.Biometrics, 57, 1256–1264.Google Scholar
  55. Rabe-Hesketh, S., Pickles, A., & Skrondal, A. (2001).GLLAMM Manual (Tech. Rep. 2001/01). London: King's College, University of London, Institute of Psychiatry, Department of Biostatistics and Computing. Computer software and documentation can be retreived at Scholar
  56. Rabe-Hesketh, S., Skrondal, A. & Pickles, A. (2002). Reliable estimation of generalized linear mixed models using adaptive quadrature.The Stata Journal, 2, 1–21.Google Scholar
  57. Rabe-Hesketh, S., Skrondal, A. & Pickles, A. (2003).Maximum likelihood estimation of limited and discrete dependent variable models with nested random effects. Submitted for publication.Google Scholar
  58. Rabe-Hesketh, S., Pickles, A., & Skrondal, A. (in press). Correcting for covariate measurement error in logistic regression using nonparametric maximum likelihood estimation.Statistical Modelling.Google Scholar
  59. Rabe-Hesketh, S., Skrondal, A. & Pickles, A. (in press). Generalized multilevel structural equation modeling.Psychometrika.Google Scholar
  60. Raudenbush, S.W., & Bryk, A.S. (2002).Hierarchical linear models: Applications and data analysis methods. Thousand Oaks, CA: Sage.Google Scholar
  61. Revelt, D., & Train, K. (1998). Mixed logit with repeated choices: household's choices of appliance efficiency level.Review of Economics and Statistics, 80, 647–657.Google Scholar
  62. Rivers, D. (1988). Heterogeneity in models of electoral choice.American Journal of Political Science, 32, 737–757.Google Scholar
  63. Skrondal, A. & Rabe-Hesketh, S. (2004).Generalized latent variable modeling: Multilevel, longitudinal and structural equation models. Boca Raton, FL: Chapman & Hall CRC.Google Scholar
  64. Takane, Y. (1987). Analysis of covariance structures and probabilistic binary data.Communication & Cognition, 20, 45–62.Google Scholar
  65. Theil, H. (1969). A multinomial extension of the linear logit model.International Economic Review, 10, 251–259.Google Scholar
  66. Train, K. (1986).Qualitative Choice Analysis. Cambridge, MA: MIT Press.Google Scholar
  67. Yang, M. (1997). Multilevel models for multiple category responses—A simulation.Multilevel Modelling Newsletter, 9, 10–16.Google Scholar
  68. Yang, M. (2001). Multinomial regression. In A.H. Leyland & H. Goldstein (Eds.),Multilevel modelling of health statistics (pp. 107–123). Chichester, U.K.: John Wiley & Sons.Google Scholar
  69. Yao, G., & Böckenholt, U. (1999). Bayesian estimation of Thurstonian ranking models based on the Gibbs sampler.British Journal of Mathematical and Statistical Psychology, 52, 79–92.Google Scholar
  70. Yellott, J. (1977). The relationship between Luce's choice axiom, Thurstone's theory of comparative judgement, and the double exponential distribution.Journal of Mathematical Psychology, 15, 109–44.Google Scholar

Copyright information

© The Psychometric Society 2003

Authors and Affiliations

  1. 1.Department of Biostatistics and ComputingInstitute of PsychiatryLondon
  2. 2.Division of EpidemiologyNorwegian Institute of Public HealthOsloNorway

Personalised recommendations