, Volume 21, Issue 1, pp 1–17 | Cite as

Statistical Choices in Infant Temperament Research

  • Hal Stern
  • Doreen Arcus
  • Jerome Kagan
  • Donald B. Rubin
  • Nancy Snidman
Invited Paper


Temperamental characteristics can be conceptualized as either continuous dimensions or qualitative categories. The distinction concerns the underlying temperamental characteristics rather than the measured variables, which can usually be recorded as either continuous or categorical variables. A finite mixture model captures the categorical view, and we apply such a model here to two sets of longitudinal observations of infants and young children. A measure of predictive efficacy is described for comparing the mixture model with competing models, principally a linear regression analysis. The mixture model performs mildly better than the linear regression model with respect to this measure of fit to the data; however, the primary advantage of the mixture model relative to competing approaches, is that, because it matches our a priori theory, it can be easily used to address improvements and corrections to the theory, and to suggest extensions of the research.

Key Words and Phrases

finite-mixture model latent class model EM algorithm average information measure 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Arcus, D.M. (1991) The experiential modification of temperamental bias in inhibited and uninhibited children. Unpublished doctoral dissertation, Harvard University.Google Scholar
  2. Attneave, F. (1959) Applications of Information Theory to Psychology, New York: Holt.Google Scholar
  3. Clogg, C.C (1981a). Latent class analysis across groups. Proceedings of the Social Statistics Section, 1981 Annual Meeting of the American Statistical Association, 299–304, Alexandria: American Statistical Association.Google Scholar
  4. Clogg, C.C. (1981b). Latent structure model of mobility. American Journal of Sociology, 86, 838–868.CrossRefGoogle Scholar
  5. Dempster, A.P., Laird, N.M., and Rubin, D.B. (1977) Maximum likelihood estimation from incomplete data via the EM algorithm, (with discussion) Journal of the Royal Statistical Society B, 39, 1–38.MathSciNetzbMATHGoogle Scholar
  6. Dunn, L.T. and Everitt, B.J. (1988) Double dissociations of the effects of amygdala and insular cortex lesions on condition taste aversion, passive avoidance and neophobia in the the rat using the excitotoxin ibotenic acid. Behavioral Neuroscience, 102, 3–9.CrossRefGoogle Scholar
  7. Everitt, B.S. and Hand, D.J. (1981) Finite Mixture Distributions. London: Chapman and Hall.CrossRefGoogle Scholar
  8. Gelman, A., Meng, X.L., and Stern, H.S. (1993) Bayesian model invalidation using tail area probabilities. Technical Report, Department of Statistics, Harvard University (submitted to Journal of the Royal Statistical Society B).Google Scholar
  9. Goodman, L.A. (1974a). Exploratory latent structure analysis using both identifiable and unidentifiable models. Biometrika, 61, 215–231.MathSciNetCrossRefGoogle Scholar
  10. Goodman, L.A. (1974b). The analysis of a system of qualitative variables when some of the variables are unobservable. Part I: A modified latent structure approach. American Journal of Sociology, 79, 1179–1259.CrossRefGoogle Scholar
  11. Haberman, S.J. (1979) Analysis of Qualitative Data, Vol. 2, Chapter 10. New York: Academic Press.Google Scholar
  12. Haberman, S J. (1988) A stabilized Newton-Raphson algorithm for log-linear models for frequency tables derived by indirect observation. Sociological Methodology, 18, 193–211.CrossRefGoogle Scholar
  13. Hinde, R.A. and Dennis, A. (1986) Categorizing individuals. International Journal of Behavioral Development, 9, 105–119.CrossRefGoogle Scholar
  14. Kagan, J. (1989) Temperamental contributions to social behavior. American Psychologist, 44, 668–674.CrossRefGoogle Scholar
  15. Kagan, J. and Snidman, N. (1991a). Temperamental factors in human development. American Psychologist, 46, 856–862.CrossRefGoogle Scholar
  16. Kagan, J. and Snidman, N. (1991b). Infant predictors of inhibited and uninhibited profiles. Psychological Science, 2, 40–44.CrossRefGoogle Scholar
  17. Kelley, A.E., Domesick, V.B. and Nauta, WJ.H. (1982) The amygdalostriatal projection in the rat: an anatomical study by antrograde and retrograde tracing techniques. Neuroscience, 7, 615–630.CrossRefGoogle Scholar
  18. Lazarsfeld, P.F. and Henry, N.W. (1968) Latent Structure Analysis. Boston: Houghton Mifflin.zbMATHGoogle Scholar
  19. Magnusson, D. and Allen, V J. (1983) Human Developmemnt: An Interactional Perspective. New York: Academic Press.Google Scholar
  20. McCutcheon, A.L. (1987) Latent Class Analysts. Beverly Hills: Sage Publications.CrossRefGoogle Scholar
  21. Meethl, P.E. (1989) Schizotaxia revisited. Archives of General Schizophrenia, 46, 935–944.CrossRefGoogle Scholar
  22. Meng, X.L. and Rubin, D.B. (1991) Using EM to obtain asymptotic variance-covariance matrices: the SEM algorithm. Journal of the American Statistical Association, 86, 899–909.CrossRefGoogle Scholar
  23. Mishkin, M. and Aggleton, J. (1981) Multiple functional contributions of the amygdala in the monkey. In Y. Ben-Ari (ed), The Amygdala Complex, 409–420. Amsterdam: North Holland Press.Google Scholar
  24. Rubin, D.B. (1984) Bayesianly justifiable and relevant frequency calculations for the applied statistician. The Annals of Statistics, 12, 1151–1172.MathSciNetCrossRefGoogle Scholar
  25. Rubin, D.B. and Stern, H.S. (1992) Testing in latent class models using a posterior predictive check distribution. To appear in C. Clogg and A. von Eye (eds.), Analysis of Latent Variables in Developmental Research.Google Scholar
  26. Stern, H., Arcus, D., Kagan, J., Rubin, D.B. and Snidman, N. (1993) Using mixture models in temperament research. To appear in International Journal of Behavioral Development.Google Scholar
  27. Titterington, D.M., Smith, A.F.M., and Makov, U.E. (1985) Statistical Analysis of Finite Mixture Distributions. New York: John Wiley.zbMATHGoogle Scholar

Copyright information

© The Behaviormetric Society 1994

Authors and Affiliations

  • Hal Stern
    • 1
  • Doreen Arcus
    • 2
  • Jerome Kagan
    • 2
  • Donald B. Rubin
    • 1
  • Nancy Snidman
    • 2
  1. 1.The Department of StatisticsHarvard UniversityCambridgeUSA
  2. 2.The Department of PsychologyHarvard UniversityCambridgeUSA

Personalised recommendations