![[PDF]](/pb-assets/Icons/adobe-pdf-icon-1498649896243.png){kind=icon}
Abstract
Logit and probit models are widely used in empirical sociological research. However, the common practice of comparing the coefficients of a given variable across differently specified models fitted to the same sample does not warrant the same interpretation in logits and probits as in linear regression. Unlike linear models, the change in the coefficient of the variable of interest cannot be straightforwardly attributed to the inclusion of confounding variables. The reason for this is that the variance of the underlying latent variable is not identified and will differ between models. We refer to this as the problem of rescaling. We propose a solution that allows researchers to assess the influence of confounding relative to the influence of rescaling, and we develop a test to assess the statistical significance of confounding. A further problem in making comparisons is that, in most cases, the error distribution, and not just its variance, will differ across models. Monte Carlo analyses indicate that other methods that have been proposed for dealing with the rescaling problem can lead to mistaken inferences if the error distributions are very different. In contrast, in all scenarios studied, our approach performs as least as well as, and in some cases better than, others when faced with differences in the error distributions. We present an example of our method using data from the National Education Longitudinal Study.
References
|
Agresti, Alan . 2002. Categorical Data Analysis. 2nd ed. New Jersey: Wiley. Google Scholar | Crossref | |
|
Allison, Paul D. 1999. “Comparing Logit and Probit Coefficients Across Groups.” Sociological Methods and Research 28(3):186–208. Google Scholar | SAGE Journals | ISI | |
|
Amemiya, Takeshi 1975. “Qualitative Response Models.” Annals of Economic and Social Measurement 4:363–88. Google Scholar | |
|
Bartus, Tamás . 2005. “Estimation of Marginal Effects Using margeff.” Stata Journal 5(3):309–29. Google Scholar | |
|
Blalock, Hubert M. 1979. Social Statistics. 2nd ed. New York: McGraw-Hill. Google Scholar | |
|
Clogg, Clifford C., Petkova, Eva, Haritou, Adamantios. 1995. “Statistical Methods for Comparing Regression Coefficients between Models.” American Journal of Sociology 100(5):1261–93. Google Scholar | Crossref | ISI | |
|
Cramer, J. S. 2003. Logit Models. From Economics and Other Fields. Cambridge, England: Cambridge University Press. Google Scholar | Crossref | |
|
Cramer, J. S. 2007. “Robustness of Logit Analysis: Unobserved Heterogeneity and Mis-specified Disturbances.” Oxford Bulletin of Economics and Statistics 69(4):545–55. Google Scholar | Crossref | ISI | |
|
Curtin, Thomas R., Ingels, Steven J., Wu, Shiying, Heuer, Ruth. 2002. User’s Manual. National Education Longitudinal Study of 1988: Base-Year to Fourth Follow-up Data File User’s Manual (NCES 2002–323). Washington, DC: U.S. Department of Education, National Center for Education Statistics. Google Scholar | |
|
Goldberger, Arthur S. 1991. A Course in Econometrics. Cambridge, MA: Chapman and Hall. Google Scholar | |
|
Hoetker, Glenn . 2004. “Confounded Coefficients: Accurately Comparing Logit and Probit Coefficients across Groups.” Working paper 03-0100. College of Business Working Papers, University of Illinois at Urbana-Champaign. Google Scholar | |
|
Hoetker, Glenn 2007. “The Use of Logit and Probit Models in Strategic Management Research: Critical Issues.” Strategic Management Journal 28(4):331–43. Google Scholar | Crossref | ISI | |
|
Kendall, Patricia, Lazarsfeld, Paul L. 1950. “Problems of Survey Analysis.” Pp. 133–96 in Continuities in Social Research, edited by Merton, Robert K., Lazarsfeld, Paul L. Glencoe, IL: Free Press. Google Scholar | |
|
Lazarsfeld, Paul L. 1955. “The Interpretation of Statistical Relations as a Research Operation.” Pp. 115–25 in The Language of Social Research, edited by Lazarsfeld, Paul L., Rosenberg, Morris. Glencoe, IL: Free Press. Google Scholar | |
|
Lazarsfeld, Paul L. 1958. “Evidence and Inference in Social Research.” Daedalus 87(4):99–130. Google Scholar | ISI | |
|
Long, J. Scott 1997. Regression Models for Categorical and Limited Dependent Variables. Thousand Oaks, CA: Sage. Google Scholar | |
|
Long, J. Scott, Freese, Jeremy. 2005. Regression Models for Categorical Dependent Variables Using Stata. 2nd ed. College Station, TX: Stata Press. Google Scholar | |
|
Maddala, G. S. 1983. Limited-dependent Variables and Qualitative Variables in Economics. New York: Cambridge University Press. Google Scholar | Crossref | |
|
McKelvey, Richard D., Zavoina, William. 1975. “A Statistical Model for the Analysis of Ordinal Level Dependent Variables.” Journal of Mathematical Sociology 4(1):103–20. Google Scholar | Crossref | ISI | |
|
Mood, Carina . 2010. “Logistic Regression: Why We Cannot Do What We Think We Can Do, and What We Can Do about It.” European Sociological Review 26(1):67–82. Google Scholar | Crossref | ISI | |
|
Powers, Daniel A., Xie, Yu. 2000. Statistical Methods for Categorical Data Analysis. San Diego, CA: Academic Press. Google Scholar | |
|
Simon, Herbert A. 1954. “Spurious Correlation: A Causal Interpretation.” Journal of the American Statistical Association 49(267):467–79. Google Scholar | ISI | |
|
Sobel, Michael E. 1982. “Asymptotic Confidence Intervals for Indirect Effects in Structural Equation Models.” Pp. 290–312 in Sociological Methodology, vol. 13, edited by Leinhardt, Samuel . San Francisco: Jossey-Bass. Google Scholar | Crossref | |
|
Sobel, Michael E. 1987. “Direct and Indirect Effects in Linear Structural Equation Models.” Sociological Methods and Research 16(1):155–76. Google Scholar | SAGE Journals | ISI | |
|
Turner, Robert W., Rockel, Mark L. 1988. “Estimating Covariances of Parameter Estimates from Different Models.” Economics Letters 26(2): 137–40. Google Scholar | Crossref | ISI | |
|
White, Halbert . 1982. “Maximum Likelihood Estimation of Misspecified Models.” Econometrica 50(1):1–25. Google Scholar | Crossref | ISI | |
|
Williams, Richard . 2009. “Using Heterogeneous Choice Models to Compare Logit and Probit Coefficients across Groups.” Sociological Methods and Research 37(4):531–59. Google Scholar | SAGE Journals | ISI | |
|
Winship, Christopher, Mare, Robert D. 1984. “Regression Models with Ordinal Variables.” American Sociological Review 49(4):512–25. Google Scholar | Crossref | ISI | |
|
Wooldridge, Jeffrey M. 2002. Econometric Analysis of Cross Section and Panel Data. Cambridge, MA: MIT Press. Google Scholar | |
|
Yatchew, Adonis, Griliches, Zvi. 1985. “Specification Error in Probit Models.” Review of Economics and Statistics 67(1):134–39. Google Scholar | Crossref | ISI |
