Comparing Regression Coefficients Between Models using Logit and Probit: A New Method
This seminar has been organised by the local Edinburgh network and is free for all members to attend. Places are limited, sign up using the link below if you would like to attend.
Richard Breen, William Graham Sumner Professor of Sociology, Yale University and Co-Director of the Centre for Research on Inequalities and the Life Course (CIQLE)
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 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. We also demonstrate that other methods for comparing coefficients across models, average partial effects, y-standardization, and the linear probability model, are not suitable for this purpose in a range of situations met in real applications. We present an example of our method using data from the National Educational Longitudinal Survey.
Venue:
Seminar Room 2, Chrystal Macmillan Building,
George Square, University of Edinburgh
