Abstract
This paper introduces and applies an EM algorithm for the maximum-likelihood estimation of a latent class version of the grouped-data regression model. This new model is applied to examine the effects of college athletic participation of females on incomes. No evidence for an “athlete” effect in the case of females has been found in the previous work by Long and Caudill [12], Henderson et al. [10], and Caudill and Long [5]. Our study is the first to find evidence of a lower wage for female athletes. This effect is present in a regime characterizing 42% of the sample. Further analysis indicates that female athletes in many otherwise low-paying jobs actually get paid less than non-athletes.
Acknowledgements
The authors are grateful to two anonymous referees of this journal for helpful comments on an earlier version.
Notes
For an introduction to partially adaptive estimators, see Citation9 Citation14 Citation18 Citation27.
For an application of the EM algorithm to a latent class stochastic frontier model, see Caudill Citation4.
A similar result was found by using an OLS in interval mid-points regression. The coefficient of Athlete was −67.263 and was not significantly different from zero.
Sarstedt Citation23 conducted a Monte Carlo comparison of several information-theoretic measures for testing for the presence of a mixture. These measures include: the AIC of Akaike Citation1, the CAIC of Bozdogan Citation3, the BIC of Schwarz Citation24, and the ABIC of Rissanen Citation21 and Sclove Citation25. We use all four statistics to evaluate our results.
We are grateful to an anonymous referee for this suggestion. The complete set of estimation results is available upon request.
We are grateful to an anonymous referee for this suggestion. The complete set of estimation results is available upon request.