Abstract
The impact of sparse data conditions was examined among one or more predictor variables in logistic regression and assessed the effectiveness of the Firth (1993) procedure in reducing potential parameter estimation bias. Results indicated sparseness in binary predictors introduces bias that is substantial with small sample sizes, and the Firth procedure can effectively correct this bias.
DOI
10.22237/jmasm/1604190660
Recommended Citation
Walker, D. A., & Smith, T. J. (2019). Logistic regression under sparse data conditions. Journal of Modern Applied Statistical Methods, 18(2), eP3372. doi: 10.22237/jmasm/1604190660
Included in
Applied Statistics Commons, Social and Behavioral Sciences Commons, Statistical Theory Commons
