An alternative method for logistic regression on contingency tables with zero cell counts
This paper introduces an alternative method for solving a problem of non-convergence in logistic regression. The method does not require any special software to be developed. It simply involves modifying the data by replacing the zero count by 1 and doubling a corresponding non-zero count. The met...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Prince of Songkla University
2016-04-01
|
| Series: | Songklanakarin Journal of Science and Technology (SJST) |
| Subjects: | |
| Online Access: | http://rdo.psu.ac.th/sjstweb/journal/38-2/38-2-8.pdf |
| Summary: | This paper introduces an alternative method for solving a problem of non-convergence in logistic regression. The
method does not require any special software to be developed. It simply involves modifying the data by replacing the zero
count by 1 and doubling a corresponding non-zero count. The method is compared with that based on penalized likelihood
suggested by Firth. Results show that the data modification method provides statistical significance of associations similar to
Firth’s method while using standard logistic regression output. |
|---|---|
| ISSN: | 0125-3395 |