Improved Exact Inference in Logistic Regression Model

Title & Authors
Improved Exact Inference in Logistic Regression Model
Kim, Donguk; Kim, Sooyeon;

Abstract
We propose modified exact inferential methods in logistic regression model. Exact conditional distribution in logistic regression model is often highly discrete, and ordinary exact inference in logistic regression is conservative, because of the discreteness of the distribution. For the exact inference in logistic regression model we utilize the modified P-value. The modified P-value can not exceed the ordinary P-value, so the test of size $\small{\alpha}$ based on the modified P-value is less conservative. The modified exact confidence interval maintains at least a fixed confidence level but tends to be much narrower. The approach inverts results of a test with a modified P-value utilizing the test statistic and table probabilities in logistic regression model.
Keywords
Confidence interval;Conservative;Coverage probability;Exact inference;Logistic regression;Modified exact P-value;2$\small{{\times}}$J$\small{{\times}}$K table;
Language
Korean
Cited by
References
1.
Biometrics, 2001. vol.57. pp.963-971

2.
Discrete Multivariate Analysis, 1975.

3.
Journal of the American Statistical Association, 1992. vol.87. pp.470-475

4.
Statistics in Medicine, 1994. vol.13. pp.2189-2203

5.
Biometrics, 1979. vol.35. pp.623-630

6.
Biometrics, 1991. vol.47. pp.487-496

7.
Journal of the American Statistical Association, 1987. vol.82. pp.1110-1117

8.
Biometrics, 1998. vol.44. pp.803-814

9.
Applied Statistics, 1994. vol.43. pp.541-548

10.
The Korean Communications in Statistics, 1998. vol.5. pp.905-926

11.
Journal of the American Statistical Association, 1995. vol.90. pp.632-639

12.
Journal of the American Statistical Association, 1961. vol.56. pp.223-234

13.
Statistics in Medicine, 1995. vol.14. pp.2143-2160