Maximum likelihood regression methods for paired binary data

Statistics in Medicine - Tập 9 Số 12 - Trang 1517-1525 - 1990
S. Lipsitz1, Nan M. Laird, David P. Harrington
1Department of Biostatistics , Harvard School of Public Health , Boston , MA , 02115

Tóm tắt

AbstractWe discuss maximum likelihood methods for analysing binary responses measured at two times, such as in a cross‐over design. We construct a 2 × 2 table for each individual with cell probabilities corresponding to the cross‐classification of the responses at the two times; the underlying likelihood for each individual is multinomial with four cells. The three dimensional parameter space of the multinomial distribution is completely specified by the two marginal probabilities of success of the 2 × 2 table and an association parameter between the binary responses at the two times. We examine a logistic model for the marginal probabilities of the 2 × 2 table for individual i; the association parameters we consider are either the correlation coefficient, the odds ratio or the relative risk. Simulations show that the parameter estimates for the logistic regression model for the marginal probabilities are not very sensitive to the parameters used to describe the association between the binary responses at the two times. Thus, we suggest choosing the measure of association for ease of interpretation.

Từ khóa


Tài liệu tham khảo

10.1093/biomet/73.1.13

10.2307/2531733

10.2307/2529309

Bahadur R. R., 1961, Studies in Item Analysis and Prediction, 158

10.2307/2529950

Bishop Y. M. M., 1975, Discrete Multivariate Analysis: Theory and Practice

10.1016/0002-9343(86)90539-5

10.1093/biomet/54.1-2.235

10.1007/978-1-4899-3244-0

10.1093/biomet/63.3.581

10.1093/biomet/49.1-2.205

Thông tin
Thông tin xuất bản

Statistics in Medicine

Tập 9 Số 12

1517-1525

Thông tin tác giả