Generalized quasilikelihood method for misclassified longitudinal binary data
Thesis (M.A.S.)--Memorial University of Newfoundland, 2010. Mathematics and Statistics Bibliography: leaves 68-70. In this practicum we develop the generalized quasi-likelihood approach to analyzing longitudinal binary data with misclassification in response. We utilize the method of Monahan and Ste...
Main Author: | |
---|---|
Other Authors: | |
Format: | Thesis |
Language: | English |
Published: |
2010
|
Subjects: | |
Online Access: | http://collections.mun.ca/cdm/ref/collection/theses5/id/10761 |
Summary: | Thesis (M.A.S.)--Memorial University of Newfoundland, 2010. Mathematics and Statistics Bibliography: leaves 68-70. In this practicum we develop the generalized quasi-likelihood approach to analyzing longitudinal binary data with misclassification in response. We utilize the method of Monahan and Stefanski (1992) to approximate the expectation of an unknown function involved in the calculation of the means and covariances, which are further used to develop GQL estimating functions. The results of an intensive simulation study show that the proposed method works very well in all the preselected settings. The efficiency gain as compared to the naive method is remarkable. The method is robust in the sense that the performance varies just slightly when model parameters change in the simulation. -- Keywords: Logit link; longitudinal binary response; GQL; Misclassification. |
---|