Sankhya: The Indian Journal of Statistics
On Optimal Lag 1 Dependence Estimation for Dynamic Binary Models with Application to Asthma Data
Brajendra C. Sutradhar,
Memorial University of Newfoundland, Canada
Patrick J. Farrell Carleton University, Canada
SUMMARY. In some longitudinal studies for binary data, the expectation of the binary response variable of an individual at a given point of time may depend on the covariate history up to the present time. In the same token, the variance at a given point of time and the correlation of the two responses at two given time points may also depend on the history of the time dependent covariates of the individual. In this paper, we exploit a dynamic logistic model to analyse such history based binary data. A moment based generalized quasilikelihood (GQL) approach is considered for optimal estimation for the effects of the covariates as well as dynamic dependence. The estimation approach is applied to re-analyse a longitudinal binary data on asthma status.
AMS (2000) subject classification. Primary 62F10; secondary 62F12, 62P10.
Key words and phrases. Consistency and efficiency, lagged dependence, nonstationary correlations, regression effects, repeated binary responses.