Semiparametric Model Statistical Inference with Adjusting by Propensity Scores for Panel Count Data

Panel count data are frequently encountered in follow-up studies such as clinical trials and sociological studies. Models about this type data usually assume the underlying recurrent event process is independent with the observation process. However, the independence assumption cannot be always guaranteed in practical applications, especially when they both are relevant with the covariates. In this paper, we develop a semiparametric additive model weighted by propensity score for analyzing panel count data. By introducing propensity score into the model, the confounding bias of parameter estimate caused by the dependent observation process may be reduced. In particular, we combined the inverse probability-weighted estimation equation to estimate the parameters and further derived the asymptotic properties of the estimator. Numerical simulations were conducted to evaluate the proposed procedures. Finally, we apply the methodologies to analyzing a set of skin cancer data.