Asymmetric kernel and positive wavelet smoothing for size-biased data

点击翻译按钮获取中文摘要

I have developed through previous research grants some appropriate smoothing methods dealing with survival data. These methods have been useful for estimating the survival probability beyond the largest observation in the sample as well as other important characteristics of the population such as the expected life time conditional on a given age. Traditional methods such as the kernel methods require additional corrective measures to ward of the boundary bias that is avoided in the new smoothing techniques. The basic objective of the present proposal is to investigate extensions and modifications of such techniques to non-standard data such as weighted data, censored data and dependent data. These extensions are useful in practical settings of many applied fields such as reliability and engineering, clinical studies as well as agricultural studies.