Smooth estimation of uniformly stochastically ordered surviaval functions
Publish place: 08th Iranian Statistics Conference
Publish Year: 1385
نوع سند: مقاله کنفرانسی
زبان: English
View: 1,341
This Paper With 11 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
ISC08_008
تاریخ نمایه سازی: 26 دی 1388
Abstract:
Let S and T denote two survival functions, such that the function θ(x) = S(x)/T(x) is non -T. This concept is useful in reliability and life testing as it is equivalent to to the hazard ordering. Rojo and Samaniego (1991, 1993) study consistent estimation of S under uniform stochastic ordering where as Mukerjee (1996) considered the general problem of estimating S and T along the lines considered in Rojo and Samaniego (1991). The delicate matter of the asymptotic distribution of estimators in question has been recently tackled by Arcones and Samaniego (2000). When the underlying survival functions are assumed obsolutely continuous, here is naturally an interest in finding smooth estimators, which are not available through the above estimators. Their smooth version through the popular smoothing methods do not guarantee the stochastic ordering property in the resulting estimators. In this paper we consider an adaptation of the smoothing technique introduced in Chaubey and Sen (1996) and show that the smooth estimator kind of dove tails the non-smooth estimator and as such the strong and weak convergence properties of the previous estimators are maintained.
Authors
Yogendra P. Chaubey (Invited)
Concordia University, Montreal, Canada and Portland State Universtiy, Portland, USA
Subhash C.Kochar
Concordia University, Montreal, Canada and Portland State Universtiy, Portland, USA