Showing papers by "Pranab Kumar Sen published in 1995"

One-sided tests in generalized linear models with parallel regression lines

Abstract: Likelihood ratio tests for two general one-sided hypotheses in generalized linear models with parallel regression lines are discussed in this paper. This kind of model may be interpreted as a generalization of the Finney's (1971, Probit Analysis. Cambridge: Cambridge University Press) model for simple similar action between two or more compounds. In particular, for some balanced studies, it is shown that the asymptotic null distributions do not depend on the parameters and have the same size for a class of ordered hypotheses for the potencies. The conventional distribution theory of the likelihood ratio test does not hold in these cases. For the practical situations of simple order and simple tree order, the asymptotic null distributions reduce to the -2 distribution. A power study is also conducted in order to compare the likelihood ratio tests against ordered and different potencies. Finally, we present an illustrative example where the direction of the antagonism between two insecticides is investigated by comparing the relative potencies of their mixtures.

The Hájek asymptotics for finite population sampling and their ramifications

Abstract: In finite population (equal as well as unequal probability) sampling late Jaroslav Hajek's contributions to the general asymptotics are fundamental. In the last two decades more research work has been accomplished in this area with the basic ideas germinating from Hajek's work. A systematic review of such developments with due emphasis on some martingale formulations is presented here.

Statistics and quality of life: Third world perspectives

Abstract: SUMMARY The socio-economics, standard of living (in the poverty/affluence differential) reflects the quality of life, while in health care and management, physical, socio-environmental, psychological and mental health perspectives dominate the scenario. Chronic diseases, autism and other developmental disabilities, congenital anomalies, occupational hazards related disabilities, prevalence of AIDS, cancer, arthritis, disorders requirin~ organ transplants and major surgeries, and many other incurable diseases/disorders have profound impact on quality of life not only for individuals affected but also of a society/community/country where they live. Although, quality of life standards and preserving measures vary from industrialized countries to the third world ones, they all are confronted with the basic challenging task: Subject to prevailing natural resources, socioeconomic setups and technological advances, how to maintain (and improve) the quality of life? Statistical perspectives in this complex task are critically appraised with due emphasis on quality gap ratio and quality of life deficiency concepts.

Generalized linear models in biomedical statistical applications

Abstract: SUMMARY In biological assays, clinical trials, life-testing problems, reliability and survival analysis, and a variety of applied fields ranging from agrometry to biodivrersity to zodiacal sciences, generalized linear models covering usual linear, transformed linear, log-linear and nonlinear regression models, multi-nomial and logistic regression models, as well as some semiparametric ones, are potentially adoptable for drawing statistical conclusions from acquired data sets. Yet there may be some hidden barriers, originating from experimental as well as observational schemes, that merit careful examination in applications. Merits and demerits of generalized linear models in biomedical applications with due emphasis on their validity and robustness properties are thoroughly discussed.. .