UNOBSERVABLE HETEROGENEITY IN WEIBULL AND POISSON REGRESSION MODELS; AN APPLICATION TO TIlE STUDY OF INFANT MORTALITY IN NORTH CAROLINA

نویسندگان

  • John Robert Feaganes
  • JOHN ROBERT FEAGANES
چکیده

In many situations individuals with the same values for all observed covariables will have important covariables which cannot be measured or which were not measured during the study. These unknown or unmeasured covariables make the subpopulations, as defined by the observable covariables, heterogeneous. The present study explores the affect of unobservable heterogeneity in the context of Weibull regression and Poisson regression. -By incorporating frailty into these two models an explicit test for unobservable heterogeneity is developed. These two models are also used as a basis for quantifying the effect of unobservable heterogeneity on the estimates of the regression parameters. The frailty Poisson regr~ion model and frailty Weibull regression model are used to investigate the determinants of infant mortality in North Carolina between 1985 and 1987. The frailty Poisson regression model is used to study the infant mortality rate for each county, and the frailty Weibull regression model is used to study the individual time to death. At the county level the more urbanization and less poverty there is in a county, the lower the total infant mortality rate. A county's total infant mortality rate increases with greater nonwhite proportion of the population and greater proportion of poor eligible for financial aid. Also, the total infant mortality rate increases as the level of available health services decreases and the level of unemployment increases. At the individual level infant mortality is higher for women who are young, uneducated, unmarried, with numerous previous live births, experience complications during pregnancy or during labor, and do not receive appropriate and timely prenatal care. Characteristics of the infant which are indicators of high risk are male gender and low birthweight. Race appears to be an indicator of high risk when looking at crude infant mortality rates; however, after controlling for all other indicators of high risk the effect of race is statistically insignificant.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Determining the correlated factors of breast cancer recurrence by Poisson Beta-Weibull non- mixture cure model

Introduction: Therapies for many of diseases, especially cancer, have been improved significantly in the recent years, resulting in an increase in the number of patients who do not experience mortality. Therefore, the application of cure models is more suitable for survival analysis in this population than the usual survival models are. The aim of this study was to estimate the recurrence-free ...

متن کامل

تحلیل بقای بیماران مبتلا به سرطان پستان با استفاده از مدل‌های شفایافته نا آمیخته وایبل و بتا وایبل پواسون

Background and Aim: Therapies for many of diseases especially cancers have been improved significantly in the recent year, so there have been an increased number of patients who do not experience mortality. In analysis of these disease, cured models is used instead of usual survival models. Weibull model and its generalized version beta Weibull Poisson (BWP), are flexible models in cure models ...

متن کامل

A New Lifetime Distribution: The Beta Modified Weibull Power Series Distribution

In this paper, we propose a new parametric distribution which called as the Beta Modified Weibull Power Series (BMWPS) distribution. This distribution is obtained by compounding Beta Modified Weibull (BMW) and power series distributions. BMWPS distribution contains, as special sub-models, such as Beta Modified Weibull Poisson (BMWP) distribution, Beta Modified Weibull Geometric (BMWG) distribut...

متن کامل

Modeling Heterogeneity in Bivariate Survival Data by Compound Poisson Distribution using Bayesian Approach

Shared frailty models are often used to model heterogeneity in survival analysis. There are certain assumptions about the baseline distribution and distribution of frailty. In this paper, we consider compound Poisson distribution as frailty distribution and three different baseline distributions namely, Weibull, generalized exponential and exponential power distribution. With these three baseli...

متن کامل

Parameter Estimation of Geographically Weighted Trivariate Weibull Regression Model

In this study, Geographically Weighted Trivariate Weibull Regression (GWTWR) model and parameter estimation procedure are proposed. GWTWR is trivariate Weibull regression model which all of the regression parameters depend on the geographical location, and parameter estimation is done locally at each location in the study area. The location is expressed as a point coordinate in two-dimensional ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1993