文档介绍：Analysis of Baldder Tumor Recurrence Data
with the Ternimal Event and Cure Fraction
Cuiliu Xiao and Yang Bing Xiaobing Zhao *
School of Science, Jiangnan University School of Mathematics and Statistics,
1800 Lihu Road, Wuxi, Jiangsu Province, CHINA 214122 Zhejiang University of Finance and Economics, Hangzhou,
Email:xiaoclasd@ Email: maxbzhao@
plete observation of the recurrent events may rate function and the frailty function. The frailty model has
not be available, since some subjects might drop out or fail been extensively applied to model the dependent variables,
before the endpoint of observation. However, the assumption however recently, the copula functions are prevalent to model
of independency of the recurrent events and the censoring is
not realistic in many situations. In this paper, we develop an the correlation of both bivariate and multivariate in survival
innovative model based on the Clayton-Oakes copula function to analysis, finance and actuarial studies, and among others.
fit the correlation of these variables. The joint survival function of In particular, the Clayton-Oakes copula function, which can
the recurrent event times can be obtained through the marginal be translated from a frailty model with the frailty function
hazard functions with copula parameters which measure the
degree of dependence and control the association between these given by such as a gamma distribution (cf. Glidden 2000),
variables. The cure fraction can be concluded into the proposed has been investigated and applied to analyze survival data by
model as well. An example of application on bladder tumor many authors, since it has many mathematical properties of
recurrence data is re-analyzed to assess the proposed models association and could be the mathematical tractability. The
and methodologies. existing application in survival analysis of copula model is to
I. INTRODUCTION fit the cluster data, such as He and Lawless (2003) proposed a
bivariate