講座題目:  Semiparametric transformation models for semicompeting survival data

主講人: 西南財經(jīng)大學(xué)統(tǒng)計學(xué)院統(tǒng)計研究中心主任  林華珍教授

主講人簡介:

林華珍，華西醫(yī)科大學(xué)衛(wèi)生統(tǒng)計專業(yè)博士，美國華盛頓大學(xué)生物統(tǒng)計系博士后，西南財經(jīng)大學(xué)統(tǒng)計學(xué)院教授。先后作為副研究員、訪問教授或訪問學(xué)者在美國UCLA、美國University of Washington、加拿大University of Waterloo、英國University of Manchester、香港中文大學(xué)、香港大學(xué)、香港科技大學(xué)及香港浸會大學(xué)學(xué)習(xí)和工作。

林教授2011年獲國家杰出青年科學(xué)基金資助，2010入選教育部新世紀(jì)優(yōu)秀人才支持計劃。從事統(tǒng)計學(xué)研究，論文發(fā)表在包括《The Annals of Statistics》、《Journal of the Royal Statistical Society Series B》、《Biometrika》及《Biometrics》國際統(tǒng)計學(xué)排位前5的學(xué)術(shù)刊物上。

時間：2014年5月21日下午15:00點 

地點：kaiyun開云官方網(wǎng)站犀浦校區(qū)kaiyun開云官方網(wǎng)站會議室X2511 

內(nèi)容簡介:

Semicompeting risk outcome data, e.g. time to disease progression and time to death,  are commonly collected in clinical trials. However,  analysis of these data is often hampered by a scarcity of  available statistical tools. As such, we propose a novel semiparametric transformation model that improves the existing models in the following ways. First, it estimates   regression coefficients and association parameters simultaneously. Second, the measure of surrogacy, for example, the proportion of the treatment effect that is mediated by the surrogate and the ratio of the overall treatment effect on the true end point over that on the surrogate end point, can  be directly obtained. We propose  a two-stage estimation procedure for inference and show that the  proposed estimator is  consistent and asymptotically normal. Extensive simulations demonstrate the valid usage of  our method.  We apply the method to a multiple myeloma trial to study the impact of several biomarkers on patients' semicompeting outcomes, namely, time to progression and time to death.