講座嘉賓：劉妍巖 教授

講座日期：2019-12-24

講座時(shí)間：15:00

報(bào)告地點(diǎn)：長安校區(qū) 數(shù)學(xué)與信息科學(xué)學(xué)院學(xué)術(shù)交流廳

主辦單位：數(shù)學(xué)與信息科學(xué)學(xué)院

講座人簡介：

劉妍巖，武漢大學(xué)數(shù)學(xué)與統(tǒng)計(jì)學(xué)院教授，博士生導(dǎo)師。2001年獲武漢大學(xué)理學(xué)博士學(xué)位。主要研究方向?yàn)樯娣治?、半?yún)?shù)統(tǒng)計(jì)推斷、高維數(shù)據(jù)統(tǒng)計(jì)分析等。主持完成國家自然科學(xué)基金以及教育部基金項(xiàng)目6項(xiàng)，正在主持國家自然科學(xué)基金面上項(xiàng)目一項(xiàng)，參加完成的成果“風(fēng)險(xiǎn)模型中的統(tǒng)計(jì)方法及相關(guān)理論與應(yīng)用” 獲2013年湖北省自然科學(xué)獎(jiǎng)三等獎(jiǎng)（排名第一）。在Journal of Machine Learning Research, Biometrics, Biostatistics, Genetics，Lifetime Data Analysis等期刊發(fā)表SCI研究論文五十余篇。目前擔(dān)任中國現(xiàn)場統(tǒng)計(jì)學(xué)會(huì)第十屆理事會(huì)常務(wù)理事、中國教育統(tǒng)計(jì)協(xié)會(huì)常務(wù)理事、中國工業(yè)統(tǒng)計(jì)學(xué)會(huì)常務(wù)理事、中國數(shù)學(xué)會(huì)女?dāng)?shù)學(xué)家及西部數(shù)學(xué)發(fā)展工作委員會(huì)委員。

講座簡介：

Regularization methods for the Cox proportional hazards regression with high-dimensional survival data have been studied extensively in the literature. However, if the models are misspecified, this would result in misleading statistical inference and prediction. To enhance the prediction accuracy for the relative risk and the survival probability of clinical interest, we propose three model averaging approaches for the high-dimensional Cox proportional  hazards regression. Based on the martingale residual process, we define the delete-one crossvalidation process. Further, we propose three novel cross-validation functionals, including the end-time cross-validation, integrated cross-validation, and supremum cross-validation, to achieve more accurate prediction for the risk quantities. The optimal weights for candidate models, without the constraint of summing up to one, can be obtained by minimizing these functionals, respectively. The proposed model averaging approaches can attain the lowest possible prediction loss asymptotically. Furthermore, we develop a greedy model averaging algorithm to overcome the computational obstacle when the dimension is high. The performance of the proposed model averaging procedures is evaluated via extensive simulation studies, showing that our methods have superior prediction accuracy over the existing regularization methods. As an illustration, we apply the proposed methods to the mantle cell lymphoma study.