講座名稱：Modelling Spatially Correlated Binary Data

講座時(shí)間：2019-08-19 16:00:00

講座地點(diǎn)：南校區(qū)信遠(yuǎn)樓二區(qū)205室

講座人：潘建新 教授

講座人介紹：

潘建新教授，英國曼徹斯特大學(xué)(University of Manchester)數(shù)學(xué)學(xué)院終身教授，英國皇家統(tǒng)計(jì)學(xué)會(huì)(The Royal Statistical Society) 會(huì)士（Fellow）, 國際統(tǒng)計(jì)學(xué)會(huì)（International Statistical Institute）當(dāng)選會(huì)員（elected member）和美國數(shù)理統(tǒng)計(jì)學(xué)會(huì)（Institute of Mathematical Statistics）會(huì)員。統(tǒng)計(jì)學(xué)雜志Biometrics（2008-2018）， Journal of Multivariate Analysis (2018-)和Biometrical Journal (2016-)編委（Associated Editor）。1996年在香港浸會(huì)大學(xué)獲得統(tǒng)計(jì)學(xué)博士學(xué)位，之后到英國洛桑(Rothamsted)實(shí)驗(yàn)中心從事博士后研究。2002年10月加盟曼徹斯特大學(xué)數(shù)學(xué)學(xué)院，先后仼講師(2002)、高級(jí)講師(2004)、Reader(2005)。2006年被曼徹斯特大學(xué)聘為終身教授，并兼任曼徹斯特大學(xué)醫(yī)學(xué)院研究員。曾擔(dān)任曼大數(shù)學(xué)學(xué)院概率統(tǒng)計(jì)系系主任。致力于統(tǒng)計(jì)學(xué)領(lǐng)域內(nèi)復(fù)雜數(shù)據(jù)模型的理論研究及其在醫(yī)學(xué)、金融及工業(yè)上的應(yīng)用，取得了多項(xiàng)創(chuàng)新性研究成果。成果發(fā)表在包括Journal of the American Statistical Association和Biometrika在內(nèi)的統(tǒng)計(jì)學(xué)主流期刊上。至今已發(fā)表學(xué)術(shù)論文100余篇，出版學(xué)術(shù)專著2部(Growth Curve Models and Statistical Diagnostics和Case-Deletion Diagnostics in Linear Mixed Models)，其中1部于2002年由Springer出版社出版。已指導(dǎo)18名博士研究生并獲得學(xué)位。

講座內(nèi)容：

Generalized estimating equations lead to consistent estimators of the mean parameters for spatially correlated binary data, but the estimation of covariance matrix is also of interest in spatial data analysis. In this talk, a specific parametric form is proposed to model the correlation matrix for spatially correlated binary data. An iterative approach based on generalized estimating equations is developed to estimate the mean and correlation parameters simultaneously. Asymptotic normality for the estimators of the mean and correlation parameters is provided. Simulation studies are conducted through considering various model parameters such as different working correlation matrices, correlation parameters and dimensions of the mean parameters. The proposed approach is used to analyze the spatial bovine tuberculosis infection data in Ireland, aiming to quantify the influence of some important factors on the infection for both badgers and cattle, as well as the correlation between their setts and herds.

主辦單位：數(shù)學(xué)與統(tǒng)計(jì)學(xué)院