講座題目： Semi-parametric Estimation Based on Orthogonality

   for Semi-varying Coefficient Models with Heteroscedastic Errors

報(bào)告人：林金官，教授，東南大學(xué)

主持人：鄭海濤

時(shí)間： 6月24號(hào)，周二，下午：3:00pm-4:00pm；

地點(diǎn)： 犀浦校區(qū)二號(hào)樓kaiyun開(kāi)云官方網(wǎng)站 X2511

內(nèi)容簡(jiǎn)介：This paper is concerned with the estimation in semi-varying coefficient models with heteroscedastic errors. Based on orthogonality, we propose an iterated two-stage estimation approach to estimate the coefficients and variance of the error term. Furthermore, the conditional biases, variances and asymptotic normalities of the resulting estimators are studied explicitly. The estimators of the coefficient functions in nonparametric part perform efficiently and robustly regardless of smoothness degree of the coefficient functions. Some simulation studies are carried out to examine the finite sample performance of the proposed methods. Finally, the methodologies are illustrated by a real data set.

報(bào)告人簡(jiǎn)介：林金官，1964年7月生，男，博士，東南大學(xué)數(shù)學(xué)系副主任、統(tǒng)計(jì)學(xué)教授、統(tǒng)計(jì)學(xué)科帶頭人、博士生導(dǎo)師?，F(xiàn)主要從事非線(xiàn)性統(tǒng)計(jì)、金融統(tǒng)計(jì)與風(fēng)險(xiǎn)度量、模糊統(tǒng)計(jì)分析、面板數(shù)據(jù)分析和統(tǒng)計(jì)應(yīng)用等方面的研究工作。2000年以來(lái), 在國(guó)內(nèi)外核心期刊上發(fā)表論文七十余篇，其中SCI和SSCI論文五十余篇。近十年來(lái)，主持國(guó)家自然科學(xué)基金、國(guó)家社會(huì)科學(xué)基金項(xiàng)目等國(guó)家及項(xiàng)目四項(xiàng)，主持省部級(jí)基金項(xiàng)目六項(xiàng)。目前學(xué)術(shù)兼職為東南大學(xué)應(yīng)用概率統(tǒng)計(jì)研究所所長(zhǎng)、東南大學(xué)金融統(tǒng)計(jì)研究所常務(wù)副所長(zhǎng)；中國(guó)概率統(tǒng)計(jì)學(xué)會(huì)理事、中國(guó)現(xiàn)場(chǎng)統(tǒng)計(jì)研究會(huì)常務(wù)理事、中國(guó)統(tǒng)計(jì)學(xué)會(huì)常務(wù)理事、中國(guó)教育統(tǒng)計(jì)學(xué)會(huì)常務(wù)理事、中國(guó)工程概率統(tǒng)計(jì)學(xué)會(huì)副理事長(zhǎng)、江蘇省概率統(tǒng)計(jì)學(xué)會(huì)理事長(zhǎng)、江蘇省現(xiàn)場(chǎng)統(tǒng)計(jì)研究會(huì)副理事長(zhǎng)、江蘇省統(tǒng)計(jì)學(xué)會(huì)常務(wù)理事；中文核心期刊《應(yīng)用概率統(tǒng)計(jì)》、《數(shù)理統(tǒng)計(jì)與管理》雜志編委，第六屆全國(guó)統(tǒng)計(jì)教材編審委員會(huì)委員，2013-2017教育部統(tǒng)計(jì)學(xué)類(lèi)教學(xué)指導(dǎo)委員會(huì)委員等。

                                                                               主辦：研究生院
                                                                                      承辦：kaiyun開(kāi)云官方網(wǎng)站