講座題目：An overview of Spearman filter for feature screening
主 講 人：嚴(yán)曉東 香港理工大學(xué)助理研究員
時(shí) 間：1月25日（周四）下午14:30
地 點(diǎn)：燕山校區(qū)1號(hào)教學(xué)樓5樓統(tǒng)計(jì)學(xué)院資料室
主講人簡(jiǎn)介：
嚴(yán)曉東，香港理工大學(xué)助理研究員；于2017年獲得云南大學(xué)博士；2006-2010就讀于山東財(cái)經(jīng)大學(xué)統(tǒng)計(jì)與數(shù)學(xué)學(xué)院； 2007.9-2009.6在山東大學(xué)交流訪問(wèn)一年；2014.10-2014.12在香港中文大學(xué)訪問(wèn)；2015.7-2017.12 在香港理工大學(xué)做全職研究助理； 2017.12年在香港理工大學(xué)做博士后至今。研究興趣主要集中在高維數(shù)據(jù)的變量選擇和特征篩選、缺失數(shù)據(jù)統(tǒng)計(jì)建模、貝葉斯局部影響分析、生存分析以及最近熱門(mén)的子群分析、融合分析和深度學(xué)習(xí)。論文發(fā)表在諸如經(jīng)濟(jì)領(lǐng)域權(quán)威期刊Journal of Econometrics以及概率統(tǒng)計(jì)領(lǐng)域一流期刊 Computational Statistics & Data Analysis.
報(bào)告摘要：
In this presentation, we propose Spearman rank correlation based screening procedure for ultrahigh-dimensional data with complete, censored, missing or categorical response cases, respectively . The proposed method is model-free without specifying any regression form of predictors and a response variable and it is invariant to monotone transformations of a response variable and predictors. The sure screening and rank consistency properties are established under some mild regularity conditions. The simulation studies demonstrate that the new screening method performs well in the presence of the heavy-tailed distribution or strongly dependent predictors or outliers and that it has the superior performance over the existing nonparametric screening procedures. In particular, the new screening method still works well when a response variable is observed under a high censoring or missing rate. And when the response is categorical, it can deal with categorical-adaptive screening procedure. An illustrative example is provided.
科研處 統(tǒng)計(jì)學(xué)院（大數(shù)據(jù)與指數(shù)研究院）
山東省大數(shù)據(jù)研究會(huì)
2018年1月23日
官方微博