高維混合效應(yīng)模型的雙正則化分位回歸方法研究
[Abstract]:In this paper, a double regularization quantile regression method is proposed for high dimensional mixed effect model. By simultaneously implementing L1 regularization punishment for both random and fixed effect coefficients, we can select important explanatory variables on the one hand, and eliminate the deviation caused by individual random fluctuations on the other. The alternative iterative algorithm for parameter estimation not only solves the problem of determining two parameters simultaneously, but also has a fast speed. The simulation results also show that this method not only has strong anti-interference ability to the error types, but also performs well when the model has different sparse degree, especially in the case of higher dimension of explanatory variables than samples. In order to facilitate the selection of optimal regularization parameters in practical problems, this paper also makes a comparative study of the two parameters selection criteria. Finally, an empirical demonstration of an educational data is made by using a new method to find out the important factors that affect the students' achievement at each locus.
【作者單位】: 湖北工業(yè)大學(xué)理學(xué)院;中國(guó)人民大學(xué)統(tǒng)計(jì)學(xué)院;華中師范大學(xué)數(shù)學(xué)與統(tǒng)計(jì)學(xué)學(xué)院;
【基金】:國(guó)家社會(huì)科學(xué)基金項(xiàng)目“高維復(fù)雜面板數(shù)據(jù)的雙懲罰分位回歸建模方法研究”(17BJY210) 國(guó)家自然科學(xué)基金項(xiàng)目“基于當(dāng)代分位回歸與鞍點(diǎn)逼近方法的復(fù)雜數(shù)據(jù)分析”(11271368) 教育部人文社會(huì)科學(xué)青年基金項(xiàng)目“面板數(shù)據(jù)的分位回歸方法及其變量選擇問(wèn)題研究”(13YJC790105) 湖北工科研啟業(yè)大學(xué)博士動(dòng)基金項(xiàng)目“高維復(fù)雜縱向數(shù)據(jù)的分位回歸建模研究”(BSQD13050)資助
【分類號(hào)】:C81
【參考文獻(xiàn)】
相關(guān)期刊論文 前2條
1 ;A Longitudinal Study of the Effects of Family Background Factors on Mathematics Achievements Using Quantile Regression[J];Acta Mathematicae Applicatae Sinica;2008年01期
2 ;Hierarchical linear regression models for conditional quantiles[J];Science in China(Series A:Mathematics);2006年12期
【共引文獻(xiàn)】
相關(guān)期刊論文 前10條
1 羅幼喜;田茂再;李翰芳;;高維混合效應(yīng)模型的雙正則化分位回歸方法研究[J];統(tǒng)計(jì)研究;2017年07期
2 羅幼喜;李翰芳;;基于雙自適應(yīng)Lasso懲罰的隨機(jī)效應(yīng)分位回歸模型研究[J];數(shù)量經(jīng)濟(jì)技術(shù)經(jīng)濟(jì)研究;2017年05期
3 TIAN MaoZai;CHAN Ngai Hang;;Adaptive quantile regression with precise risk bounds[J];Science China(Mathematics);2017年05期
4 王天穎;楊亞琦;田茂再;;面板數(shù)據(jù)分位回歸中適應(yīng)性LASSO調(diào)節(jié)參數(shù)的選擇[J];數(shù)理統(tǒng)計(jì)與管理;2017年03期
5 戴曉文;晏振;田茂再;;帶固定效應(yīng)面板數(shù)據(jù)空間誤差模型的分位回歸估計(jì)[J];應(yīng)用數(shù)學(xué)學(xué)報(bào);2016年06期
6 晏振;田茂再;;刪失線性分位回歸模型的MCEM估計(jì)及應(yīng)用[J];系統(tǒng)科學(xué)與數(shù)學(xué);2016年02期
7 司世景;李二倩;田茂再;;帶有二元連接函數(shù)的半?yún)?shù)模型[J];數(shù)學(xué)年刊A輯(中文版);2015年02期
8 李子強(qiáng);田茂再;羅幼喜;;面板數(shù)據(jù)的自適應(yīng)Lasso分位回歸方法研究[J];統(tǒng)計(jì)與信息論壇;2014年07期
9 陳彥靚;田茂再;;關(guān)于縱向數(shù)據(jù)分析方法的比較研究[J];統(tǒng)計(jì)與決策;2013年10期
10 張圓圓;鄧文禮;田茂再;;基于變系數(shù)模型的自適應(yīng)分位回歸方法[J];數(shù)學(xué)年刊A輯(中文版);2012年05期
,本文編號(hào):2157356
本文鏈接:http://sikaile.net/shekelunwen/shgj/2157356.html