Robust weighted generalized estimating equations based on statistical depth

ABSTRACT Most of the longitudinal data contain influential points and for analyzing them generalized and weighted generalized estimating equations (GEEs and WGEEs) are highly influenced by these points. An approach for dealing with outliers is having weight functions. In this article, we propose some new weights based on the statistical depth. These weights express centrality of points with respect to the whole sample with a smaller depth (larger depth) for the point far from the center (for the point near the center). The proposed approach leads to robust WGEE. These approaches are applied on two real datasets and some simulation studies.

[1]  Robert Serfling,et al.  Nonparametric Multivariate Descriptive Measures Based on Spatial Quantiles , 2004 .

[2]  J. Chang-Claude,et al.  Identifying influential families using regression diagnostics for generalized estimating equations , 1998, Genetic epidemiology.

[3]  Wenqing He,et al.  Median Regression Models for Longitudinal Data with Dropouts , 2009, Biometrics.

[4]  Douglas W Mahoney,et al.  Linear mixed effects models. , 2007, Methods in molecular biology.

[5]  G. Molenberghs,et al.  Models for Discrete Longitudinal Data , 2005 .

[6]  Michael Ruogu Zhang,et al.  Comprehensive identification of cell cycle-regulated genes of the yeast Saccharomyces cerevisiae by microarray hybridization. , 1998, Molecular biology of the cell.

[7]  S. Zeger,et al.  Longitudinal data analysis using generalized linear models , 1986 .

[8]  B. Lindsay,et al.  Improving generalised estimating equations using quadratic inference functions , 2000 .

[9]  Nicole A. Lazar,et al.  Statistical Analysis With Missing Data , 2003, Technometrics.

[10]  D. Pregibon.  Resistant fits for some commonly used logistic models with medical application. , 1982, Biometrics.

[11]  S. Keleş,et al.  Sparse partial least squares regression for simultaneous dimension reduction and variable selection , 2010, Journal of the Royal Statistical Society. Series B, Statistical methodology.

[12]  Zhong Yi Zhu,et al.  Variable selection in robust regression models for longitudinal data , 2012, J. Multivar. Anal..

[13]  Unkyung Lee.  Analysis of semiparametric regression models for the cumulative incidence functions under the two-phase sampling designs , 2016 .

[14]  R. Dyckerhoff.  Data depths satisfying the projection property , 2004 .

[15]  R. Serfling,et al.  General notions of statistical depth function , 2000 .

[16]  D. Kosiorowski,et al.  DepthProc: An R Package for Robust Exploration of Multidimensional Economic Phenomena , 2014, 1408.4542.

[17]  Andrzej T. Galecki,et al.  Linear mixed-effects models using R , 2013 .

[18]  J. Ware,et al.  Random-effects models for longitudinal data. , 1982, Biometrics.

[19]  B. Qaqish,et al.  Resistant fits for regression with correlated outcomes an estimating equations approach , 1999 .

[20]  Regina Y. Liu,et al.  Multivariate analysis by data depth: descriptive statistics, graphics and inference, (with discussion and a rejoinder by Liu and Singh) , 1999 .

[21]  W. Pan.  Akaike's Information Criterion in Generalized Estimating Equations , 2001, Biometrics.

[22]  E. Ronchetti,et al.  Robust Inference for Generalized Linear Models , 2001 .

[23]  P. Thall,et al.  Some covariance models for longitudinal count data with overdispersion. , 1990, Biometrics.

[24]  Minghua Chen,et al.  Robust estimating equation based on statistical depth , 2006 .