swgee: An R Package for Analyzing Longitudinal Data with Response Missingness and Covariate Measurement Error

Though longitudinal data often contain missing responses and error-prone covariates, relatively little work has been available to simultaneously correct for the effects of response missingness and covariate measurement error on analysis of longitudinal data. Yi (2008) proposed a simulation based marginal method to adjust for the bias induced by measurement error in covariates as well as by missingness in response. The proposed method focuses on modeling the marginal mean and variance structures, and the missing at random mechanism is assumed. Furthermore, the distribution of covariates are left unspecified. These features make the proposed method applicable to a broad settings. In this paper, we develop an R package, called swgee, which implements the method proposed by Yi (2008). Moreover, our package includes additional implementation steps which extend the setting considered by Yi (2008). To describe the use of the package and its main features, we report simulation studies and analyses of a data set arising from the Framingham Heart Study.

[1]  M. Kenward,et al.  Informative dropout in longitudinal data analysis (with discussion) , 1994 .

[2]  Raymond J. Carroll,et al.  Measurement error in nonlinear models: a modern perspective , 2006 .

[3]  Grace Y. Yi,et al.  A functional generalized method of moments approach for longitudinal studies with missing responses and covariate measurement error , 2012, Biometrika.

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

[5]  Wei Liu,et al.  Simultaneous Inference for Semiparametric Nonlinear Mixed‐Effects Models with Covariate Measurement Errors and Missing Responses , 2007, Biometrics.

[6]  Dylan S. Small,et al.  Marginal regression analysis of longitudinal data with time‐dependent covariates: a generalized method‐of‐moments approach , 2007 .

[7]  Paul J Rathouz,et al.  Performance of weighted estimating equations for longitudinal binary data with drop‐outs missing at random , 2002, Statistics in medicine.

[8]  John P. Buonaccorsi,et al.  Measurement Error: Models, Methods, and Applications , 2010 .

[9]  Alexander Kukush,et al.  Measurement Error Models , 2011, International Encyclopedia of Statistical Science.

[10]  M. Kenward.  Selection models for repeated measurements with non-random dropout: an illustration of sensitivity. , 1998, Statistics in medicine.

[11]  Wenqing He,et al.  SIMEX R Package for Accelerated Failure Time Models with Covariate Measurement Error , 2012 .

[12]  A. Genz,et al.  Computation of Multivariate Normal and t Probabilities , 2009 .

[13]  Grace Y Yi,et al.  A simulation-based marginal method for longitudinal data with dropout and mismeasured covariates. , 2008, Biostatistics.

[14]  J. R. Cook,et al.  Simulation-Extrapolation Estimation in Parametric Measurement Error Models , 1994 .

[15]  Robert N. Rodriguez,et al.  Weighted Methods for Analyzing Missing Data with the GEE Procedure , 2015 .

[16]  Viswanath Devanarayan,et al.  Empirical simulation extrapolation for measurement error models with replicate measurements , 2002 .

[17]  J. Robins,et al.  Analysis of semiparametric regression models for repeated outcomes in the presence of missing data , 1995 .

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

[19]  Assessing the validity of weighted generalized estimating equations , 2011 .

[20]  Grace Y. Yi,et al.  Statistical Analysis with Measurement Error or Misclassification , 2017 .

[21]  Paul Gustafson.  Measurement Error and Misclassification in Statistics and Epidemiology , 2003 .

[22]  Expected Estimating Equations for Missing Data, Measurement Error, and Misclassification, with Application to Longitudinal Nonignorable Missing Data , 2008, Biometrics.