An Approximate Generalized Linear Model with Random Effects for Informative Missing Data

Follmann, Dean; Wu, Margaret

doi:10.2307/2533322

Cited by 253 publications

(281 citation statements)

References 18 publications

Supporting

Mentioning

278

Contrasting

Unclassified

Order By: Relevance

“…In this case random effects are are used to affect the dependence between the responses Y and the missing mechanism M . These models are also known as shared parameter models [24,25]. In this cases the factorization of the joint model is…”

Section: Implications Of Violating the Mar Assumption Although The DImentioning

confidence: 99%

Multiple imputation: review of theory, implementation and software

Harel

Zhou

2007

Statistics in Medicine

347

274

View full text Add to dashboard Cite

SUMMARYMissing data is a common complication in data analysis. In many medical settings missing data can cause difficulties in estimation, precision and inference. Multiple imputation (MI) [1] is a simulation based approach to deal with incomplete data. Although there are many different methods to deal with incomplete data, MI has become one of the leading methods. Since the late 80's we observed a constant increase in the use and publication of MI related research. This tutorial does not attempt to cover all the material concerning MI, but rather provides an overview and combines together the theory behind MI, the implementation of MI, and discusses increasing possibilities of the use of MI using commercial and free software. We illustrate some of the major points using an example from an Alzheimer disease

show abstract

Section: Implications Of Violating the Mar Assumption Although The DImentioning

confidence: 99%

Multiple imputation: review of theory, implementation and software

Harel

Zhou

2007

Statistics in Medicine

347

274

View full text Add to dashboard Cite

show abstract

“…This type of models have been developed as a shared parameter model (Follmann and Wu, 1995) or a shared random effects model (Gao, 2004).…”

Section: Basic Setupmentioning

confidence: 99%

“…The methods handling nonignorable missingness require both auxiliary models to be correctly specified. Many authors attacked the nonignorability problem using likelihood approach (Follmann and Wu, 1995;Ibrahim et al, 2001;Gao, 2004;Zhang and Paik, 2009), imputation approach (Paik, 1997;Yang et al, 2013), and inverse probability weighting approach Shao and Wang, 2016). Nonignorability often causes nonidentifiability which should be carefully addressed in developing methods (Wang et al, 2014;Molenberghs et al, 2008).…”

Section: Introductionmentioning

confidence: 99%

A Robust Calibration-Assisted Method for Linear Mixed Effects Model Under Cluster-Specific Nonignorable Missingness

Kwon¹,

Kim²,

Paik³

et al. 2018

STAT SINICA

View full text Add to dashboard Cite

We propose a method for linear mixed effects models when the covariates are completely observed but the outcome of interest is subject to missing under cluster-specific nonignorable (CSNI) missingness. Our strategy is to replace missing quantities in the full-data objective function with unbiased predictors derived from inverse probability weighting and calibration technique. The proposed approach can be applied to estimating equations or likelihood functions with modified E-step, and does not require numerical integration as previous methods. Unlike usual inverse probability weighting, the proposed method does not require correct specification of the response model as long as the CSNI assumption is correct, and renders inference under CSNI without a full distributional assumption. Consistency and asymptotic normality are shown with a consistent variance estimator. Simulation results and a real data example are presented.

show abstract

“…Therefore, nonignorable dropout mechanism is introduced. Different selection models were proposed to handle nonignorable dropouts by (Diggle and Kenward, 1994;Heckman, 1976;Little, 1995;Follmann and Wu, 1995;Crouchley and Ganjali, 2002;Yang and Li, 2011). In addition this issue was addressed in detail in advanced statistical books (Molenberghs and Kenward, 2007;Daniels and Hogan, 2008;Fitzmaurice et al, 2008;Enders, 2010).…”

Section: Jmssmentioning

confidence: 99%

“…Second, this model is sensitive to misspecification. Crouchley and Ganjali (2002) introduced a Generalized Heckman selection model and showed that the models proposed by (Wu and Carroll, 1988;Follmann and Wu, 1995;Diggle and Kenward, 1994;Ridder, 1990) can be written by this model.…”

Section: Introductionmentioning

confidence: 99%

A Mixture Dropout Mechanism in a Longitudinal Study With Two Time Points: A Methadone Study

Toghrayee¹,

Jalili²,

Low³

et al. 2014

Journal of Mathematics and Statistics

View full text Add to dashboard Cite

One of the most important issues that confront statisticians in longitudinal studies is dropouts. A variety of reasons may lead to withdrawal from a study and produce two different missingness mechanisms, namely, missing at random and non-ignorable dropouts. Nevertheless, none of these mechanisms is tenable in most studies. In addition, it may be that not all of dropouts are nonignorable. Many dropout handling methods have been employed by assuming only one of these dropout mechanisms. In this study, the dropout indicator is improved to take into account both dropout mechanisms. In this two-stage approach, a selection model is combined with an imputation method for dropout process in a longitudinal study with two time points. Simulation studies in a variety of situations are conducted to evaluate this approach in estimating the mean of the response variable at the second time point. This parameter is estimated by using maximum likelihood method. The results of the simulation studies indicate the superiority of the proposed method to the existing ones in estimating the mean of the variable with dropouts. In addition, this method is performed on a methadone dataset of 161 patients admitted to an Iranian clinic to estimate the final methadone dose.

show abstract

An Approximate Generalized Linear Model with Random Effects for Informative Missing Data

Cited by 253 publications

References 18 publications

Multiple imputation: review of theory, implementation and software

Multiple imputation: review of theory, implementation and software

A Robust Calibration-Assisted Method for Linear Mixed Effects Model Under Cluster-Specific Nonignorable Missingness

A Mixture Dropout Mechanism in a Longitudinal Study With Two Time Points: A Methadone Study

Contact Info

Product

Resources

About