The Practical Use of Different Strategies to Handle Dropout in Longitudinal Studies

In the presence of dropout, valid statistical inferences based on longitudinal data can, in general, only be obtained from modeling the measurement process and the dropout process simultaneously. Many models have been proposed in the statistical literature, most of which have been formulated within the framework of selection models or pattern-mixture models. In this paper, we will use continuous data from a longitudinal clinical trial with a 24% dropout rate to illustrate some of the models frequently used in practice. We emphasize the underlying implicit assumptions made by the different approaches, and the sensitivity of the results with respect to these assumptions. The merits and drawbacks of the procedures are extensively discussed and compared from a practical point of view.

[1]  E. Lesaffre,et al.  A 12–week treatment for dermatophyte toe onychomycosis terbinafine 250mg/day vs. itraconazole 200mg/day—a double‐blind comparative trial , 1996, The British journal of dermatology.

[2]  Geert Molenberghs,et al.  Likelihood Based Frequentist Inference When Data Are Missing at Random , 1998 .

[3]  Geert Molenberghs,et al.  Linear Mixed Models in Practice: A SAS-Oriented Approach , 1997 .

[4]  Geert Molenberghs,et al.  Influence analysis to assess sensitivity of the dropout process , 2001 .

[5]  Taesung Park,et al.  Models for Categorical Data with Nonignorable Nonresponse , 1994 .

[6]  E Lesaffre,et al.  Assessing the goodness-of-fit of the Laird and Ware model--an example: the Jimma Infant Survival Differential Longitudinal Study. , 1999, Statistics in medicine.

[7]  M. Kenward,et al.  The analysis of longitudinal ordinal data with nonrandom drop-out , 1997 .

[8]  K. Bailey,et al.  Analysing changes in the presence of informative right censoring caused by death and withdrawal. , 1988, Statistics in medicine.

[9]  E Lesaffre,et al.  The detection of residual serial correlation in linear mixed models. , 1998, Statistics in medicine.

[10]  Geert Molenberghs,et al.  The Milk Protein Trial: Influence Analysis of the Dropout Process , 2000 .

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

[12]  G Molenberghs,et al.  Selection Models and Pattern‐Mixture Models for Incomplete Data with Covariates , 1999, Biometrics.

[13]  D. Roberts,et al.  Prevalence of dermatophyte onychomycosis in the United Kingdom: Results of an omnibus survey , 1992, The British journal of dermatology.

[14]  Roderick J. A. Little,et al.  Modeling the Drop-Out Mechanism in Repeated-Measures Studies , 1995 .

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

[16]  M. Kenward,et al.  Informative Drop‐Out in Longitudinal Data Analysis , 1994 .

[17]  R. Little.  Pattern-Mixture Models for Multivariate Incomplete Data , 1993 .

[18]  N M Laird,et al.  Model-based approaches to analysing incomplete longitudinal and failure time data. , 1997, Statistics in medicine.

[19]  Donald B. Rubin,et al.  Multiple imputation in mixture models for nonignorable nonresponse with follow-ups , 1993 .

[20]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[21]  G Molenberghs,et al.  Sensitivity Analysis for Nonrandom Dropout: A Local Influence Approach , 2001, Biometrics.

[22]  Mark R. Conaway,et al.  Non-ignorable Non-response Models for Time-ordered Categorical Variables , 1993 .

[23]  K. Bailey,et al.  Estimation and comparison of changes in the presence of informative right censoring: conditional linear model. , 1989, Biometrics.

[24]  N M Laird,et al.  Mixture models for the joint distribution of repeated measures and event times. , 1997, Statistics in medicine.

[25]  Mark R. Conaway,et al.  The Analysis of Repeated Categorical Measurements Subject to Nonignorable Nonresponse , 1992 .

[26]  Geert Molenberghs,et al.  Mastitis in diary cattle: local influence to assess sensitivity of the dropout process , 2001 .

[27]  Elizabeth A. Stasny,et al.  Estimating Gross Flows Using Panel Data with Nonresponse: An Example from the Canadian Labour Force Survey , 1986 .

[28]  D. Rubin.  INFERENCE AND MISSING DATA , 1975 .

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

[30]  W. P. Dixon,et al.  BMPD statistical software manual , 1988 .

[31]  Raymond J. Carroll,et al.  Estimation and comparison of changes in the presence of informative right censoring by modeling the censoring process , 1988 .

[32]  D. Rubin,et al.  Statistical Analysis with Missing Data. , 1989 .

[33]  Geert Verbeke,et al.  Assessing the goodness-of-fit of the laird and ware model : An example : The jimma infant survival differential longitudinal study , 1999 .

[34]  Cristián Zegers Ariztía,et al.  Manual , 2002 .

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

[36]  P. Bickel,et al.  Mathematical Statistics: Basic Ideas and Selected Topics , 1977 .

[37]  V. De Gruttola,et al.  Modelling progression of CD4-lymphocyte count and its relationship to survival time. , 1994, Biometrics.

[38]  Geert Molenberghs,et al.  Linear Mixed Models in Practice: A SAS-Oriented Approach , 1997 .

[39]  Nan M. Laird,et al.  Regression Analysis for Categorical Variables with Outcome Subject to Nonignorable Nonresponse , 1988 .

[40]  W F Rosenberger,et al.  Closed-form estimates for missing counts in two-way contingency tables. , 1992, Statistics in medicine.

[41]  P. Diggle,et al.  Analysis of Longitudinal Data , 2003 .