Handling missing data issues in clinical trials for rheumatic diseases.

Missing data are ubiquitous in clinical trials for rheumatic diseases, and it is important to accommodate them using appropriate statistical techniques. We review some of the basic considerations for missing data and survey a range of statistical techniques for analysis of longitudinal clinical trial data with missingness. Using clinical trial data from patients with diffuse systemic sclerosis, we show that different approaches to handling missing data can lead to different conclusions on the efficacy of the treatment. We then suggest how such discrepancies might be addressed. In particular, we emphasize that the commonly used method in rheumatic clinical trials of carrying the last observation forward to impute missing values should not be the primary analysis. We review software for analyzing different types of missing data and discuss our freely available software library for analyzing the more difficult but more realistic situation when the probability of dropout or missing data may depend on the unobserved missing value.

[1]  Jun Shao,et al.  Last observation carry‐forward and last observation analysis , 2003, Statistics in medicine.

[2]  John M. Thompson,et al.  Bayesian Analysis in Stata with WinBUGS , 2006 .

[3]  Vic Hasselblad,et al.  Can one assess whether missing data are missing at random in medical studies? , 2006, Statistical methods in medical research.

[4]  Myunghee C. Paik,et al.  The generalized estimating equation approach when data are not missing completely at random , 1997 .

[5]  Nicholas J. Horton,et al.  Multiple Imputation in Practice , 2001 .

[6]  Sophia Rabe-Hesketh,et al.  Multilevel and Longitudinal Modeling Using Stata , 2005 .

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

[8]  S J Pocock,et al.  Estimation and comparison of rates of change in longitudinal studies with informative drop-outs. , 1999, Statistics in medicine.

[9]  G H Guyatt,et al.  Intention-to-treat principle. , 2001, CMAJ : Canadian Medical Association journal = journal de l'Association medicale canadienne.

[10]  T. Belin,et al.  Using Multiple Imputation to Incorporate Cases with Missing Items in a Mental Health Services Study , 2000, Health Services and Outcomes Research Methodology.

[11]  Stuart R. Lipsitz,et al.  Analysis of longitudinal data with non‐ignorable non‐monotone missing values , 2002 .

[12]  S. Pocock,et al.  Coping with missing data in clinical trials: A model‐based approach applied to asthma trials , 2002, Statistics in medicine.

[13]  C. Begg.  Ruminations on the intent-to-treat principle. , 2000, Controlled Clinical Trials.

[14]  C. Coffey,et al.  Modern statistical methods for handling missing repeated measurements in obesity trial data: beyond LOCF , 2003, Obesity reviews : an official journal of the International Association for the Study of Obesity.

[15]  Myunghee C. Paik.  Nonignorable Missingness in Matched Case–Control Data Analyses , 2004 .

[16]  N. Breslow,et al.  Approximate inference in generalized linear mixed models , 1993 .

[17]  Christopher F. Baum,et al.  Instrumental Variables and GMM: Estimation and Testing , 2003 .

[18]  T. Stijnen,et al.  Review: a gentle introduction to imputation of missing values. , 2006, Journal of clinical epidemiology.

[19]  R. Jennrich,et al.  Unbalanced repeated-measures models with structured covariance matrices. , 1986, Biometrics.

[20]  D. Machin,et al.  Intention to treat--who should use ITT? , 1993, British Journal of Cancer.

[21]  D. Heitjan,et al.  Distinguishing “Missing at Random” and “Missing Completely at Random” , 1996 .

[22]  S. Lipsitz,et al.  Missing responses in generalised linear mixed models when the missing data mechanism is nonignorable , 2001 .

[23]  S. Hollis,et al.  What is meant by intention to treat analysis? Survey of published randomised controlled trials , 1999, BMJ.

[24]  Robert E. Weiss,et al.  Modeling Longitudinal Data , 2005 .

[25]  Xiaohong Yan,et al.  A reanalysis of a longitudinal scleroderma clinical trial using non-ignorable missingness models , 2007 .

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

[27]  J. Ware,et al.  Applied Longitudinal Analysis , 2004 .

[28]  Ken P Kleinman,et al.  Much Ado About Nothing , 2007, The American statistician.

[29]  LAST OBSERVATION ANALYSIS IN ANOVA AND ANCOVA , 2005 .

[30]  D B Rubin,et al.  Multiple imputation in health-care databases: an overview and some applications. , 1991, Statistics in medicine.

[31]  D. Bates,et al.  Nonlinear mixed effects models for repeated measures data. , 1990, Biometrics.

[32]  Scott L. Zeger,et al.  [Inference Based on Estimating Functions in the Presence of Nuisance Parameters]: Rejoinder , 1995 .

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

[34]  Joseph L Schafer,et al.  Analysis of Incomplete Multivariate Data , 1997 .

[35]  D. Heitjan,et al.  Annotation: what can be done about missing data? Approaches to imputation. , 1997, American journal of public health.

[36]  Geert Molenberghs,et al.  Analyzing incomplete longitudinal clinical trial data. , 2004, Biostatistics.

[37]  Ning Li,et al.  Tools for Analyzing Multiple Imputed Datasets , 2003 .

[38]  Byron Hall.  Bayesian Inference , 2011 .

[39]  T. Belin.  Missing data: what a little can do, and what researchers can do in response. , 2009, American journal of ophthalmology.

[40]  Geert Molenberghs,et al.  Sensitivity Analysis for Pattern Mixture Models , 2004, Journal of biopharmaceutical statistics.

[41]  Stephen Evans,et al.  Last observation carry‐forward and last observation analysis , 2004, Statistics in medicine.

[42]  Peter J. Diggle,et al.  Testing for random dropouts in repeated measurement data. , 1989 .

[43]  S. E. Hills,et al.  Illustration of Bayesian Inference in Normal Data Models Using Gibbs Sampling , 1990 .

[44]  K. Rockwood,et al.  Size of the treatment effect on cognition of cholinesterase inhibition in Alzheimer’s disease , 2004, Journal of Neurology, Neurosurgery & Psychiatry.

[45]  Patrick Royston,et al.  Multiple Imputation of Missing Values: Further Update of Ice, with an Emphasis on Categorical Variables , 2009 .

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

[47]  Geert Molenberghs,et al.  Missing Data in Clinical Studies , 2007 .

[48]  J. Schafer.  Multiple imputation: a primer , 1999, Statistical methods in medical research.

[49]  Andrew Gelman,et al.  R2WinBUGS: A Package for Running WinBUGS from R , 2005 .

[50]  M. Mayes,et al.  A multicenter, randomized, double-blind, placebo-controlled trial of oral type I collagen treatment in patients with diffuse cutaneous systemic sclerosis: I. oral type I collagen does not improve skin in all patients, but may improve skin in late-phase disease. , 2008, Arthritis and rheumatism.

[51]  M Y Hu,et al.  Performance of a general location model with an ignorable missing-data assumption in a multivariate mental health services study. , 1999, Statistics in medicine.

[52]  H. Boshuizen,et al.  Multiple imputation of missing blood pressure covariates in survival analysis. , 1999, Statistics in medicine.

[53]  G. Koch,et al.  The Application of the Principle of Intention–to–Treat to the Analysis of Clinical Trials , 1991 .

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

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

[56]  Roderick J A Little,et al.  A Review of Hot Deck Imputation for Survey Non‐response , 2010, International statistical review = Revue internationale de statistique.

[57]  Donald Hedeker,et al.  Longitudinal Data Analysis , 2006 .

[58]  D. Bates,et al.  Mixed-Effects Models in S and S-PLUS , 2001 .

[59]  Mark Woodward,et al.  Imputations of missing values in practice: results from imputations of serum cholesterol in 28 cohort studies. , 2004, American journal of epidemiology.

[60]  D. Rubin,et al.  Estimation in Covariance Components Models , 1981 .

[61]  R Little,et al.  Intent-to-treat analysis for longitudinal studies with drop-outs. , 1996, Biometrics.

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

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

[64]  R C Littell,et al.  Statistical analysis of repeated measures data using SAS procedures. , 1998, Journal of animal science.

[65]  Geert Molenberghs,et al.  Analyzing Incomplete Discrete Longitudinal Clinical Trial Data , 2006, math/0606497.

[66]  G. King,et al.  Analyzing Incomplete Political Science Data: An Alternative Algorithm for Multiple Imputation , 2001, American Political Science Review.