The role of proxy information in missing data analysis

This article investigates the role of proxy data in dealing with the common problem of missing data in clinical trials using repeated measures designs. In an effort to avoid the missing data situation, some proxy information can be gathered. The question is how to treat proxy information, that is, is it always better to utilize proxy information when there are missing data? A model for repeated measures data with missing values is considered and a strategy for utilizing proxy information is developed. Then, simulations are used to compare the power of a test using proxy to simply utilizing all available data. It is concluded that using proxy information can be a useful alternative when such information is available. The implications for various clinical designs are also considered and a data collection strategy for efficiently estimating parameters is suggested.

[1]  D. Rubin,et al.  Statistical Analysis with Missing Data , 1988 .

[2]  M. Wickens.  A Note on the Use of Proxy Variables , 1972 .

[3]  Gregory C. Reinsel,et al.  Investigation of dual-balanced crossover designs for two treatments , 1992 .

[4]  Incomplete Repeated Measures Data Analysis in the Presence of Treatment Effects , 1994 .

[5]  H. I. Patel.  Use of baseline measurements in the two-period crossover design , 1983 .

[6]  Bennett T. McCallum,et al.  Relative Asymptotic Bias from Errors of Omission and Measurement , 1972 .

[7]  Dennis J. Aigner.  MSE dominance of least squares with errors-of-observation , 1974 .

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

[9]  J. Grizzle.  THE TWO-PERIOD CHANGE-OVER DESIGN AN ITS USE IN CLINICAL TRIALS. , 1965, Biometrics.

[10]  K C Carriere,et al.  Crossover designs for clinical trials. , 1994, Statistics in medicine.

[11]  The Use of Proxy Variables When One or Two Independent Variables are Measured with Error , 1976 .

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

[13]  Keumhee C. Carriere,et al.  Crossover designs for two-treatment clinical trials , 2000 .

[14]  D. Feeny,et al.  Does it matter whom and how you ask? inter- and intra-rater agreement in the Ontario Health Survey. , 1997, Journal of clinical epidemiology.

[15]  On the Use of a Proxy Variable in Prediction: An MSE Comparison , 1981 .

[16]  G. Funk,et al.  Health states following head and neck cancer treatment: Patient, health‐care professional, and public perspectives , 1998, Head & neck.

[17]  Keumhee C. Carriere,et al.  Methods for repeated measures data analysis with missing values , 1999 .

[18]  H. I. Patel.  Analysis of incomplete data from a clinical trial with repeated measurements , 1991 .

[19]  G. Trenkler,et al.  Dropping variables versus use of proxy variables in linear regression , 1996 .

[20]  Roger A. Sugden,et al.  Multiple Imputation for Nonresponse in Surveys , 1988 .

[21]  P. Frost.  Proxy Variables and Specification Bias , 1979 .