The role of proxy information in missing data analysis

Abstract

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.

Get full access to this article

View all access options for this article.

References

Schafer JL. Analysis of incomplete multivariate data. London: Chapman & Hall , 1997.

Carrie`re KC. Incomplete repeated measures data analysis in the presence of treatment effects . Journal of the American Statistical Association 1994; 89: 680-686 .

Carrie`re KC. Methods for repeated measures data analysis with missing values . Journal of Statistical Planning and Inference, 1999; 77: 221-236 .

Rubin DB. Multiple imputation for nonresponse in surveys. New York: John Wiley , 1987.

Grootendorst P , Feeny D , Furlong W. Does it matter whom and how you ask? An investigation into inter- and intra-rater agreement in the 1996 Ontario Health Survey . Journal of Clinic Epidemiology. 1997; 50: 127-135 .

Jalukar V , Funk GF , Christensen AJ , Karnell LH , Moran PJ. Health states following head and neck cancer treatment: patient, health-care professional, and public perspectives . Health and Neck 1998; 20: 600-608 .

McCallum BT. Relative asymptotic bias from errors of omission and measurement . Econometrica 1972; 40: 757-758 .

Wickens MR. A note on the use of proxy variables . Econometrica 1972; 40: 759-761 .

Barnow BS. The use of proxy variables when one or two independent variables are measured with error . The American Statistician 1976; 30: 119-121 .

10.

Aigner DJ. MSE dominance of least squares with errors-of-observation . Journal of Econometrics 1974; 2: 365-372 .

11.

Maddala GS. Econometrics. New York: McGraw-Hill , 1977.

12.

Frost PA. Proxy variables and specification bias . The Review of Economics and Statistics 1979; 61: 323-325 .

13.

Dhrymes PJ. Introductory econometrics. New York: Springer , 1978.

14.

Ohtani K. On the use of a proxy variable in prediction: an MSE comparison . The Review of Economics and Statistics 1981; 63: 627-629 .

15.

Trenkler G , Stahlecker P. Dropping variables versus use of proxy variables in linear regression . Journal of Statistical Planning and Inference 1996; 50: 65-75 .

16.

Rubin DB. Inference and missing data . Biometrika 1976; 63: 581-592 .

17.

Huang R. Issues with repeated measures data. Unpublished PhD thesis, University of Alberta, 2001.

18.

Patel HI. Analysis of incomplete data from a clinical trial with repeated measurements . Biometrika 1991; 78: 609-619 .

19.

Carrie`re KC , Huang R. Crossover designs for two-treatment clinical trials . Journal of Statistical Planning and Inference 2000; 87: 125-134 .

20.

Carrie`re KC , Huang R. Traditional paradigms in pharmacoeconomics: consideration for cost-effective designs. In introduction to applied pharmacoeconomics. McGraw-Hill Medical Publishing Division , 2001; 19-39.

21.

Carrie`re KC , Reinsel GC. Investigation of dual-balanced crossover designs for two treatments . Biometrics 1992; 48: 1157-1164 .

22.

Carrie`re KC. Crossover designs for clinical trials . Statistics in Medicine 1994; 13: 1063-1069 .

23.

Patel HI. Use of baseline measurements in the two-period crossover design . Communications in Statistics-Theory and Methods 1983; 12: 2693-2712 .

24.

Grizzle JE. The two-period change-over design and its use in clinical trials . Biometrics 1965; 21: 467-480 .

25.

Little RJA , Rubin DB. Statistical analysis with missing data. New York, John Wiley : 1987.

26.

Goldstein H , Woodhouse G. Multilevel models with missing data . Eleventh International Workshop on Statistical Modelling. Orvieto, Italy, 1996

27.

Yu Lin. Hierarchical data and analytic methods: a simulation study. Unpublished MSc project, Department of Mathematical and Statistical Sciences, University of Alberta. Edmonton. Canada , 2003.