Unpredictable bias when using the missing indicator method or complete case analysis for missing confounder values: an empirical example

Journal of Clinical Epidemiology

Volumn 63, Issue 7, 2010, Pages 728-736

  Knol, Mirjam J ^a,b   Janssen, Kristel J M ^a   Donders, A Rogier T ^c   Egberts, Antoine C G ^a,b   Heerdink, E Rob ^b   Grobbee, Diederick E ^a   Moons, Karel G M ^a   Geerlings, Mirjam I ^a  

^a UNIVERSITY MEDICAL CENTER UTRECHT   (Netherlands)

^b UTRECHT UNIVERSITY   (Netherlands)

^c RADBOUD UNIVERSITY MEDICAL CENTER   (Netherlands)

Author keywords

Complete case; Confounder; Etiologic; Indicator method; Missing; Multiple imputation

Indexed keywords

ADULT; ALGORITHM; ARTICLE; COHORT ANALYSIS; COMPLETE CASE ANALYSIS; CONTROLLED STUDY; FEMALE; HUMAN; INCOME; INTERMETHOD COMPARISON; MAJOR CLINICAL STUDY; MAJOR DEPRESSION; MALE; MARRIAGE; MISSING INDICATOR METHOD; MULTIPLE IMPUTATION; PRIORITY JOURNAL; RISK FACTOR; STATISTICAL ANALYSIS;

AGE FACTORS; BIAS (EPIDEMIOLOGY); BIOMEDICAL RESEARCH; COHORT STUDIES; CONFOUNDING FACTORS (EPIDEMIOLOGY); DATA COLLECTION; DEPRESSIVE DISORDER; FEMALE; HUMANS; INCOME; MALE; MARITAL STATUS; MIDDLE AGED; OUTCOME ASSESSMENT (HEALTH CARE); RESEARCH DESIGN; SEX FACTORS;

EID: 77952422361     PISSN: 08954356     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.jclinepi.2009.08.028     Document Type: Article

References (29)

1. Greenland S., and Finkle W.D. A critical look at methods for handling missing covariates in epidemiologic regression analyses. Am J Epidemiol 142 (1995) 1255-1264
2. Little R.J. Regression with missing X's: a review. J Am Stat Assoc 87 (1992) 1227-1237
3. Jones M.P. Indicator and stratification methods for missing explanatory variables in multiple linear regression. J Am Stat Assoc 91 (1996) 222-230
4. Schafer J.L., and Graham J.W. Missing data: our view of the state of the art. Psychol Methods 7 (2002) 147-177
5. Vach W., and Blettner M. Biased estimation of the odds ratio in case-control studies due to the use of ad hoc methods of correcting for missing values for confounding variables. Am J Epidemiol 134 (1991) 895-907
6. Anderson A.B., Basilevsky A., and Hum D.P.J. Missing data: a review of the literature. In: Rossi P.H., Wright J.D., and Anderson A. (Eds). Handbook of survey research (1983), Academic Press, New York, NY 415-492
7. Regression analysis. Miettinen OS Theoretical epidemiology: principles of occurrence research (1985), John Wiley & Sons, New York, NY 216-243
8. Donders A.R., van der Heijden G.J., Stijnen T., and Moons K.G. Review: a gentle introduction to imputation of missing values. J Clin Epidemiol 59 (2006) 1087-1091
9. Burton A., and Altman D.G. Missing covariate data within cancer prognostic studies: a review of current reporting and proposed guidelines. Br J Cancer 91 (2004) 4-8
10. Vandenbroucke J.P., von Elm E.E., Altman D.G., Gotzsche P.C., Mulrow C.D., Pocock S.J., et al. Strengthening the reporting of observational studies in epidemiology (STROBE): explanation and elaboration. Epidemiology 18 (2007) 805-835
11. White I.R., and Thompson S.G. Adjusting for partially missing baseline measurements in randomized trials. Stat Med 24 (2005) 993-1007
12. Moons K.G., Donders R.A., Stijnen T., and Harrell Jr. F.E. Using the outcome for imputation of missing predictor values was preferred. J Clin Epidemiol 59 (2006) 1092-1101
13. Rubin D.B. Multiple imputation after 18+ years. J Am Stat Assoc 91 (1996) 473-489
14. Rubin D.B., and Schenker N. Multiple imputation in health-care databases: an overview and some applications. Stat Med 10 (1991) 585-598
15. van Buuren S., Boshuizen H.C., and Knook D.L. Multiple imputation of missing blood pressure covariates in survival analysis. Stat Med 18 (1999) 681-694
16. Arnold A.M., and Kronmal R.A. Multiple imputation of baseline data in the cardiovascular health study. Am J Epidemiol 157 (2003) 74-84
17. van der Heijden G.J., Donders A.R., Stijnen T., and Moons K.G. Imputation of missing values is superior to complete case analysis and the missing-indicator method in multivariable diagnostic research: a clinical example. J Clin Epidemiol 59 (2006) 1102-1109
18. Crawford S.L., Tennstedt S.L., and McKinlay J.B. A comparison of anlaytic methods for non-random missingness of outcome data. J Clin Epidemiol 48 (1995) 209-219
19. Goldstein A.M., Martinez M., Tucker M.A., and Demenais F. Gene-covariate interaction between dysplastic nevi and the CDKN2A gene in American melanoma-prone families. Cancer Epidemiol Biomarkers Prev 9 (2000) 889-894
20. Knol M.J., Heerdink E.R., Egberts A.C., Geerlings M.I., Gorter K.J., Numans M.E., et al. Depressive symptoms in subjects with diagnosed and undiagnosed type 2 diabetes. Psychosom Med 69 (2007) 300-305
21. King M., Weich S., Torres F., Svab I., Maaroos H., Neeleman J., et al. Prediction of depression in European general practice attendees: the PREDICT study. BMC Public Health 6 (2006) 6
22. World Health Organization. Composite international diagnostic interview (CIDI). Version 2.1 (1997), WHO, Geneva, Switzerland
23. Robins L.N., Wing J., Wittchen H.U., Helzer J.E., Babor T.F., Burke J., et al. The Composite International Diagnostic Interview. An epidemiologic instrument suitable for use in conjunction with different diagnostic systems and in different cultures. Arch Gen Psychiatry 45 (1988) 1069-1077
24. Buuren van S., and Oudshoorn K. Flexible multivariate imputation by MICE (1999), TNO Prevention and Health, Leiden, The Netherlands
25. Rubin D.B. Multiple imputation for nonresponse in surveys (1987), John Wiley & Sons, Hoboken, NJ
26. R Development Core Team. R: a language and environment for statistical computing. ISBN 3-900051-07-0. Available at (2006), R Foundation for Statistical Computing, Vienna, Austria. http://www.R-project.org
27. Gorelick M.H. Bias arising from missing data in predictive models. J Clin Epidemiol 59 (2006) 1115-1123
28. Horton N.J., and Kleinman K.P. Much ado about nothing: a comparison of missing data methods and software to fit incomplete data regression models. Am Stat 61 (2007) 79-90
29. Little R.J., and Rubin D.B. Statistical analysis with missing data (1987), John Wiley & Sons, Hoboken, NJ