Prevention Science

, Volume 19, Issue 3, pp 284–294 | Cite as

Principled Missing Data Treatments

Article

Abstract

We review a number of issues regarding missing data treatments for intervention and prevention researchers. Many of the common missing data practices in prevention research are still, unfortunately, ill-advised (e.g., use of listwise and pairwise deletion, insufficient use of auxiliary variables). Our goal is to promote better practice in the handling of missing data. We review the current state of missing data methodology and recent missing data reporting in prevention research. We describe antiquated, ad hoc missing data treatments and discuss their limitations. We discuss two modern, principled missing data treatments: multiple imputation and full information maximum likelihood, and we offer practical tips on how to best employ these methods in prevention research. The principled missing data treatments that we discuss are couched in terms of how they improve causal and statistical inference in the prevention sciences. Our recommendations are firmly grounded in missing data theory and well-validated statistical principles for handling the missing data issues that are ubiquitous in biosocial and prevention research. We augment our broad survey of missing data analysis with references to more exhaustive resources.

Keywords

Missing data Multiple imputation Full information maximum likelihood Auxiliary variables Intent-to-treat Statistical inference 

Notes

Acknowledgments

The authors wish to acknowledge the diligent assistance of Jacob Curtis, Brooke Bell, Naomi Norwid, Virginia Stokes, and Jacquelyn Wall in preparing the systematic literature review presented in this article.

Compliance with Ethical Standards

Conflict of Interest

Todd D. Little owns and receives remuneration from Yhat Enterprises (yhatenterprises.com), which runs educational workshops such as Stats Camp (statscamp.org), and processes his royalties and his fees for consulting on statistics and methods with life science researchers.

Ethical Approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.

Informed Consent

Informed consent was obtained from all individual participants included in the study.

Funding

This study was supported by grant NSF 1053160 (Wei Wu and Todd D. Little, co-PIs) and by the Institute for Measurement, Methodology, Analysis, and Policy (Todd D. Little, Director) at Texas Tech University.

References

  1. Allison, P. D. (2002). Missing data. Thousand Oaks, CA: Sage Publications.CrossRefGoogle Scholar
  2. Anderson, T. W. (1957). Maximum likelihood estimates for a multivariate normal distribution when some observations are missing. Journal of the American Statistical Association, 52, 200–203. doi: 10.1080/01621459.1957.10501379.CrossRefGoogle Scholar
  3. Andridge, R. R., & Little, R. J. A. (2010). A review of hot deck imputation for survey non-response. International Statistical Review, 78, 40–64. doi: 10.1111/j.1751-5823.2010.00103.x.CrossRefPubMedPubMedCentralGoogle Scholar
  4. Arbuckle, J. L. (1996). Full information estimation in the presence of incomplete data. In G. A. Marcoulides & R. E. Schumacker (Eds.), Advanced structural equation modeling (pp. 243–277). Mahwah, NJ: Lawrence Erlbaum Associates, Inc.Google Scholar
  5. Bodner, T. E. (2006). Missing data: prevalence and reporting practices. Psychological Reports, 99, 675–680. doi: 10.2466/PR0.99.7.675-680.CrossRefPubMedGoogle Scholar
  6. Carpenter, J. R., & Kenward, M. G. (2013). Multiple imputation and its application. Chichester, West Sussex: Wiley.Google Scholar
  7. Collins, L. M., Schafer, J. L., & Kam, C. M. (2001). A comparison of inclusive and restrictive strategies in modern missing data procedures. Psychological Methods, 6, 330–351. doi: 10.1037//1082-989X.6.4.330.CrossRefPubMedGoogle Scholar
  8. Diggle, P., & Kenward, M. G. (1994). Informative dropout in longitudinal data analysis (with discussion). Applied Statistics, 43, 49–94.CrossRefGoogle Scholar
  9. Enders, C. K. (2001). The performance of the full information maximum likelihood estimator in multiple regression models with missing data. Educational and Psychological Measurement, 61, 713–740. doi: 10.1177/00131640121971482.CrossRefGoogle Scholar
  10. Enders, C. K. (2010). Applied missing data analysis. New York: Guilford.Google Scholar
  11. Enders, C. K., & Bandalos, D. L. (2001). The relative performance of full information maximum likelihood estimation for missing data in structural equation models. Structural Equation Modeling, 8, 430–457. doi: 10.1207/S15328007SEM0803_5.CrossRefGoogle Scholar
  12. Goldstein, H., Carpenter, J., Kenward, M. G., & Levin, K. A. (2009). Multilevel models with multivariate mixed response types. Statistical Modelling., 9, 173–197. doi: 10.1177/1471082X0800900301.CrossRefGoogle Scholar
  13. Goldstein, H., Carpenter, J., & Browne, W. J. (2014). Fitting multilevel multivariate models with missing data in responses and covariates that may include interactions and non-linear terms. Journal of the Royal Statistical Society: Series A (Statistics in Society), 177, 553–564. doi: 10.1111/rssa.12022.CrossRefGoogle Scholar
  14. Graham, J. W. (2003). Adding missing-data-relevant variables to FIML-based structural equation models. Structural Equation Modeling, 10, 80–100. doi: 10.1207/S15328007SEM1001_4.CrossRefGoogle Scholar
  15. Graham, J. (2012). Missing data: analysis and design. New York: Springer.CrossRefGoogle Scholar
  16. Graham, J. W., Olchowski, A. E., & Gilreath, T. D. (2007). How many imputations are really needed? Some practical clarifications of multiple imputation theory. Prevention Science, 8, 206–213. doi: 10.1007/s11121-007-0070-9.CrossRefPubMedGoogle Scholar
  17. Heckman, J. (1976). The common structure of statistical models of truncation, sample selection and limited dependent variables and a simple estimator for such models. The Annals of Economic and Social Measurement, 5, 475–492.Google Scholar
  18. Heckman, J. (1979). Sample selection bias as a specification error. Econometrica, 47, 153–161. doi: 10.2307/1912352.CrossRefGoogle Scholar
  19. Honaker, J., & King, G. (2010). What to do about missing values in time-series cross-section data. American Journal of Political Science, 54, 561–581. doi: 10.1111/j.1540-5907.2010.00447.x.CrossRefGoogle Scholar
  20. Honaker, J., King, G., & Blackwell, M. (2011). Amelia II: a program for missing data. Journal of Statistical Software, 45, 1–47.CrossRefGoogle Scholar
  21. Howard, W., Rhemtulla, M., & Little, T. D. (2015). Using principal components as auxiliary variables in missing data estimation. Multivariate Behavioral Research, 50, 285–299. doi: 10.1080/00273171.2014.999267.CrossRefPubMedGoogle Scholar
  22. Little, R. J. A. (1993). Pattern-mixture models for multivariate incomplete data. Journal of the American Statistical Association, 88, 125–134. doi: 10.2307/2290705.Google Scholar
  23. Little, R. J. A. (1995). Modeling the drop-out mechanism in repeated-measures studies. Journal of the American Statistical Association, 90, 1112–1121. doi: 10.1080/01621459.1995.10476615.CrossRefGoogle Scholar
  24. Little, R. J. A., & Rubin, D. B. (2002). Statistical analysis with missing data. Hoboken, NJ: John Wiley & Sons.CrossRefGoogle Scholar
  25. Little, R. J. A., & Yau, L. (1996). Intent-to-treat analysis for longitudinal studies with drop-outs. Biometrics, 52, 1324–1333. doi: 10.2307/2532847.CrossRefPubMedGoogle Scholar
  26. Little, T. D., Jorgensen, T. D., Lang, K. M., & Moore, E. W. G. (2014). On the joys of missing data. Journal of Pediatric Psychology, 39, 151–162. doi: 10.1093/jpepsy/jst048.CrossRefPubMedGoogle Scholar
  27. Little, T. D., Lang, K. M., Wu, W., & Rhemtulla, M. (2016). Missing data. In D. Cicchetti (Ed.), Developmental Psychopathology: Vol. 1. Theory and method (3rd ed., pp. 760–796). New York: Wiley.Google Scholar
  28. Liu, M., Taylor, J. M. G., & Belin, T. R. (2000). Multiple imputation and posterior simulation for multivariate missing data in longitudinal studies. Biometrics, 56, 1157–1163. doi: 10.1111/j.0006-341X.2000.01157.x.CrossRefPubMedGoogle Scholar
  29. Peugh, J. L., & Enders, C. K. (2004). Missing data in educational research: a review of reporting practices and suggestions for improvement. Review of Educational Research, 74, 525–556. doi: 10.3102/00346543074004525.CrossRefGoogle Scholar
  30. Raghunathan, T. E., Lepkowski, J. M., Van Hoewyk, J., & Solenberger, P. (2001). A multivariate technique for multiply imputing missing values using a sequence of regression models. Survey Methodology, 27, 85–96.Google Scholar
  31. Rubin, D. B. (1978). Multiple imputations in sample surveys—a phenomenological Bayesian approach to nonresponse (Proceedings of the Survey Research Methods Section of the American Statistical Association, pp. 30–34).Google Scholar
  32. Rubin, D. B. (1987). Multiple imputation for nonresponse in surveys. New York: Wiley.CrossRefGoogle Scholar
  33. Rubin, D. B. (1996). Multiple imputation after 18+ years. Journal of the American Statistical Association, 91, 473–489. doi: 10.2307/2291635.CrossRefGoogle Scholar
  34. Savalei, V., & Rhemtulla, M. (2012). On obtaining estimates of the fraction of missing information from full information maximum likelihood. Structural Equation Modeling, 19, 477–494. doi: 10.1080/10705511.2012.687669.CrossRefGoogle Scholar
  35. Schafer, J. L. (1997). Analysis of incomplete multivariate data. New York: Chapman Hall.CrossRefGoogle Scholar
  36. Schafer, J. L., & Yucel, R. M. (2002). Computational strategies for multivariate linear mixed-effects models with missing values. Journal of Computational and Graphical Statistics., 11, 437–457. doi: 10.1198/106186002760180608.CrossRefGoogle Scholar
  37. van Buuren, S. (2011). Multiple imputation of multilevel data. In J. Hox & J. Roberts (Eds.), Handbook of advanced multilevel analysis (pp. 173–196). Milton Park, UK: Routledge.Google Scholar
  38. van Buuren, S. (2012). Flexible imputation of missing data. Boca Raton, FL: CRC Press.CrossRefGoogle Scholar
  39. van Buuren, S., & Groothuis-Oudshoorn, K. (2011). mice: multivariate imputation by chained equations in R. Journal of Statistical Software, 45, 1–67.CrossRefGoogle Scholar
  40. van Buuren, S., Brand, J. P. L., Groothuis-Oudshoorn, C. G. M., & Rubin, D. B. (2006). Fully conditional specification in multivariate imputation. Journal of Statistical Computation and Simulation, 76, 1049–1064. doi: 10.1080/10629360600810434.CrossRefGoogle Scholar
  41. von Hippel, P. T. (2007). Regression with missing Ys: an improved strategy for analyzing multiply imputed data. Sociological Methodology, 37, 83–117. doi: 10.1111/j.1467-9531.2007.00180.x.CrossRefGoogle Scholar
  42. von Hippel, P. T. (2009). How to impute interactions, squares, and other transformed variables. Sociological Methodology, 39, 265–291. doi: 10.1111/j.1467-9531.2009.01215.x.CrossRefGoogle Scholar
  43. Wilkinson, L., & Task Force on Statistical Inference. (1999). Statistical methods in psychology journals: guidelines and explanations. American Psychologist, 54, 594–604. doi: 10.1037//0003-066X.54.8.594.CrossRefGoogle Scholar
  44. Wu, W., Jia, F., & Enders, C. K. (2015). A comparison of imputation strategies for ordinal missing data on Likert scale variables. Multivariate Behavioral Research, 50, 484–503. doi: 10.1080/00273171.2015.1022644.CrossRefPubMedGoogle Scholar
  45. Yucel, R. M. (2008). Multiple imputation inference for multivariate multilevel continuous data with ignorable non-response. Philosophical Transactions of the Royal Society A, 366, 2389–2403. doi: 10.1098/rsta.2008.0038.CrossRefGoogle Scholar
  46. Zhao, J. H., & Schafer, J. L. (2013). pan: multiple imputation for multivariate panel or clustered data (Version 0.9) [R Package].Google Scholar
  47. Zhao, E., & Yucel, R. M. (2009). Performance of sequential imputation method in multilevel applications. In the Proceedings of the American Statistical Association Survey Research Methods Section (pp. 2800–2810).Google Scholar

Copyright information

© Society for Prevention Research 2016

Authors and Affiliations

  1. 1.Institute for Measurement, Methodology, Analysis, and PolicyTexas Tech UniversityLubbockUSA

Personalised recommendations