Multiple Imputation Under Violated Distributional Assumptions: A Systematic Evaluation of the Assumed Robustness of Predictive Mean Matching
Abstract
Predictive mean matching (PMM) is a standard technique for the imputation of incomplete continuous data. PMM imputes an actual observed value, whose predicted value is among a set of k ≥ 1 values (the so-called donor pool), which are closest to the one predicted for the missing case. PMM is usually better able to preserve the original distribution of the empirical data than fully parametric multiple imputation (MI) approaches, when empirical data deviate from their distributional assumptions. Use of PMM is therefore especially worthwhile in situations where model assumptions of fully parametric MI procedures are violated and where fully parametric procedures would yield highly implausible estimates. Unfortunately, today there are only a handful of studies that systematically tested the robustness of PMM and it is still widely unknown where exactly the limits of this procedure lie. I examined the performance of PMM in situations where data were skewed to varying degrees, under different sample sizes, missing data percentages, and using different settings of the PMM approach. It was found that small donor pools overall yielded better results than large donor pools and that PMM generally worked well, unless data were highly skewed and more than about 20% to 30% of the data had to be imputed. Also, PMM generally performed better when sample size was sufficiently large.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Missing data were imputed using predictive mean matching (PMM).
“we imputed missing data using the predictive mean matching (PMM) method [57, 58] as simulation results showed that the PMM method worked well across a wide range of missing data situations [59].”
From The psychometric properties of the Vietnamese Version of the Five Facet Mindfulness Questionnaire (2022) · cites this paper as [59]
Cites
Multiple Imputation for Nonresponse in Surveys
Rubin, D. B. (1987) · Wiley Series in Probability and Statistics · doi:10.1002/9780470316696 · Cited by 20,701 · see citing works
<b>mice</b>: Multivariate Imputation by Chained Equations in<i>R</i>
Buuren, S. V., & Groothuis-Oudshoorn, K. (2011) · Journal of Statistical Software · doi:10.18637/jss.v045.i03 · Cited by 13,870 · see citing works
Missing data: our view of the state of the art
Schafer, J. L., & Graham, J. W. (2002) · Psychological Methods · doi:10.1037/1082-989x.7.2.147 · Cited by 11,638 · see citing works
RUBIN, D. B. (1976) · Biometrika · doi:10.1093/biomet/63.3.581 · Cited by 9,925 · see citing works
Missing data analysis: making it work in the real world
Graham, J. W. (2009) · Annual Review of Psychology · doi:10.1146/annurev.psych.58.110405.085530 · Cited by 6,163 · see citing works
Analysis of Incomplete Multivariate Data
Schafer, J. L. (1997) · doi:10.1201/9781439821862 · Cited by 6,012 · see citing works
Enders, C., & Bandalos, D. (2001) · Structural Equation Modeling: A Multidisciplinary Journal · doi:10.1207/s15328007sem0803_5 · Cited by 4,978 · see citing works
Journal of Statistical Software
de Leeuw, J. (2009) · Wiley Interdisciplinary Reviews Computational Statistics · doi:10.1002/wics.10 · Cited by 3,608 · see citing works
Scandinavian Journal of Statistics
Rosén, B. G. (2005) · Encyclopedia of Statistical Sciences · doi:10.1002/0471667196.ess2351.pub2 · Cited by 3,608 · see citing works
A tutorial on pilot studies: the what, why and how
Thabane, L., Ma, J., Chu, R., Cheng, J., Ismaila, A., Rios, L. P., Robson, R., Thabane, M., Giangregorio, L., & Goldsmith, C. H. (2010) · BMC Medical Research Methodology · doi:10.1186/1471-2288-10-1 · Cited by 3,384 · see citing works
A comparison of inclusive and restrictive strategies in modern missing data procedures.
Collins, L. M., Schafer, J. L., & Kam, C.-M. (2001) · Psychological Methods · doi:10.1037/1082-989x.6.4.330 · Cited by 2,389 · see citing works
Statistical Analysis with Missing Data.
Chatfield, C., Little, R. J. A., & Rubin, D. B. (1988) · Journal of the Royal Statistical Society Series A (Statistics in Society) · doi:10.2307/2982783 · Cited by 2,203 · see citing works
Flexible Imputation of Missing Data
van Buuren, S. (2012) · doi:10.1201/b11826 · Cited by 2,022 · see citing works
A multivariate technique for multiply imputing missing values using a sequence of regression models
Raghunathan, T. E., Lepkowski, J. M., Hoewyk, J. V., & Solenberger, P. W. (2001) · Survey methodology · Cited by 1,981 · see citing works
Analysis of Semiparametric Regression Models for Repeated Outcomes in the Presence of Missing Data
Robins, J. M., Rotnitzky, A. G., & Zhao, L. P. (1995) · Journal of the American Statistical Association · doi:10.1080/01621459.1995.10476493 · Cited by 1,574 · see citing works
Fully conditional specification in multivariate imputation
Van Buuren, S., Brand, J. P. L., Groothuis-Oudshoorn, C. G. M., & Rubin, D. B. (2006) · Journal of Statistical Computation and Simulation · doi:10.1080/10629360600810434 · Cited by 1,217 · see citing works
Rubin, D. B. (1981) · The Annals of Statistics · doi:10.1214/aos/1176345338 · Cited by 1,178 · see citing works
Missing-Data Adjustments in Large Surveys
Little, R. J. A. (1988) · Journal of Business and Economic Statistics · doi:10.1080/07350015.1988.10509663 · Cited by 1,109 · see citing works
A Review of Hot Deck Imputation for Survey Non‐response
Andridge, R., & Little, R. J. A. (2010) · International Statistical Review · doi:10.1111/j.1751-5823.2010.00103.x · Cited by 1,073 · see citing works
A Primer on Maximum Likelihood Algorithms Available for Use With Missing Data
Enders, C. K. (2001) · Structural Equation Modeling: A Multidisciplinary Journal · doi:10.1207/s15328007sem0801_7 · Cited by 1,027 · see citing works
Semiparametric Efficiency in Multivariate Regression Models with Missing Data
Robins, J. M., & Rotnitzky, A. G. (1995) · Journal of the American Statistical Association · doi:10.1080/01621459.1995.10476494 · Cited by 888 · see citing works
Miscellanea. Small-sample degrees of freedom with multiple imputation
Barnard, J. (1999) · Biometrika · doi:10.1093/biomet/86.4.948 · Cited by 841 · see citing works
Enders, C. K. (2001) · Educational and Psychological Measurement · doi:10.1177/0013164401615001 · Cited by 816 · see citing works
Multiple Imputation for Interval Estimation From Simple Random Samples With Ignorable Nonresponse
Rubin, D. B., & Nathaniel Schenker, A. (1986) · Journal of the American Statistical Association · doi:10.1080/01621459.1986.10478280 · Cited by 768 · see citing works
Handbook of Advanced Multilevel Analysis
Hox, J. J., & Roberts, J. (2011) · Routledge eBooks · doi:10.4324/9780203848852 · Cited by 751 · see citing works
What Improves with Increased Missing Data Imputations?
Bodner, T. E. (2008) · Structural Equation Modeling A Multidisciplinary Journal · doi:10.1080/10705510802339072 · Cited by 695 · see citing works
Methods for Handling Missing Data
Graham, J. A., Cumsille, P. E., & Elek, E. (2003) · Handbook of Psychology · doi:10.1002/0471264385.wei0204 · Cited by 658 · see citing works
Tuning multiple imputation by predictive mean matching and local residual draws
Morris, T. P., White, I. R., & Royston, P. (2014) · BMC Medical Research Methodology · doi:10.1186/1471-2288-14-75 · Cited by 568 · see citing works
Missing Data, Imputation, and the Bootstrap
Efron, B. (1994) · Journal of the American Statistical Association · doi:10.1080/01621459.1994.10476768 · Cited by 471 · see citing works
Partially parametric techniques for multiple imputation
Nathaniel Schenker, A., & Taylor, J. M. G. (1996) · Computational Statistics & Data Analysis · doi:10.1016/0167-9473(95)00057-7 · Cited by 335 · see citing works
Predictive mean matching imputation of semicontinuous variables
Vink, G., Frank, L. E., Pannekoek, J., & van Buuren, S. (2014) · Statistica Neerlandica · doi:10.1111/stan.12023 · Cited by 178 · see citing works
Evaluation of software for multiple imputation of semi-continuous data
Yu, L.-M., Burton, A., & Rivero-Arias, O. (2007) · Statistical Methods in Medical Research · doi:10.1177/0962280206074464 · Cited by 117 · see citing works
Multiple imputation using an iterative hot‐deck with distance‐based donor selection
Siddique, J., & Belin, T. R. (2007) · Statistics in Medicine · doi:10.1002/sim.3001 · Cited by 93 · see citing works
Multiple Imputation of Multilevel Missing Data—Rigor Versus Simplicity
Drechsler, J. (2015) · Journal of Educational and Behavioral Statistics · doi:10.3102/1076998614563393 · Cited by 79 · see citing works
Efficient ways to impute incomplete panel data
Kleinke, K., Stemmler, M., Reinecke, J., & Lösel, F. A. (2011) · AStA Advances in Statistical Analysis · doi:10.1007/s10182-011-0179-9 · Cited by 33 · see citing works
Self-citationSemi-parametric estimation of models for the means and covariances in the presence of missing data
Robins, J. M., & Rotnitzky, A. G. (1995) · Scandinavian Journal of Statistics · Cited by 24 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Khelfaoui, I., Xie, Y., Hafeez, M., Ahmed, D., Degha, H. E., & Meskher, H. (2022) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph19127338 · Cited by 24 · see citing works
The psychometric properties of the Vietnamese Version of the Five Facet Mindfulness Questionnaire
Nguyen, H. T. M., Nguyen, H. V., & Bui, T. T. H. (2022) · BMC Psychology · doi:10.1186/s40359-022-01003-3 · Cited by 6 · see citing works
“For each study sample, we imputed missing data using the predictive mean matching (PMM) method [57, 58] as simulation results showed that the PMM method worked well across a wide range of missing data situations [59].”
MethodVolkert, J., Taubner, S., Berning, A., Kling, L., Wießner, H., Georg, A. K., & Holl, J. (2021) · Frontiers in Psychology · doi:10.3389/fpsyg.2021.720104 · Cited by 6 · see citing works
- Authors
- Kleinke, K.
- Affiliations
- FernUniversität in Hagen (DE)
- Corresponding author
- Kleinke, Kristian
- ORCID
- Kleinke, Kristian
- Venue
- Journal of Educational and Behavioral Statistics
- Published
- 2017-01-24
- Volume
- 42
- Issue
- 4
- Pages
- 371-404
- ISSN
- 1076-9986 (ISSN-L)
- 1935-1054
- OpenAlex
- W2606442136
- Cited by
- 148
- References
- 36
- Citations by year
- 2026: 8 · 2025: 29 · 2024: 20 · 2023: 26 · 2022: 22 · 2021: 18 · 2020: 14 · 2019: 5 · 2018: 4 · 2017: 1 · 2012: 1
- FWCI
- 4.58
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Journal of Educational and Behavioral Statistics (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- PUB – Publications at Bielefeld University (Bielefeld University) (submittedVersion)
- Publikationen an der Universität Bielefeld (Universität Bielefeld) (submittedVersion)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Applications
- Keywords
- predictive mean matching, multiple imputation, missing data, robustness, skewed data, sample size effects, distributional assumptions
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
