ML Versus MI for Missing Data With Violation of Distribution Conditions
Open accessThe DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
Normal-distribution-based maximum likelihood (ML) and multiple imputation (MI) are the two major procedures for missing data analysis. This article compares the two procedures with respects to bias and efficiency of parameter estimates. It also compares formula-based standard errors (SEs) for each procedure against the corresponding empirical SEs. The results indicate that parameter estimates by MI tend to be less efficient than those by ML; and the estimates of variance -covariance parameters by MI are also more biased. In particular, when the population for the observed variables possesses heavy tails, estimates of variance -covariance parameters by MI may contain severe bias even at relative large sample sizes. Although performing a lot better, ML parameter estimates may also contain substantial bias at smaller sample sizes. The results also indicate that, when the underlying population is close to normally distributed, SEs based on the sandwich-type covariance matrix and those based on the observed information matrix are very comparable to empirical SEs with either ML or MI. When the underlying distribution has heavier tails, SEs based on the sandwich-type covariance matrix for ML estimates are more reliable than those based on the observed information matrix. Both empirical results and analysis show that neither SEs based on the observed information matrix nor those based on the sandwich-type covariance matrix can provide consistent SEs in MI. Thus, ML is preferable to MI in practice, although parameter estimates by MI might still be consistent.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
RUBIN, D. B. (1976) · Biometrika · doi:10.1093/biomet/63.3.581 · Cited by 9,925
Statistical Analysis with Missing Data
Little, R. J. A., & Rubin, D. B. (2002) · Wiley Series in Probability and Statistics · doi:10.1002/9781119013563 · Cited by 8,473
Analysis of Incomplete Multivariate Data
Schafer, J. L. (1997) · doi:10.1201/9781439821862 · Cited by 6,012 · cited 4×
“50) of Schafer (1997). 8.”
BackgroundMethodInfluentialHow Many Imputations are Really Needed? Some Practical Clarifications of Multiple Imputation Theory
Graham, J. W., Olchowski, A. E., & Gilreath, T. D. (2007) · Prevention Science · doi:10.1007/s11121-007-0070-9 · Cited by 2,795 · cited 1×
“These are well within the range of the skewness and kurtosis of a real data set as reported in table 2 of Graham and Schafer (1999). The population skewness and kurtosis of y1 are (0, 0) when z1;N (0, 1), (2:939, 18:507) when z1;LNs(0, 1=2), and (0, 1:200) when z1;Us(0, 1).”
BackgroundA 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
Analyzing Incomplete Political Science Data: An Alternative Algorithm for Multiple Imputation
King, G., Honaker, J., Joseph, A., & Scheve, K. (2001) · American Political Science Review · doi:10.1017/s0003055401000235 · Cited by 1,834 · cited 1×
“Nowadays, ML and MI are the recommended procedures in essentially all areas of data analysis with missing values (e.g., Allison 2000, 2003; Buhi, Goodson, and Neilands 2008; Choi et al. 2005; Croy and Novins, 2005; Jamshidian and Bentler 1999; Kenward and Carpenter 2007; King et al. 2001; Lee and Song 2007; Olinsky, C…”
BackgroundA Suggestion for Using Powerful and Informative Tests of Normality
D'agostino, R. B., Belanger, A., & D'agostino, R. B. (1990) · The American Statistician · doi:10.2307/2684359 · Cited by 1,809
Multiple Imputation for Multivariate Missing-Data Problems: A Data Analyst's Perspective
Schafer, J. L., & Olsen, M. K. (1998) · Multivariate Behavioral Research · doi:10.1207/s15327906mbr3304_5 · Cited by 1,518
4. Regression with Missing Ys: An Improved Strategy for Analyzing Multiply Imputed Data
von Hippel, P. T. (2007) · Sociological Methodology · doi:10.1111/j.1467-9531.2007.00180.x · Cited by 1,495
Cited by
Cheung, M. W.-L. (2014) · Psychological Methods · doi:10.1037/a0032968 · Cited by 1,342
Moshagen, M., Hilbig, B. E., & Zettler, I. (2018) · Psychological Review · doi:10.1037/rev0000111 · Cited by 519
Robitzsch, A. (2020) · Frontiers in Education · doi:10.3389/feduc.2020.589965 · Cited by 379
Ullman, J. B., & Bentler, P. M. (2012) · Handbook of Psychology, Second Edition · doi:10.1002/9781118133880.hop202023 · Cited by 330
Self-citationGoldsmith, L. P., Lewis, S. W., Dunn, G., & Bentall, R. P. (2015) · Psychological Medicine · doi:10.1017/s003329171500032x · Cited by 174
Metadata
- Authors
- Yuan, K.-H., Yang-Wallentin, F., & Bentler, P. M.
- Venue
- Sociological Methods & Research
- Publisher
- SAGE Publications
- Published
- 2012-10-24
- Volume
- 41
- Issue
- 4
- Pages
- 598-629
- ISSN
- 0049-1241 (ISSN-L)
- 1552-8294
- OpenAlex
- W2162204499
- Cited by
- 103
- References
- 9
- FWCI
- 6.59
- Type
- journal article
- Language
- en
- Open access
- green
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: ML Versus MI for Missing Data With Violation of Distribution Conditions. https://app.cochat.ai/papers/10.1177/0049124112460373
- The paper
- Yuan, K.-H., Yang-Wallentin, F., & Bentler, P. M. (2012). ML Versus MI for Missing Data With Violation of Distribution Conditions. Sociological Methods & Research. https://doi.org/10.1177/0049124112460373
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.