On Structural Equation Modeling with Data that are not Missing Completely at Random
The DOI matches its Crossref record; 44 of the 45 references it cites were found in a registry or an index.
Abstract
A general latent variable model is given which includes the specification of a missing data mechanism. This framework allows for an elucidating discussion of existing general multivariate theory bearing on maximum likelihood estimation with missing data. Here, missing completely at random is not a prerequisite for unbiased estimation in large samples, as when using the traditional listwise or pairwise present data approaches. The theory is connected with old and new results in the area of selection and factorial invariance. It is pointed out that in many applications, maximum likelihood estimation with missing data may be carried out by existing structural equation modeling software, such as LISREL and LISCOMP. Several sets of artifical data are generated within the general model framework. The proposed estimator is compared to the two traditional ones and found superior.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
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?
In the citing paper
“The mean values of the skewness and kurtosis were smaller than the prescribed levels (skewness, 2.0 and kurtosis, 7.0), indicating no significant problems regarding multivariate normality of the data [35].”
From The Mediating Role of Generative AI Self-Regulation on Students’ Critical Thinking and Problem-Solving (2024) · cites this paper as [35]
Citations
Cites
Maximum Likelihood from Incomplete Data Via the EM Algorithm
Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1977.tb01600.x · Cited by 50,444
Statistical Analysis With Missing Data
Lahiff, M., Little, R. J. A., & Rubin, D. B. (1989) · Journal of the American Statistical Association · doi:10.2307/2289883 · Cited by 17,265
RUBIN, D. B. (1976) · Biometrika · doi:10.1093/biomet/63.3.581 · Cited by 9,925
Journal of The American Statistical Association
Fienberg, S. E. (2005) · Encyclopedia of Statistical Sciences · doi:10.1002/0471667196.ess1317 · Cited by 6,125
BMDP Statistical Software 1981.
Bubolz, T. A., & Dixon, W. J. (1984) · Journal of the American Statistical Association · doi:10.2307/2288308 · Cited by 5,221
(1976) · Annals of Economic and Social Measurement · Cited by 5,035
Assessing Reliability and Stability in Panel Models
Wheaton, B., Muthen, B., Alwin, D. F., & Summers, G. F. (1977) · Sociological Methodology · doi:10.2307/270754 · Cited by 3,116
Self-citationA General Approach to Confirmatory Maximum Likelihood Factor Analysis
Jöreskog, K. G. (1969) · Psychometrika · doi:10.1007/bf02289343 · Cited by 2,489
Marginal Maximum Likelihood Estimation of Item Parameters: Application of an EM Algorithm
Bock, R. D., & Aitkin, M. (1981) · Psychometrika · doi:10.1007/bf02293801 · Cited by 2,339
Quasi-likelihood functions, generalized linear models, and the Gauss—Newton method
WEDDERBURN, R. W. M. (1974) · Biometrika · doi:10.1093/biomet/61.3.439 · Cited by 2,122 · cited 2×
“In terms of the Wheaton et al. (1977) example, an increased value of any of the socioeconomic background indicators is taken to yield an increased propensity not to attrit (a high s* value), while an increased value of the time one alienation indicators is taken to yield a decreased propensity not to attrit (i.”
BackgroundMethod
Research works printed but not linked: 5
- Little, 1983, Incomplete data in sample surveys, Vol. 2: Theory and bibliographies
- Dixon, 1983, BMDP Statistical Software
- Olsson, 1978, Selection bias in confirmatory factor analysis
- Marini, 1980, Sociological Methodology
- Lawley, 1943, A note on Karl Pearson's selection formulae, Proceedings of the Royal Society Edinburgh, Section A (Mathematics and Physics Section), 62, 28
Cited by
Items 601–700 of 881
Pahl, K., Capasso, A., Lekas, H., Lee, J. Y., Winters, J., & Pérez‐Figueroa, R. (2020) · Journal of Behavioral Medicine · doi:10.1007/s10865-020-00184-9 · Cited by 8
Immigrant groups, vocational training, and employment
Kvist, A. V. (2012) · European journal of training and development · doi:10.1108/03090591211263530 · Cited by 12
“Applicants for different courses took different combinations of tests, resulting in a pattern of missing data, which was handled using missing data modeling (Muthén et al., 1987).”
MethodZhang, W. (2008) · Structural Equation Modeling A Multidisciplinary Journal · doi:10.1080/10705510801922555 · Cited by 9
“gif"/> with population value β, relative bias is computed in the following way: Relative bias in excess of 10% is considered significant in covariance structure analysis ( Kaplan, 1988 ; Muthen, Kaplan, & Hollis, 1987 ).”
MethodA Study of Missing Data Imputation and Predictive Modeling of Strength Properties of Wood Composites
Zeng, Y. (2011) · Cited by 7
REICHER, S. D. (1996) · European Journal of Social Psychology · doi:10.1002/(sici)1099-0992(199601)26:1<115::aid-ejsp740>3.0.co;2-z · Cited by 373
Hoy, E. Q. W., & Oh, V. Y. S. (2024) · Journal of Social and Personal Relationships · doi:10.1177/02654075241276713 · Cited by 12
“…structural equation modelling with full-information maximum likelihood (FIML), which provides the gold standard approach for handling missing data that outperforms listwise deletion even under conditions where data is missing not at random (MNAR; Enders & Bandalos, 2001; Muth´en et al., 1987).”
Analyzing Structural Equation Models with Missing Data
Enders, C. K. (2013) · Emerald Group Publishing Limited eBooks · doi:10.1108/978-1-62396-246-320251016 · Cited by 55
Li, H., Lam, S. M., Zhang, X., & Bao, M. (2024) · Learning and Individual Differences · doi:10.1016/j.lindif.2024.102489 · Cited by 11
Wang, W., Shen, X., Guo, X., Liu, S., Chen, Q., Ma, S., & Jian, Y. (2025) · Journal of Pacific Rim Psychology · doi:10.1177/18344909241310783 · Cited by 10
“Lastly, the Average Relative Parameter Bias (ARPB) assesses the accuracy of parameter estimates in the bifactor model, with values below 10 – 15% generally considered acceptable, indicating minimal bias (Muthén et al., 1987).”
A novel item-allocation procedure for the three-form planned missing data design
Lang, K. M., Moore, E. W. G., & Grandfield, E. M. (2020) · MethodsX · doi:10.1016/j.mex.2020.100941 · Cited by 6
“Absolute values of PRB larger than 10 are often viewed as indicative of “unacceptable” levels of bias [18] .”
BackgroundFitzpatrick, C., Archambault, I., Barnett, T. A., & Pagani, L. S. (2020) · South African Journal of Childhood Education · doi:10.4102/sajce.v10i1.803 · Cited by 8
“Parameters were obtained by maximum likelihood estimation using an expectation maximisation algorithm (Muthén et al. 1987).”
MethodSchweizer, T. H., Snyder, H. R., Young, J. F., & Hankin, B. L. (2021) · Research on Child and Adolescent Psychopathology · doi:10.1007/s10802-021-00839-4 · Cited by 8
Three Sample Estimates of Fraction of Missing Information From Full Information Maximum Likelihood
Chen, L., & Savalei, V. (2021) · Frontiers in Psychology · doi:10.3389/fpsyg.2021.667802 · Cited by 6
“In the past decade or so, modern missing data techniques with better statistical properties, such as full information maximum likelihood (FIML; Allison, 1987; Muthén et al., 1987; Arbuckle, 1996) and multiple imputation (MI; Rubin, 1987), have become increasingly accessible via computer programs like lavaan (Rosseel,…”
BackgroundChesnut, R. P., Richardson, C. B., Morgan, N. R., Bleser, J. A., McCarthy, K. J., & Perkins, D. F. (2022) · Journal of Religion and Health · doi:10.1007/s10943-022-01606-5 · Cited by 9
Investigating associations between parent engagement and toddlers' mathematics performance
Silver, A. M., Swirbul, M. S., Tamis‐LeMonda, C. S., Cabrera, N., & Libertus, M. E. (2023) · British Journal of Developmental Psychology · doi:10.1111/bjdp.12459 · Cited by 7
Marques, C., Castilho, P., Pereira, A. T., Goss, K., Castelo-Branco, M. S., & Macedo, A. (2023) · Eating Disorders · doi:10.1080/10640266.2023.2259676 · Cited by 6
“Muthén et al. (1987) recommend that a maximum of 10–15% of ARPB is acceptable and indicates no significant bias if the items are forced into a unidimensional structure.”
BackgroundChen, L., Miočević, M., & Falk, C. F. (2024) · Structural Equation Modeling A Multidisciplinary Journal · doi:10.1080/10705511.2023.2300079 · Cited by 8
“A common missing data technique applied in SEM is full information maximum likelihood (FIML; Allison, 1987; Muth � en et al., 1987; Arbuckle, 1996), which is sometimes referred to as direct maximum likelihood.”
ADHD, Conduct Disorder, Substance Use Disorder, and Nonprescription Stimulant Use
Brook, J. S., Balka, E. B., Zhang, C., & Brook, D. W. (2014) · Journal of Attention Disorders · doi:10.1177/1087054714528535 · Cited by 7
Lemacks, J. L., Ilich, J. Z., Liu, P.-Y., Shin, H., Ralston, P. A., Cui, M., & Wickrama, K. A. S. (2015) · The journal of nutrition health & aging · doi:10.1007/s12603-015-0637-2 · Cited by 6
“However, the use of FIML to impute missing information is reputable and indicated to produce the least amount of bias compared to listwise and casewise deletion methods (58-60).”
Zhao, J., An, Y., Li, X. S., & Huang, J. (2021) · Child Psychiatry & Human Development · doi:10.1007/s10578-021-01278-4 · Cited by 8
“Thus, the full information maximum likelihood estimates (FIML) procedure, available in Mplus 7, was used to handle the missing data, which is an unbiased method for dealing with missing data compared to other methods [52, 53].”
MethodLongitudinal satisfaction measurement using latent growth curve models and extensions
Weismayer, C. (2010) · Journal of Retailing and Consumer Services · doi:10.1016/j.jretconser.2010.03.013 · Cited by 6
Mikkelsen, A., Øgaard, T., & Lovrich, N. P. (1997) · Review of Public Personnel Administration · doi:10.1177/0734371x9701700308 · Cited by 6
Metodproblem vid studier av Högskoleprovets prognosförmåga - och deras lösning!
Gustafsson, J., & Reuterberg, S. (2000) · Bulletin Monumental · Cited by 6
Wang, W. (2005) · Swinburne figshare (Swinburne University of Technology) · doi:10.25916/sut.26274829 · Cited by 9
Defining the p-Factor: An Empirical Test of Five Leading TheoriesPreprint
Southward, M. W., Cheavens, J. S., & Coccaro, E. F. (2022) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/bszt4 · Cited by 6
Issues in longitudinal research on motivation
Stoel, R. D., Roeleveld, J., Peetsma, T. T. D., van den Wittenboer, G. L. H., & Hox, J. J. (2005) · Learning and Individual Differences · doi:10.1016/j.lindif.2005.07.006 · Cited by 5
Sexual Empowerment Among Young Black Men Who Have Sex with Men
Choi, S. K., Boynton, M. H., Ennett, S. T., Muessig, K. E., Bauermeister, J. A., LeGrand, S., & Hightow‐Weidman, L. (2020) · The Journal of Sex Research · doi:10.1080/00224499.2020.1809614 · Cited by 6
“According to Muthén and colleagues, an average RPB less than 10–15% is acceptable and posed no serious concern in unidimensional models (Muthén et al., 1987).”
BackgroundKey processes and popular analyses in the SEM family of techniques
Schreiber, J. B. (2022) · Elsevier eBooks · doi:10.1016/b978-0-323-91888-6.00023-5 · Cited by 6
Morozov, M., & Boislard, M.-A. (2022) · The Canadian Journal of Human Sexuality · doi:10.3138/cjhs.2022-0022 · Cited by 10
Evaluating the dimensionality of L2 grit: A confirmatory bifactor model
Zhang, X., Zhang, S., & Xu, H. (2023) · System · doi:10.1016/j.system.2023.103144 · Cited by 6
Utilization of Mental Health Services by Minority Urban Adults: Psychosocial Predictors
Brook, J. S., Lee, J. Y., Balka, E. B., Finch, S. J., & Brook, D. W. (2014) · Journal of Urban Health · doi:10.1007/s11524-014-9878-3 · Cited by 7
Bayesian Estimation of the True Score Multitrait–Multimethod Model With a Split-Ballot Design
Helm, J. L., Castro‐Schilo, L., Zavala‐Rojas, D., DeCastellarnau, A., & Oravecz, Z. (2017) · Structural Equation Modeling A Multidisciplinary Journal · doi:10.1080/10705511.2017.1378103 · Cited by 5
Huber Inventory of Trainee Self‐efficacy: Assessment of measurement models
Lockwood, A. B., Gross, T. J., Farmer, R. L., & Loke, S. W. (2019) · Psychology in the Schools · doi:10.1002/pits.22230 · Cited by 6
Standardized estimates for latent interaction effects: Method comparison and selection strategy
Wen, Z., Ouyang, J., & Fang, J. (2021) · Acta Psychologica Sinica · doi:10.3724/sp.j.1041.2022.00091 · Cited by 6
“…法、LMS、无先验信息和有先验信息的贝叶斯法估 计的结果。 乘积指标法使用无均值结构的模型(Lin et al., 2010; Marsh et al., 2004; 吴艳 等, 2009), 采用配对 乘积指标 1 4 2 5 3 6, ,x x x x x x (Marsh et al., 2004), 并使 用固定负荷法指定测量单位。无论潜变量是何分 布 , 乘积指标都不是正态分布 , 在 Mplus 中指定 “ESTIMATOR=MLM”实现对参数估计的标准误和 模型卡方统计量的矫正(Satorra & Bentler, 1994)。 根据温忠麟等(2008, 也见 Wen et…”
Qiu, M., & Yuan, K. (2023) · Structural Equation Modeling A Multidisciplinary Journal · doi:10.1080/10705511.2023.2213842 · Cited by 7
“Muth (cid:1) en et al. (1987) provided a benchmark for assessing relative bias, suggesting that magnitudes of relative bias lower than 10% can be considered negligible.”
BackgroundTokar, D. M., Kaut, K. P., & Allen, P. A. (2023) · PLoS ONE · doi:10.1371/journal.pone.0287208 · Cited by 6
“ARPB values less than 10–15% indicate acceptable levels of parameter bias when modeling multidimensional data as unidimensional in SEM (Muthén, Kaplan, & Hollis, 1987 [47]; Rodriguez et al.”
MethodSIMULATION OF MULTINOMIAL PROBIT PROBABILITIES AND IMPUTATION OF MISSING DATA
Lavy, V., Palumbo, M. G., & Stern, S. N. (1999) · Advances in econometrics · doi:10.1108/s0731-9053(1999)0000013008 · Cited by 10
Illness self-management among adults living with ANCA small vessel vasculitis
Thorpe, C. T. (2006) · Carolina Digital Repository (University of North Carolina at Chapel Hill) · doi:10.17615/tn7r-zx93 · Cited by 6
Subject Attrition in Prevention Research
Biglan, A., Hood, D., Brozovsky, P., Ochs, L., Ary, D. V., & Black, C. (1997) · Substance Use & Misuse · doi:10.3109/10826089709035563 · Cited by 5
Hansen, K. Y., Rosén, M., & Gustafsson, J. (2006) · International Journal of Research & Method in Education · doi:10.1080/17437270600891721 · Cited by 5
“Mplus uses the available information to estimate a model based on the covariance matrix of each pattern of missing data, which can reduce the bias in factor score estimates caused by missingness (Muthen et al , 1987 ; Muthen & Muthen, 2004 ).”
MethodEstimation of the Correlation Coefficient Based on Selected Data
Hägglund, G., & Larsson, R. (2006) · Journal of Educational and Behavioral Statistics · doi:10.3102/10769986031004377 · Cited by 5
“In Muthén, Kaplan, and Hollis (1987) a method within the framework of structural equation modeling is proposed.”
MethodWilliams, C. J., Viken, R. J., & Rose, R. J. (1992) · Behavior Genetics · doi:10.1007/bf01067000 · Cited by 5
The Impact of Unmodeled Error Covariance on Measurement Models in Structural Equation Modeling
Bocell, F. D. (2015) · ResearchWorks at the University of Washington (University of Washington) · Cited by 14
Bai, Y., Di, M., Huo, Y., Wang, J., Xia, X., & Zhao, M. (2021) · Current Psychology · doi:10.1007/s12144-020-01243-9 · Cited by 6
Carter, S. R., Collins, J. C., Hu, J., O’Reilly, C. L., Wheeler, A., McMillan, S. S., & El‐Den, S. (2022) · International Journal of Mental Health and Addiction · doi:10.1007/s11469-022-00981-0 · Cited by 4
“When ARPB is less than 10–15%, bias is acceptable and poses no concern to the interpretation of the bifactor model (Muthén et al., 1987).”
Impact of missing data and ICC on full information maximum-likelihood estimation in multilevel SEMs
Niu, C. (2024) · Model Assisted Statistics and Applications · doi:10.3233/mas-231444 · Cited by 9
“Specifically, FIML estimates were less biased and more efficient, and yielded lowest model rejection rate and near-optimal Type 1 error rates than other methods (Arbuckle, 1996; Enders, 2001; Enders & Bandalos, 2001; Marsh, 1998; Muthén et al., 1987; Wothke, 2000).”
Sischka, P. E., Albert, I., & Kornadt, A. E. (2024) · Assessment · doi:10.1177/10731911241283609 · Cited by 6
“Substantial differences in the discrimination parameters (i.e., average relative bias above 15%; e.g., B. Muthe´n et al., 1987) may indicate that a unidimensional IRT model might lead to substantial parameter bias.”
Onorato, P. R., Rawana, J. S., & Flett, G. L. (2025) · Cognitive Therapy and Research · doi:10.1007/s10608-024-10566-x · Cited by 4
“…(FIML)—a frequently utilized estimation method when missing data is present (e.g., prefer not to answer responses in the current study)—to consider all data that is available in the analysis (e.g., Allison, 1987; Arbuckle, 1996; Duncan et al., 1998; Enders & Ban-dalos, 2001; Muthén et al., 1987).”
Fossum, M., Söderhamn, O., Cliffordson, C., & Söderhamn, U. (2012) · BMJ Open · doi:10.1136/bmjopen-2012-001575 · Cited by 4
Knowledge Transfer in Teams and Its Role for the Prevention of Knowledge Loss
Noethen, D. (2011) · Cited by 7
Tengelin, E., Cliffordson, C., Lyckhage, E. D., & Berndtsson, I. (2019) · Equality Diversity and Inclusion An International Journal · doi:10.1108/edi-10-2017-0222 · Cited by 5
Kwan, Y. H., Uy, E. J. B., Bautista, D. C., Xin, X., Xiao, Y., Lee, G. L., Subramaniam, M., Vaingankar, J. A., Chan, M. F., Kumar, N., et al. (2019) · PLoS ONE · doi:10.1371/journal.pone.0220293 · Cited by 9
The Performance of the Semigeneralized Partial Credit Model for Handling Item-Level Missingness
Zhou, S., & Huggins‐Manley, A. C. (2020) · Educational and Psychological Measurement · doi:10.1177/0013164420918392 · Cited by 5
“The maximum absolute value of bias was .28 when using the Semi-GPCM and all bias was in a confined range, which was consistent with the results shown in previous studies (e.g., B. Muthén et al., 1987; Reise & Yu, 1990).”
ResultEßer, F. J., Holtmann, J., & Eid, M. (2021) · Structural Equation Modeling A Multidisciplinary Journal · doi:10.1080/10705511.2021.1913594 · Cited by 4
“In line with B. O. Muthén et al. (1987) and other simulation studies on latent variable modeling (Holtmann et al., 2016; Muthén & Muthén, 2002; Ulitzsch et al., 2017), a cutoff value of 0.10 (10”
BackgroundInfluentialIncome moderates changes in big-five personality traits across eighteen years
Oh, V. Y. S., Ismail, I., & Tong, E. M. W. (2022) · European Journal of Personality · doi:10.1177/08902070221078479 · Cited by 10
“…likelihood (FIML) procedures, which are considered gold standard approaches to addressing missing data, and even under conditions when the data is missing not at random (MNAR), FIML procedures generally outperform listwise deletion (Enders & Bandalos, 2001; Ferro, 2014; Muthén et al., 1987).”
BackgroundKim, S. Y., Park, S. Y., Mathai, B. B., Daheim, J., France, C. R., & Delgado, B. (2022) · Journal of Clinical Psychology · doi:10.1002/jclp.23425 · Cited by 6
“Full information maximum likelihood estimation was implemented to handle missing values, which has been shown to produce less biased parameter estimates and standard errors compared to other missing value handling methods (listwise or pairwise deletion) under the MAR or MCAR patterns (Muthén et al., 1987).”
MethodWang, X., Yang, X., & Zhou, X. (2023) · International Journal of Clinical and Health Psychology · doi:10.1016/j.ijchp.2023.100366 · Cited by 5
Pocuca, N., Geoffroy, M., Paquin, S., Archambault, K., Séguin, J. R., Parent, S., Boivin, M., Tremblay, R. E., Côté, S. M., & Ryan, N. C. (2023) · Journal of Psychopathology and Clinical Science · doi:10.1037/abn0000816 · Cited by 6
Depression and Reciprocal Language Style Matching in Text Messages
Weinstein, M., & Jensen, M. R. (2023) · Journal of Language and Social Psychology · doi:10.1177/0261927x231163305 · Cited by 5
“FIML assumes that missing data are at least missing at random (MAR; Muthén et al., 1987), and works best with data that is MCAR.”
Baraldi, A. N., & Enders, C. K. (2020) · Cambridge University Press eBooks · doi:10.1017/9781316995808.040 · Cited by 4
De målrelaterade gymnasiebetygens prognosförmåga
Cliffordson, C. (2004) · Bulletin Monumental · Cited by 4
A Latent Variable Model with Non-Ignorable Missing Data
Hoshino, T. (2005) · Behaviormetrika · doi:10.2333/bhmk.32.71 · Cited by 4
“The MAR estimation by Muthén et al. (1987) is very attractive, but was not attempted here because each set of data had several missing patterns.”
MethodImages of aging are related to the plasticity of adult development
Bowen, C. E. (2011) · Cited by 4
Callow-Heusser, C. A. (2011) · Digital Commons - USU (Utah State University) · doi:10.26076/beac-9364 · Cited by 7
Culpepper, S. A. (2015) · Psychometrika · doi:10.1007/s11336-015-9466-9 · Cited by 4
Zorowitz, S., & Tuominen, L. J. (2022) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/uexgy · Cited by 4
Jamil, M. F. A. (2012) · Bradford Scholars (University of Bradford) · Cited by 19
Güilgüiruca, M., Quiñones, M., & Zúñiga, C. (2023) · Revista Iberoamericana de Diagnóstico y Evaluación - e Avaliação Psicológica · doi:10.21865/ridep70.4.03 · Cited by 11
Correcting bias in extreme groups design using a missing data approach.
Chen, L., & Fouladi, R. T. (2022) · Psychological Methods · doi:10.1037/met0000508 · Cited by 6
Linking a latent variable trait-state-occasion model of emotion regulation to cognitive control
Olatunji, B. O., Knowles, K. A., Adamis, A. M., & Cole, D. A. (2024) · Cognition & Emotion · doi:10.1080/02699931.2024.2332594 · Cited by 6
“Maximum likelihood estimation assumes only that the data are missing at random (not missing completely at random, like list-wise or pairwise deletion) and can yield robust estimates even when this assumption is violated (Little & Rubin, 1987; Muthén et al., 1987; Schafer, 1997).”
He, L., Lu, Y., Falk, C. F., & Hwang, H. (2025) · Structural Equation Modeling A Multidisciplinary Journal · doi:10.1080/10705511.2025.2531528 · Cited by 3
“FIML estimation for SEMs was first demonstrated by Allison (1987) and Muth � en et al., (1987).”
Bayesian factor mixture modeling with response time for detecting careless respondents
Zhang, L., Ulitzsch, E., & Domingue, B. W. (2025) · Behavior Research Methods · doi:10.3758/s13428-025-02797-x · Cited by 4
“In general, the relative bias for parameters associated with the attentive group, which are typically the parametersofinterestinpractice,remainedwithinacceptable limits (i.e., RB lower than 10% or 15%; Muthén et al. (1987)) across nearly all scenarios.”
Bardeen, J. R., Clauss, K. E., & Fergus, T. A. (2022) · Journal of Psychopathology and Behavioral Assessment · doi:10.1007/s10862-022-09955-x · Cited by 3
Bae, D., & Park, E. (2022) · 한국가정관리학회지 · doi:10.7466/jfbl.2022.40.1.11 · Cited by 4
Parallel Process Latent Growth Modeling with Multivariate Confounders/Suppressors
Lee, S., & Whittaker, T. A. (2022) · Structural Equation Modeling A Multidisciplinary Journal · doi:10.1080/10705511.2022.2133774 · Cited by 4
Formations à l’entrepreneuriat : les connaissances aptes à développer l’intention d’entreprendre
Rodríguez-Escobar, J. A., Lissillour, R., & Scotto, M.-J. (2022) · Formation emploi · doi:10.4000/formationemploi.11179 · Cited by 4
On the Performance of Full Information Maximum Likelihood in SEM Missing Data
Hmimou, A., Iaousse, M., Hmimou, S., Hachimi, H., & Elkettani, Y. (2023) · Mathematics and Statistics · doi:10.13189/ms.2023.110115 · Cited by 3
Gender differences in hierarchically ordered ability dimensions: The impact of missing data
Rosén, M. (1998) · Structural Equation Modeling A Multidisciplinary Journal · doi:10.1080/10705519809540088 · Cited by 3
McPherson, S., & Barbosa‐Leiker, C. (2012) · Journal of Applied Statistics · doi:10.1080/02664763.2012.702205 · Cited by 4
“FIML falls into the general category of model-based approaches to missing data [23,25].”
BackgroundInterpretation of Cognitive Test Scores in Relation to Swedish and Immigrant Groups
Kvist, A. V. (2011) · Nordic Psychology · doi:10.1027/1901-2276/a000027 · Cited by 3
Measuring family satisfaction with inpatient rehabilitation care
Angelino, E., Gragnano, A., & Miglioretti, M. (2016) · International Journal of Health Care Quality Assurance · doi:10.1108/ijhcqa-03-2015-0036 · Cited by 4
Muthén, L. K., & Muthén, B. (2008) · Cited by 3
Self-citationThe Diffusion of Hausman's Econometric Ideas
Zapata, H. O., & Caminita, C. M. (2012) · Advances in econometrics · doi:10.1108/s0731-9053(2012)0000029006 · Cited by 4
General and Specific Factors in Selection Modeling
Muthén, B. (2016) · Methodology of educational measurement and assessment · doi:10.1007/978-3-319-43473-5_12 · Cited by 3
Self-citationStevens, K. I., & Mennen, F. E. (2018) · SpringerBriefs in psychology · doi:10.1007/978-3-030-04561-6_4 · Cited by 3
Henschel, S. (2013) · Universitätsbibliothek der FU Berlin Hochschulschriftenstelle u. Dokumentenserver · doi:10.17169/refubium-16326 · Cited by 5
Towards the Second Generation of Structural Modeling
Tanaka, J. S. (1990) · Multivariate Behavioral Research · doi:10.1207/s15327906mbr2502_6 · Cited by 4
Efficient Estimation of Die-Level Process Parameter Variations via the EM-Algorithm
Zjajo, A., Krishnan, S., & de Gyvez, J. P. (2008) · IEEE International Symposium on Design and Diagnostics of Electronic Circuits & Systems (DDECS) · doi:10.1109/ddecs.2008.4538804 · Cited by 3
Meriton, R. (2016) · White Rose eTheses Online (University of Leeds, The University of Sheffield, University of York) · Cited by 7
Structural Equation Modeling: Nonstandard Cases
Marcoulides, G. A. (2005) · Encyclopedia of Statistics in Behavioral Science · doi:10.1002/0470013192.bsa450 · Cited by 3
Lee, M., Kim, Y., & Chesters, J. (2022) · Multicultural Education Review · doi:10.1080/2005615x.2022.2129292 · Cited by 3
“FIML has been identified as appropriate for incomplete data in that FIML estimates are less biased than listwise deletion or pairwise deletion (Little & Rubin, 1989; Muthen et al., 1987; Schafer & Olsen, 1998).”
MethodBouton, S., Chevallier, C., Cissé, A. H., Heude, B., & Jacquet, P. O. (2024) · Developmental Science · doi:10.1111/desc.13493 · Cited by 2
Multiliteracy as human capital in first-generation adult immigrants in Germany
Usanova, I., Schnoor, B., Bar‐Kochva, I., & Schröter, H. (2024) · International Journal of Bilingual Education and Bilingualism · doi:10.1080/13670050.2024.2375445 · Cited by 3
“In order to deal with missing data in the LCA, we used full information maximum likelihood estimation (FIML; Muthén, Kaplan, and Hollis 1987) in Mplus 8.2 for model parameter estimation, and a maximum likelihood algorithm producing robust standard errors (MLR) even under normal distribution…”
InfluentialTwo-year changes in hippocampal subfield volumes are age-dependent across the lifespan
Homayouni, R., Saifullah, S., Chargo, A. N., Canada, K. L., Raz, N., Ofen, N., & Daugherty, A. M. (2025) · Neurobiology of Aging · doi:10.1016/j.neurobiolaging.2025.06.011 · Cited by 2
Use of Monte Carlo Studies in Structural Equation Modeling Research
Bandalos, D. L., & Leite, W. (2013) · Emerald Group Publishing Limited eBooks · doi:10.1108/978-1-62396-246-320251019 · Cited by 50
Zhu, J., Li, Y., Zhu, S., & Li, Y. (2026) · Journal of Applied Developmental Psychology · doi:10.1016/j.appdev.2026.101923 · Cited by 2
Missing Data Reporting and Handling in Special Education Group Intervention Research
Espinas, D. R., Swanz, A., Hanson, A. L., & Logan, J. A. R. (2026) · Exceptional Children · doi:10.1177/00144029251410299 · Cited by 2
A De Jong Gierveld Magányosság Skála magyar változatának pszichometriai jellemzői
Szabó, D., & Szili, I. (2022) · Mentálhigiéné és Pszichoszomatika · doi:10.1556/0406.23.2022.002 · Cited by 5
Can avatar homophily influence flow and exploratory behaviour of online users?
Alblehai, F. (2022) · Education and Information Technologies · doi:10.1007/s10639-022-11111-7 · Cited by 3
“The mean values of the skewness and kurtosis were smaller than the prescribed levels (skewness, 2.0 and kurtosis, 7.0), indicating no significant problems regarding the multivariate normality of the data (Muthén et al., 1987).”
BackgroundInfluentialShiverdecker, L. K. (2019) · American Educational Research Association Annual Meeting (AERA) · doi:10.3102/1446683 · Cited by 2
Metadata
- Authors
- Muthén, B., Kaplan, D., & Hollis, M.
- Affiliations
- University of California, Los Angeles (US)
- ORCID
- Muthén, Bengt
- Venue
- Psychometrika
- Publisher
- Cambridge University Press (CUP)
- Published
- 1987-09
- Volume
- 52
- Issue
- 3
- Pages
- 431-462
- ISSN
- 0033-3123 (ISSN-L)
- 1860-0980
- OpenAlex
- W2065262588
- Cited by
- 883
- References
- 45
- Citations by year
- 2026: 22 · 2025: 30 · 2024: 27 · 2023: 37 · 2022: 53 · 2021: 37 · 2020: 35 · 2019: 37 · 2018: 28 · 2017: 31 · 2016: 29 · 2015: 36 · 2014: 39 · 2013: 39 · 2012: 33
- FWCI
- 6.04
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Psychometrika (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- Topics
- Social Sciences › Decision Sciences › Management Science and Operations Research › Psychometric Methodologies and Testing
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Physical Sciences › Mathematics › Applied Mathematics › Statistical and numerical algorithms
- Keywords
- structural equation modeling, missing data, missing completely at random, latent variable models, missing data mechanisms, maximum likelihood estimation, selection bias, measurement invariance, listwise deletion, pairwise deletion, LISREL
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
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.