The DOI matches its Crossref record.
A critical look at methods for handling missing covariates in epidemiologic regression analyses.
Abstract
Epidemiologic studies often encounter missing covariate values. While simple methods such as stratification on missing-data status, conditional-mean imputation, and complete-subject analysis are commonly employed for handling this problem, several studies have shown that these methods can be biased under reasonable circumstances. The authors review these results in the context of logistic regression and present simulation experiments showing the limitations of the methods. The method based on missing-data indicators can exhibit severe bias even when the data are missing completely at random, and regression (conditional-mean) imputation can be inordinately sensitive to model misspecification. Even complete-subject analysis can outperform these methods. More sophisticated methods, such as maximum likelihood, multiple imputation, and weighted estimating equations, have been given extensive attention in the statistics literature. While these methods are superior to simple methods, they are not commonly used in epidemiology, no doubt due to their complexity and the lack of packaged software to apply these methods. The authors contrast the results of multiple imputation to simple methods in the analysis of a case-control study of endometrial cancer, and they find a meaningful difference in results for age at menarche. In general, the authors recommend that epidemiologists avoid using the missing-indicator method and use more sophisticated methods whenever a large proportion of data are missing.
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
“Commonly missing values are related to observed participant or disease characteristics.”
From Reporting and Methods in Clinical Prediction Research: A Systematic Review (2012) · cites this paper as [24]
In the citing paper
“Missing values in clinical study data rarely occur completely at random.”
From Reporting and Methods in Clinical Prediction Research: A Systematic Review (2012) · cites this paper as [24]
In the citing paper
“Exclusion of participants with missing values will therefore not only lead to loss of statistical power, but often also to biased results 10,12,13,23,24,57,58.”
From Reporting and Methods in Clinical Prediction Research: A Systematic Review (2012) · cites this paper as [24]
Citations
Cited by
Sorted by citations
Items 601–700 of 892
Transitional modeling of experimental longitudinal data with missing values
de Rooij, M. (2015) · Advances in Data Analysis and Classification · doi:10.1007/s11634-015-0226-6 · Cited by 10
Singer, J. D., & Willett, J. B. (2003) · doi:10.1093/acprof:oso/9780195152968.003.0005 · Cited by 11
Jansen, E. C., Stern, D., Peterson, K. E., et al. (2019) · Maternal and Child Health Journal · doi:10.1007/s10995-018-2650-7 · Cited by 10
“…the estimates were highly similar in the missing indicator analysis is reassuring, although we recognize the possibility of introducing missing indicator bias (which could bias estimates in either direction) if the assumption of missing completely at random is not met (Greenland and Finkle 1995).”
Radon Awareness and Policy Perspectives on Testing and Mitigation
Novilla, M. L. B., Johnston, J. D., Beard, J. D., Pettit, L. L., Davis, S. F., & Johnson, C. E. (2021) · Atmosphere · doi:10.3390/atmos12081016 · Cited by 10
“The meanings of “I don’t know” and “I am not interested in this issue” responses were unclear but including categories for those responses in analyses could be similar to including a missing data indicator variable, which has been shown to bias results [65].”
BackgroundBrumariu, L. E., Bureau, J., Nemoda, Z., Sasvári‐Székely, M., & Lyons‐Ruth, K. (2015) · Journal of Reproductive and Infant Psychology · doi:10.1080/02646838.2015.1072764 · Cited by 10
A Relative Survival Model for Clustered Responses
Kuß, O., Blankenburg, T., & Haerting, J. (2008) · Biometrical Journal · doi:10.1002/bimj.200710426 · Cited by 10
Robbins, H. A., Hurley, E. A., Liu, L., & Chao, S. M. (2015) · Maternal and Child Health Journal · doi:10.1007/s10995-015-1675-4 · Cited by 10
“Strengths of our study include a large and diverse population-based sample, use of multiple imputation instead of model-wise deletion for missing data [34], and use of a mailed survey for IPV outcome ascertainment [35].”
Abraham, A. G., Lau, B., Deeks, S. G., et al. (2011) · American Journal of Epidemiology · doi:10.1093/aje/kwr141 · Cited by 10
Bengtson, A. M., Pence, B. W., Moore, R. D., Mimiaga, M. J., Mathews, W. C., Heine, A. D., Gaynes, B. N., Napravnik, S., Christopoulos, K., Crane, H. M., et al. (2017) · AIDS · doi:10.1097/qad.0000000000001431 · Cited by 10
“missing values for individual variables for all observed PRO assessments [36].”
BackgroundSheckter, C. C., Rochlin, D. H., Kiwanuka, H., et al. (2019) · Breast Cancer Research and Treatment · doi:10.1007/s10549-019-05361-2 · Cited by 10
Consequences of Model Misspecification for Maximum Likelihood Estimation with Missing Data
Golden, R. M., Henley, S. S., White, H., & Kashner, T. M. (2019) · Econometrics · doi:10.3390/econometrics7030037 · Cited by 10
“…and Kenward 2007; Zhou et al. 2014), survey data analysis (e.g., Gmel 2001; Troxel et al. 1998), regression analysis (e.g., Graham et al. 1997; Greenland and Finkle 1995), verification bias (e.g., Harel and Zhou 2006; Kosinski and Barnhart 2003a, 2003b), hierarchical modeling (e.g., Agresti…”
BackgroundCaamaño‐Isorna, F., Figueiras, A., Lado, E. U., et al. (2001) · Gaceta Sanitaria · doi:10.1016/s0213-9111(01)71614-7 · Cited by 10
Quality of out-of-hours primary care in the Netherlands.
Giesen, P. H. J. (2006) · Radboud Repository (Radboud University) · Cited by 10
Preoperative Hyponatremia and Perioperative Complications in Cervical Spinal Fusion
Pennington, Z. A., Bomberger, T. T., Lubelski, D., Benzel, E. C., Steinmetz, M. P., & Mroz, T. E. (2020) · World Neurosurgery · doi:10.1016/j.wneu.2020.06.068 · Cited by 9
Hulsegge, G., Smit, H. A., van der Schouw, Y. T., Daviglus, M. L., & Verschuren, W. M. M. (2014) · European Journal of Preventive Cardiology · doi:10.1177/2047487314544083 · Cited by 10
Secondary analysis of large databases for hepatology research
Okafor, P. N., Chiejina, M., de Pretis, N., et al. (2015) · Journal of Hepatology · doi:10.1016/j.jhep.2015.12.019 · Cited by 9
Hsieh, M., Yu, Q., Wu, X., et al. (2012) · PubMed · Cited by 9
Hormonal Contraception and Metabolic Outcomes in Women With or at Risk for HIV Infection
Womack, J. A., Scherzer, R., Cole, S. R., Fennie, K., Williams, A. B., Grey, M. J., MINKOFF, H. L., Anastos, K., Cohen, M. H., & Tien, P. C. (2009) · JAIDS Journal of Acquired Immune Deficiency Syndromes · doi:10.1097/qai.0b013e3181b9e5ee · Cited by 9
Lyles, R. H., & Allen, A. S. (2003) · Statistics in Medicine · doi:10.1002/sim.1348 · Cited by 9
“Nevertheless, several authors [14, 15] have emphasized bridging the gap between well-developed statistical theory related to missing data and the practical realities of epidemiology in practice.”
BackgroundFreeman, L. M., Middeldorp, J., van den Akker, E., et al. (2018) · PLoS ONE · doi:10.1371/journal.pone.0205220 · Cited by 9
Dyck, D. G., Weeks, D. L., Smith, C. L., & Shaw, M. R. (2020) · Journal of Spinal Cord Medicine · doi:10.1080/10790268.2019.1710946 · Cited by 9
Setting up a multivariable analysis
Katz, M. H. (2011) · Cambridge University Press eBooks · doi:10.1017/cbo9780511974175.007 · Cited by 9
Construction and Analysis of Multiparameter Prognostic Models for Melanoma Outcome
Rothberg, B. E. G., & Rimm, D. L. (2013) · Methods in molecular biology · doi:10.1007/978-1-62703-727-3_13 · Cited by 9
“Any individual with missing data for one or more selected markers will be excluded each time that protein is incorporated in a proposed model which can introduce bias if missingness is not completely at random [80].”
BackgroundChen, J. T., Kaddour, A., Krieger, N. R., et al. (2008) · Public Health Reports · doi:10.1177/003335490812300303 · Cited by 9
Buick, J. E., Austin, P. C., Cheskes, S., Ko, D. T., & Atzema, C. L. (2023) · Academic Emergency Medicine · doi:10.1111/acem.14756 · Cited by 9
“36,37,39– 42, 44, 48, 49 prediction model studies specifically, complete case analysis increases increases the risk of overfitting and poor calibration ( under”
The fallacy of single imputation for trait databases: Use multiple imputation instead
Blomberg, S. P., & Todorov, O. S. (2025) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.14494 · Cited by 15
“…al., 2021; Barnard & Rubin, 1999; Brand & Brand, 1999; Brown et al., 2012; Casiraghi et al., 2023; Diaz-Tena & Shaman, 2001; Ellington et al., 2015; Greenland & Finkle, 1995; Horton & Kleinman, 2007; Janssen et al., 2010; Johnson et al., 2021; Josse & Husson, 2012; Kontopantelis et al., 2017; Lee…”
Multiple Imputation for Continuous and Categorical Data: Comparing Joint and Conditional Approaches
Kropko, J., Goodrich, B., & Gelman, A. (2013) · Cited by 7
Deming, R. S., Wolfe, J., & DeCourcey, D. D. (2020) · Journal of Pain and Symptom Management · doi:10.1016/j.jpainsymman.2020.11.018 · Cited by 8
Lines, L. M., Humphrey, J. L., & Barch, D. H. (2022) · Medical Care · doi:10.1097/mlr.0000000000001717 · Cited by 8
Model development including interactions with multiple imputed data
Hendry, G. M., Naidoo, R. N., Zewotir, T. T., et al. (2014) · BMC Medical Research Methodology · doi:10.1186/1471-2288-14-136 · Cited by 8
“Background It is not unusual to encounter missing data in epidemiological studies [1,2].”
BackgroundOjha, R. P., & Steyerberg, E. W. (2018) · Journal of Hepatology · doi:10.1016/j.jhep.2018.02.037 · Cited by 8
“Such exclusion relies on the unrealistic assumption that excluded cases were missing completely at random.(6) Non-random exclusion of patients based on outcome status leads to a selected population of patients who completed treatment and had a high probability of SVR.”
BackgroundMenéndez-García, L. A., Fernández, M. M., Sokoła-Szewioła, V., et al. (2022) · Applied Sciences · doi:10.3390/app12136465 · Cited by 8
Margerison-Zilko, C. E., & Cubbin, C. (2013) · Obesity · doi:10.1002/oby.20333 · Cited by 8
“) Because the use of missing indicator variables has been shown to lead to biased estimates (21), we also conducted a complete case analysis excluding observations with missing data for any covariates.”
MethodEffectiveness of a cardiac surgery–specific transfusion protocol
Bilecen, S., de Groot, J. D., Kalkman, C., Spanjersberg, A., Moons, K., & Nierich, A. (2014) · Transfusion · doi:10.1111/trf.12346 · Cited by 8
“Therefore, imputing missing values is generally preferred to complete case analysis.(29-32) Missing variables were imputed using a regression model with logistic regression for dichotomous variables and linear regression for continuous variables.”
MethodGebregziabher, M., & Langholz, B. M. (2009) · Biometrics · doi:10.1111/j.1541-0420.2009.01322.x · Cited by 8
“Interestingly, other investigators have studied the performance of SMI under several analytic settings, such as in unmatched case–control data (Vach and Blettner, 1991; Greenland and Finkle, 1995) and individually matched case–control data (Huberman and Langholz, 1999; Li et al.”
BackgroundMethodMiller, P., Kendrick, D., Coupland, C. A. C., & Coffey, F. (2010) · Injury Prevention · doi:10.1136/ip.2010.029215.36 · Cited by 8
Modeling Change Using Covariance Structure Analysis
Singer, J. D., & Willett, J. B. (2003) · doi:10.1093/acprof:oso/9780195152968.003.0008 · Cited by 8
A nonparametric multiple imputation approach for missing categorical data
Zhou, M., He, Y., Yu, M., et al. (2017) · BMC Medical Research Methodology · doi:10.1186/s12874-017-0360-2 · Cited by 8
“to estimate the proportion of each category of the multinomial outcome variable, and therefore are not recommended in general [5, 9, 10].”
BackgroundAt-Risk Alcohol Use Among HIV-Positive Patients and the Completion of Patient-Reported Outcomes
Rudolph, J. E., Cole, S. R., Edwards, J. K., Moore, R. D., O’Cleirigh, C. M., Mathews, W. C., & Christopoulos, K. (2017) · AIDS and Behavior · doi:10.1007/s10461-017-1824-4 · Cited by 8
“Unlike other types of missing data, ‘‘missing not at random’’ typically cannot be controlled for using multiple imputation or inverse probability of missingness weights [12, 22].”
BackgroundStansbury, J. P., Reid, K. J., Reker, D. M., Duncan, P. W., Marshall, C. R., & Rittman, M. (2004) · The Journal of Rehabilitation Research and Development · doi:10.1682/jrrd.2004.04.0046 · Cited by 8
“In the absence of reliable substitute information, complete subject analysis may remain the best alternative given the questionable validity of trying to impute ethnic designation [51].”
BackgroundZhang, K., Chai, L., Zhang, Y., et al. (2025) · Archives of Gerontology and Geriatrics · doi:10.1016/j.archger.2025.105780 · Cited by 7
Accessing and utilizing clinical and genomic data from an electronic health record data warehouse
Arnold, C. G., Sonn, B., Meyers, F. J., et al. (2023) · Translational Medicine Communications · doi:10.1186/s41231-023-00140-0 · Cited by 7
“This allows for the inclusion of all subjects in the analysis, including those that would have been excluded due to missing values, and a less biased and more precise estimate of the outcomes under study [15, 17, 18].”
BackgroundTime Series Reconstruction With Feature-Driven Imputation: A Comparison of Base Learning Algorithms
Bashir, N., Mir, A. A., Daud, A. Y., Rafique, M., & Bukhari, A. A. (2024) · IEEE Access · doi:10.1109/access.2024.3416321 · Cited by 8
“These methods will produce incredibly biased values as well as ineffective studies [46], [47], [48].”
Methodvan Baaren, G., Bruijn, M. M. C., Vis, J. Y., Wilms, F. F., Oudijk, M. A., Kwee, A., PORATH, M. M., Oei, S. G., Scheepers, H. C. J., Spaanderman, M. E. A., et al. (2015) · European Journal of Obstetrics & Gynecology and Reproductive Biology · doi:10.1016/j.ejogrb.2015.05.004 · Cited by 7
“Since it is well documented that exclusion of incomplete cases can yield biased results, we corrected the missing values using multiple imputation (10 times) [14–16].”
MethodLewden, C., Jacqmin‐Gadda, H., Vildé, J., et al. (2004) · HIV Clinical Trials · doi:10.1310/x9ae-5f0y-ae92-g1na · Cited by 7
Data Driven Estimation of Imputation Error—A Strategy for Imputation with a Reject Option
Bak, N. K., & Hansen, L. K. (2016) · PLoS ONE · doi:10.1371/journal.pone.0164464 · Cited by 7
Anatomic Location and Mechanism of Injury Correlating with Prehospital Deaths in Sub‐Saharan Africa
Reid, T. D. S., Strassle, P. D., Gallaher, J. R., et al. (2018) · World Journal of Surgery · doi:10.1007/s00268-018-4577-y · Cited by 7
“, change the missingness assumption from missing completely at random [MCAR], which is rarely true, to missing at random [MAR], which assumes that missingness is random within each covariate strata) [8].”
BackgroundHou, G., Jiang, C., Du, J., et al. (2021) · Journal of Cancer · doi:10.7150/jca.64255 · Cited by 7
“[5] still subject to bias even under MCAR assumption and a small amount of missing data [18].”
Schuit, E., Amer‐Wåhlin, I., Groenwold, R. H. H., et al. (2012) · American Journal of Perinatology · doi:10.1055/s-0032-1314888 · Cited by 7
Hulsegge, G., van der Schouw, Y. T., Daviglus, M. L., Smit, H. A., & Verschuren, W. M. M. (2015) · European Journal of Public Health · doi:10.1093/eurpub/ckv125 · Cited by 7
Pinho, A. D. A., Chinaglia, M. L. M., Lippman, S. A., et al. (2011) · Sexually Transmitted Infections · doi:10.1136/sextrans-2011-050186 · Cited by 7
Dahal, P., Stepniewska, K., Guerin, P. J., D’Alessandro, U., Price, R. N., & Simpson, J. A. (2019) · BMC Medical Research Methodology · doi:10.1186/s12874-019-0856-z · Cited by 7
Hendry, G. M., North, D., Zewotir, T. T., & Naidoo, R. N. (2014) · Statistics in Medicine · doi:10.1002/sim.6189 · Cited by 7
“This has been made possible by the development of s-CA , a variant of CA [3].”
MethodA regime-switching longitudinal model of alcohol lapse-relapse
Chow, S., Witkiewitz, K. A., Grasman, R. P. P. P., Hutton, R. S., & Maisto, S. A. (2014) · UvA-DARE (University of Amsterdam) · Cited by 6
Occupational silica exposure and mortality from lung cancer and nonmalignant respiratory disease
Picciotto, S., Neophytou, A. M., Brown, D., et al. (2018) · Environmental Epidemiology · doi:10.1097/ee9.0000000000000029 · Cited by 6
Patel, H. C., Hayward, C., Patel, K., Claggett, B. L., Vazir, A., & Cowie, M. (2019) · International Journal of Cardiology · doi:10.1016/j.ijcard.2019.11.138 · Cited by 6
An improved kNN method based on Spearman’s rank correlation for handling medical missing values
Liang, C., Zhang, L., Wan, Z., et al. (2022) · doi:10.1109/mlke55170.2022.00033 · Cited by 6
Prick, B. W., Schuit, E., Mignini, L. E., Jansen, A. J. G., van Rhenen, D. J., Steegers, E., Mol, B. W., & Duvekot, J. J. (2015) · BJOG An International Journal of Obstetrics & Gynaecology · doi:10.1111/1471-0528.13224 · Cited by 6
Stability of outcomes after 5 years of treatment in an early intervention programme
Norman, R. M. G., Anderson, K. K., MacDougall, A. G., Manchanda, R., Harricharan, R., Subramanian, P., Richard, J., & Northcott, S. (2017) · Early Intervention in Psychiatry · doi:10.1111/eip.12450 · Cited by 6
Korthuis, P. T., Anaya, H. D., Bozzette, S. A., Brinkerhoff, C., Mancewicz, M., Wang, M., & Asch, S. M. (2004) · Journal of clinical outcomes management · Cited by 6
Gijo, T. (2015) · The University of Queensland · doi:10.14264/uql.2015.463 · Cited by 6
Synergistic effects of cardiovascular health and social isolation on adverse pregnancy outcomes
Ohseto, H., Ishikuro, M., Chen, G., Takahashi, I., Shinoda, G., Noda, A., Murakami, K., Orui, M., Iwama, N., Kikuya, M., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-03652-x · Cited by 6
“First, due to some missing values not satisfying the “missing completely at random” assumption 39 , we conducted association analyses after imputing missing values for CVH metrics and covariates using multiple imputation by chain equations with five iterations 40 in a population of 18,321 eligible…”
Leveraging auxiliary data to improve precision in inverse probability-weighted analyses
Zalla, L. C., Yang, J. Y., Edwards, J. K., & Cole, S. R. (2022) · Annals of Epidemiology · doi:10.1016/j.annepidem.2022.07.011 · Cited by 5
Song, Y., Hughes, J. P., & Ye, T. (2024) · Biometrics · doi:10.1093/biomtc/ujae094 · Cited by 5
“Note that these appealing properties are due to randomization in RCTs and do not hold in observational studies; see caveats of MIM when used in observational studies in Greenland and Finkle (1995), Donders et al. (2006), and Yang et al. (2019).”
BackgroundMethodFontela, P. S., Quach, C., Buckeridge, D. L., et al. (2012) · PLoS ONE · doi:10.1371/journal.pone.0036582 · Cited by 5
“In using this strategy, missing completely at random data were produced by design, which allowed the calculation of unbiased estimates of the annual ICU CLABSI pooled incidence rates.[14,16,17] However, as the estimates were calculated based”
MethodMirmohammadkhani, M., Foroushani, A. R., Davatchi, F., Mohammad, K., Jamshidi, A., Banihashemi, A. T., & Naieni, K. H. (2012) · Europe PMC (PubMed Central) · Cited by 5
Missing data treatment method on cluster analysis
Koko, E. E. M., & Mohamed, A. I. A. (2015) · International Journal of Advanced Statistics and Probability · doi:10.14419/ijasp.v3i2.5318 · Cited by 5
Exploring Longitudinal Data on Change
Singer, J. D., & Willett, J. B. (2003) · doi:10.1093/acprof:oso/9780195152968.003.0002 · Cited by 5
Ledipasvir/Sofosbuvir Effectively Treats Hepatitis C Virus Infections in an Underserved Population
Stewart, R. A., MacDonald, B. R., Chu, T.-C., Moore, J. D., Fasanmi, E. O., & Ojha, R. P. (2018) · Digestive Diseases and Sciences · doi:10.1007/s10620-018-5205-2 · Cited by 5
You, Y., van Grieken, A., Estévez‐López, F., Yang‐Huang, J., & Raat, H. (2022) · Frontiers in Public Health · doi:10.3389/fpubh.2021.785054 · Cited by 5
“Multiple imputation was applied to impute missing data in the determinants (30).”
MethodClot length predicts recanalisation but not outcome after basilar artery occlusion
van der Hoeven, E. J., Algra, A., Vos, J. A., et al. (2016) · European Stroke Journal · doi:10.1177/2396987316673265 · Cited by 5
Ethnic background and children’s television viewing trajectories: The Generation R Study
Yang‐Huang, J., van Grieken, A., Wang, L., Jaddoe, V. W. V., Jansen, W., & Raat, H. (2018) · PLoS ONE · doi:10.1371/journal.pone.0209375 · Cited by 5
Statistical reviewing for disability and rehabilitation
Rigby, A. S. (2008) · Disability and Rehabilitation · doi:10.1080/09638280802136837 · Cited by 5
“Recognition of the missing data mechanism is important in selecting an appropriate method of analysis, because methods that disregard the missing data process may lead to biased estimates of effect size and unrealistic estimates of power [30,34,35,37] though the latter may be overcome to some extent by including more…”
MethodDelaney, J. A., McClelland, R. L., Brown, E. R., Bluemke, D. A., Vogel‐Claussen, J., Lai, S., & Heckbert, S. R. (2009) · Canadian Journal of Cardiology · doi:10.1016/s0828-282x(09)70507-0 · Cited by 5
“Therefore, when the complete case approach and multiple imputation show differences, the estimates from the imputed datasets are likely to be closer to the true values for the parameters (4).”
BackgroundMethodITERATIVE TWO-PASS ALGORITHM FOR MISSING DATA IMPUTATION IN SNP ARRAYS
Sinoquet, C. (2009) · Journal of Bioinformatics and Computational Biology · doi:10.1142/s0219720009004357 · Cited by 5
“To warrant a sufficiently high confidence in such estimations, among other features, it is crucial that the sample should be large enough.(8,9) This additional point confirms the need for computational SNP inference methods.”
BackgroundExtending the Cox Regression Model
Singer, J. D., & Willett, J. B. (2003) · doi:10.1093/acprof:oso/9780195152968.003.0015 · Cited by 5
Extending the Discrete-Time Hazard Model
Singer, J. D., & Willett, J. B. (2003) · doi:10.1093/acprof:oso/9780195152968.003.0012 · Cited by 5
Access to Health Care Services and Self-Perceived Health of Canada’s Official-Language Minorities
Gagnon-Arpin, I. (2011) · Library and Archives Canada (Government of Canada) · doi:10.20381/ruor-4657 · Cited by 5
Rayner, C., Hannigan, L. J., Badini, I., Demange, P., Ofstad, S. B., Ystrøm, E., & McAdams, T. A. (2026) · International Journal of Epidemiology · doi:10.1093/ije/dyag122 · Cited by 7
“…may not effectively account for selection bias in other domains (e.g. ‘clinical variables’); key predictors of participation may be missing from our models; missing data in the prediction variable set were imputed by using single imputa-tion—for which the limitations are well documented [23].”
Tolani, E., Carpenter, M., Petersen, I., & Carpenter, J. R. (2025) · Clinical Epidemiology · doi:10.2147/clep.s528401 · Cited by 5
“18,19 Among the various statistical methods available, multiple imputation (MI) is widely regarded as a robust, flexible and practical approach.”
Analysis of local sensitivity to nonignorability with missing outcomes and predictors
Chen, H., & Heitjan, D. F. (2021) · Biometrics · doi:10.1111/biom.13532 · Cited by 4
“…that ignore the missing-datamechanism therefore implicitly (if not explicitly) assume an MAR mechanism and a PD parameterization (Little, 1992; Greenland and Finkle, 1995; Paik, 1996; Lipsitz et al., 1998; Horton and Laird, 1999; Ibrahim et al., 1999; Paik and Sacco, 2000; Satten and Carroll,…”
BackgroundKok, L., Elias, S. G., Witteman, B. J. M., Goedhard, J. G., Romberg-Camps, M. J. L., Muris, J. W. M., Moons, K. G. M., & de Wit, N. J. (2013) · European Journal of Gastroenterology & Hepatology · doi:10.1097/meg.0b013e32835d4ddd · Cited by 4
Time Series Analysis of Air Pollutants for Karabük Province
Can, A. (2017) · ITM Web of Conferences · doi:10.1051/itmconf/20170902002 · Cited by 4
Urinary Estrogen Metabolites and Long-Term Mortality Following Breast Cancer
Wang, T., Nichols, H. B., Nyante, S. J., Bradshaw, P. T., Moorman, P. G., Kabat, G. C., Parada, H., Khankari, N. K., Teitelbaum, S. L., Terry, M. B., et al. (2020) · JNCI Cancer Spectrum · doi:10.1093/jncics/pkaa014 · Cited by 4
“Thus, we performed multiple imputations by using PROC MI in SAS (34), which is a methodologically sound approach that implements Markov Chain Monte Carlo procedure (35) (25 imputations with 100 iterations) to address bias and loss of precision (36,37).”
MethodRelationship Between Urolithiasis and Fatty Liver Disease: Findings in Computed Tomography
Badillo, F. G. L., Cala, Ó. L. O., Campos, S. N. V., et al. (2020) · Tomography · doi:10.18383/j.tom.2020.00020 · Cited by 4
“The input and output of variables in the regression method were performed based on the criteria established by Sander Greenland (23).”
MethodTan, Q., Liu, Y., Liu, J., Shi, B., Xia, S., & Zhou, X. (2020) · Neurocomputing · doi:10.1016/j.neucom.2019.12.145 · Cited by 4
Robustness of Multiple Imputation under Missing at Random (MAR) Mechanism: A Simulation Study
Garg, P. (2013) · Cited by 4
Lin, W., & Liu, N. (2012) · Frontiers in Genetics · doi:10.3389/fgene.2012.00107 · Cited by 4
Jolani, S., & Safarkhani, M. (2017) · Methodology · doi:10.1027/1614-2241/a000121 · Cited by 4
Comparison of Haplotype-based and Tree-based SNP Imputation in Association Studies
Dai, J. Y., Ruczinski, I., LeBlanc, M. L., et al. (2006) · Collection of Biostatistics Research Archive (COBRA) · Cited by 4
Karter, A. J., Thom, D. H., Liu, J. Y., Moffet, H. H., Ferrara, A. M., & Selby, J. V. (2003) · Diabetes Care · doi:10.2337/diacare.26.7.2100 · Cited by 4
“We used missing variable indicators (“indicator method”) (38,39) for subjects for whom covariate information was missing.”
MethodWhitson, J. M., & Meng, M. V. (2013) · British Journal of Urology · doi:10.1111/j.1464-410x.2012.11718.x · Cited by 4
Baris, D., Linet, M. S., Tarone, R. E., et al. (1999) · Occupational and Environmental Medicine · doi:10.1136/oem.56.8.562 · Cited by 4
Ali, K., & Spinks, J. (2003) · Injury Prevention · doi:10.1136/ip.9.1.92 · Cited by 4
Describing Continuous-Time Event Occurrence Data
Singer, J. D., & Willett, J. B. (2003) · doi:10.1093/acprof:oso/9780195152968.003.0013 · Cited by 4
Modeling Discontinuous and Nonlinear Change
Singer, J. D., & Willett, J. B. (2003) · doi:10.1093/acprof:oso/9780195152968.003.0006 · Cited by 4
Singer, J. D., & Willett, J. B. (2003) · doi:10.1093/acprof:oso/9780195152968.003.0014 · Cited by 4
Seungju, L., 문승현, & 이소민 (2017) · 가족과 문화 · doi:10.21478/family.29.3.201709.004 · Cited by 4
Vrbaški, D., Kupusinac, A., Doroslovački, R., Stokić, E., & Ivetić, D. (2020) · Computer Science and Information Systems · doi:10.2298/csis190710003v · Cited by 3
“There are some previous results that explore comparison between methods for imputation [25] [11] [14] and even study ANNs within missing data problem [3] [22] [21] [29] [36].”
Result
Metadata
- Authors
- Greenland, S., & Finkle, W. D.
- Affiliations
- University of California, Los Angeles (US)
- Corresponding author
- Greenland, Sander
- ORCID
- Greenland, Sander
- Venue
- American Journal of Epidemiology
- Publisher
- Oxford University Press (OUP)
- Published
- 1995-12-15
- Volume
- 142
- Issue
- 12
- Pages
- 1255-1264
- ISSN
- 0002-9262 (ISSN-L)
- 1476-6256
- OpenAlex
- W2166561686
- Cited by
- 891
- References
- 0
- Citations by year
- 2026: 13 · 2025: 18 · 2024: 13 · 2023: 24 · 2022: 26 · 2021: 21 · 2020: 33 · 2019: 29 · 2018: 34 · 2017: 32 · 2016: 27 · 2015: 40 · 2014: 57 · 2013: 53 · 2012: 67
- FWCI
- 6.57
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- American Journal of Epidemiology (publishedVersion)
- PubMed (publishedVersion)
- American Journal of Epidemiology
- Funders
- National Institutes of Health (n01cp095680-001)
- National Cancer Institute (N01 CP 95680)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Keywords
- missing covariates, missing data, logistic regression, bias, model misspecification, multiple imputation, maximum likelihood estimation, weighted estimating equations, endometrial cancer, age at menarche, case-control study
- MeSH terms
- Epidemiologic Methods, Female, Humans, Menarche, Research Design, Logistic Models, Odds Ratio, Case-Control Studies, Endometrial Neoplasms
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
