The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
ACCOUNTING FOR DROPOUT BIAS USING MIXED-EFFECTS MODELS
Abstract
Treatment effects are often evaluated by comparing change over time in outcome measures. However, valid analyses of longitudinal data can be problematic when subjects discontinue (dropout) prior to completing the study. This study assessed the merits of likelihood-based repeated measures analyses (MMRM) compared with fixed-effects analysis of variance where missing values were imputed using the last observation carried forward approach (LOCF) in accounting for dropout bias. Comparisons were made in simulated data and in data from a randomized clinical trial. Subject dropout was introduced in the simulated data to generate ignorable and nonignorable missingness. Estimates of treatment group differences in mean change from baseline to endpoint from MMRM were, on average, markedly closer to the true value than estimates from LOCF in every scenario simulated. Standard errors and confidence intervals from MMRM accurately reflected the uncertainty of the estimates, whereas standard errors and confidence intervals from LOCF underestimated uncertainty.
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
“Missing data were managed using LMM, which is based on all observed data and accounts for data missing at random [108-110].”
Citations
Cites
Littell, R. C. (1996) · Medical Entomology and Zoology · Cited by 10,345
Linear Mixed Models for Longitudinal Data
Verbeke, G. (1997) · Lecture Notes in Statistics · doi:10.1007/978-1-4612-2294-1_3 · Cited by 3,506
Linear Mixed Models for Longitudinal Data
Molenberghs, G., & Verbeke, G. N. (2000) · Springer series in statistics · doi:10.1007/978-1-4419-0300-6 · Cited by 2,681
Multiple imputation in health‐are databases: An overview and some applications
Rubin, D. B., & Nathaniel Schenker, A. (1991) · Statistics in Medicine · doi:10.1002/sim.4780100410 · Cited by 1,553
Using the general linear mixed model to analyse unbalanced repeated measures and longitudinal data
Cnaan, A., Laird, N. M., & Slasor, P. (1997) · Statistics in Medicine · doi:10.1002/(sici)1097-0258(19971030)16:20 · Cited by 1,227
Tollefson, G. D., Beasley, C. M., Tran, P. V., Street, J. S., Krueger, J. A., Tamura, R., Graffeo, K. A., & Thieme, M. E. (1997) · American Journal of Psychiatry · doi:10.1176/ajp.154.4.457 · Cited by 891
Some Conceptual and Statistical Issues in Analysis of Longitudinal Psychiatric Data
Gibbons, R. D. (1993) · Archives of General Psychiatry · doi:10.1001/archpsyc.1993.01820210073009 · Cited by 719
Missing data in longitudinal studies
Laird, N. M. (1988) · Statistics in Medicine · doi:10.1002/sim.4780070131 · Cited by 713
A multiple imputation strategy for clinical trials with truncation of patient data
Lavori, P. W., Dawson, R., & Shera, D. M. (1995) · Statistics in Medicine · doi:10.1002/sim.4780141707 · Cited by 291
Statistical handling of drop‐outs in longitudinal clinical trials
Heyting, A., Tolboom, J. T. B. M., & Essers, J. G. A. (1992) · Statistics in Medicine · doi:10.1002/sim.4780111603 · Cited by 236
Research works printed but not linked: 6
- Milliken G. A., 1992, Designed Experiments, 326
- Little T., 1987, Analysis with Missing Data
- Lavori P. W., 1992, Neuropsychopharmacol, 6, 39
- Kay S. R., 1986, Positive and Negative Syndrome Scale (PANSS) Manual
- Mallinckrodt C. H., 1993, The Effects of Animal Model Approximations and Data Problems on the Reliability of Genetic Evaluations, Ph.D. Dissertation; Colorado State University: Fort Collins, CO
- 1997, SOLAS for Missing Data Analysis 1.0. Statistical Solutions Ltd: Cork
Cited by
Sorted by citations
Items 101–200 of 398
MMRM versus MI in Dealing with Missing Data—A Comparison Based on 25 NDA Data Sets
Siddiqui, O. (2011) · Journal of Biopharmaceutical Statistics · doi:10.1080/10543401003777995 · Cited by 63
LPHN3 and attention‐deficit/hyperactivity disorder: a susceptibility and pharmacogenetic study
Bruxel, E. M., Salatino-Oliveira, A., Akutagava-Martins, G. C., Tovo-Rodrigues, L., Genro, J., Zeni, C., Polanczyk, G. V., Chazan, R., Schmitz, M., Arcos-Burgos, M., et al. (2015) · Genes, Brain and Behavior · doi:10.1111/gbb.12224 · Cited by 77
Friberg, L. E., de Greef, R., Kerbusch, T., & Karlsson, M. (2009) · Clinical Pharmacology & Therapeutics · doi:10.1038/clpt.2009.44 · Cited by 63
“IIV AUC50 (CV%) Interindividual variability in AUC50 (exponential) 470 (19)”
BackgroundFitzgerald, P. B., Hoy, K. E., Singh, A., Gunewardene, R., Slack, C., Ibrahim, S., Hall, P. J., & Daskalakis, Z. J. (2013) · The International Journal of Neuropsychopharmacology · doi:10.1017/s1461145713000369 · Cited by 63
Parkinsonism and Related Disorders
Slow, E., & Lang, A. E. (2019) · DeckerMed Transitional Year Weekly Curriculum™ · doi:10.2310/tywc.1178 · Cited by 62
Kemani, M. K., Olsson, G. L., Lekander, M., Hesser, H., Andersson, E., & Wicksell, R. K. (2015) · The Clinical Journal of Pain · doi:10.1097/ajp.0000000000000203 · Cited by 61
Quality of life and physicians' perception in myelodysplastic syndromes.
En, O., Finelli, C., Santini, V., Poloni, A., Liso, V., Cilloni, D., Impera, S. S., Terenzi, A., Levis, A., Cortelezzi, A., et al. (2012) · Europe PMC (PubMed Central) · Cited by 61
Corticosteroid-free Kidney Transplantation Improves Growth
Webb, N. J. A., Douglas, S. E., Rajai, A., Roberts, S. A., Grenda, R., Marks, S. D., Watson, A. R., Fitzpatrick, M. M., Vondrák, K., Maxwell, H., et al. (2015) · Transplantation · doi:10.1097/tp.0000000000000498 · Cited by 61
Zhu, X. (2014) · Open Journal of Statistics · doi:10.4236/ojs.2014.411088 · Cited by 59
Johansson, R., Town, J. M., & Abbass, A. A. (2014) · PeerJ · doi:10.7717/peerj.548 · Cited by 61
Lim, S. S., Noakes, M., Keogh, J. B., & Clifton, P. M. (2010) · Nutrition, Metabolism and Cardiovascular Diseases · doi:10.1016/j.numecd.2009.05.003 · Cited by 68
“This approach was found to be superior to the traditional forms of intention-to-treat analysis in which missing data was substituted with baseline or last observed value [18].”
ResultPigott, T. A., Prakash, A., Arnold, L. M., Aaronson, S. T., Mallinckrodt, C. H., & Wohlreich, M. M. (2007) · Current Medical Research and Opinion · doi:10.1185/030079907x188107 · Cited by 59
Self-citationJohansson, R., Hesslow, T., Ljótsson, B., Jansson, A., Jonsson, L., Färdig, S., Karlsson, J., Hesser, H., Frederick, R. J., Lilliengren, P., et al. (2017) · Psychotherapy · doi:10.1037/pst0000147 · Cited by 55
Analyzing Incomplete Discrete Longitudinal Clinical Trial Data
Jansen, I., Beunckens, C., Molenberghs, G., Verbeke, G. N., & Mallinckrodt, C. H. (2006) · Statistical Science · doi:10.1214/088342305000000322 · Cited by 58
Self-citationEffects of Teriparatide Compared with Risedronate on Recovery After Pertrochanteric Hip Fracture
Aspenberg, P., Malouf, J., Tarantino, U., García-Hernández, P. A., Corradini, C., Overgaard, S., Stepan, J. J., Borris, L. C., Lespessailles, É., Frihagen, F., et al. (2016) · Journal of Bone and Joint Surgery · doi:10.2106/jbjs.15.01217 · Cited by 57
“A trial on pelvic fractures in women with osteoporosis treated using human PTH-(1-84) showed an extraordinary acceleration of healing20.”
BackgroundInfluentialTime course of depression-symptom improvement during treatment with duloxetine
Hirschfeld, R. M. A., Mallinckrodt, C. H., Lee, T. C., & Detke, M. J. (2005) · Depression and Anxiety · doi:10.1002/da.20071 · Cited by 57
“Mean changes were assessed using a likelihood-based mixed-effectsmodel repeated measures (MMRM) approach [Mallinckrodt et al., 2001].”
MethodSelf-citationLiu, M., Wei, L., & Zhang, J. (2006) · Pharmaceutical Statistics · doi:10.1002/pst.189 · Cited by 55
Are parental self‐efficacy and family flexibility mediators of treatment for anorexia nervosa?
Sadeh‐Sharvit, S., Arnow, K. D., Osipov, L., Lock, J., Jo, B., Pajarito, S., Brandt, H., Dodge, E., Halmi, K. A., Johnson, C., et al. (2018) · International Journal of Eating Disorders · doi:10.1002/eat.22826 · Cited by 52
The impact of analytic method on interpretation of outcomes in longitudinal clinical trials
Prakash, A., Risser, R. C., & Mallinckrodt, C. H. (2008) · International Journal of Clinical Practice · doi:10.1111/j.1742-1241.2008.01808.x · Cited by 59
Self-citationEllegaard, P. K., Licht, R. W., Nielsen, R. E., Dean, O. M., Berk, M., Poulsen, H. E., Mohebbi, M., & Nielsen, C. T. (2018) · Journal of Affective Disorders · doi:10.1016/j.jad.2018.10.083 · Cited by 50
“The analysis of the primary outcome measure was based on all randomized study participants Intention-To-Treat (ITT)-population and by using the Linear Mixed Effects Repeated Measures (LMERM) analyses (Laird and Ware, 1982; Mallinckrodt et al., 2001).”
MethodLee, P., Shu, L., Xu, X., Wang, C., Lee, M. S., LIU, C., Hong, J. P., Ruschel, S. I., Raskin, J., Colman, S. A., et al. (2007) · Psychiatry and Clinical Neurosciences · doi:10.1111/j.1440-1819.2007.01666.x · Cited by 50
“The average treatment effects over the entire study period were assessed using a restricted maximum likelihood (REML)-based, mixed-effects model, repeated-measures approach (MMRM).(32) Models included terms for the baseline score, treatment, center, visit, and treatment ¥ visit interaction and baseline score ¥ visit i…”
MethodMallinckrodt, C. H., Raskin, J., Wohlreich, M. M., Watkin, J. G., & Detke, M. J. (2004) · BMC Psychiatry · doi:10.1186/1471-244x-4-26 · Cited by 50
“One such method, termed MMRM (Mixed Model Repeated Measures [5]), has been studied extensively in the context of neuropsychiatric clinical trials [6-9].”
BackgroundMethodInfluentialSelf-citationRuiz, F. J., Peña-Vargas, A., Ramírez, E. S., Suárez-Falcón, J. C., García-Martín, M. B., García-Beltrán, D. M., Henao, Á. M., Monroy-Cifuentes, A., & Sánchez, P. D. (2020) · Psychotherapy · doi:10.1037/pst0000273 · Cited by 48
Malouf, J., Tarantino, U., García-Hernández, P. A., Corradini, C., Overgaard, S., Stepan, J. J., Borris, L. C., Lespessailles, É., Frihagen, F., Papavasiliou, K., et al. (2016) · Journal of Bone and Mineral Research · doi:10.1002/jbmr.3067 · Cited by 49
“MMRM accounts for data missing at random by using the correlation of observations within each patient and without the need of any explicit imputations.((42)) In addition, a “full model” was constructed by individually adding predefined fixed effects (age, gender, duration of prior bisphosphonates, and use of glucocort…”
MethodGallhofer, B., Jaanson, P., Mittoux, A., Tanghøj, P., Lis, S., & Krieger, S. (2007) · Pharmacopsychiatry · doi:10.1055/s-2007-990291 · Cited by 48
Mishra, S., & Khare, D. (2014) · Journal of Medical Statistics and Informatics · doi:10.7243/2053-7662-2-9 · Cited by 50
“Since, observed data in clinical trials explain much of information, the MAR assumption is relevant in many scenarios [2,9,15].”
BackgroundPower and Sample Size for Longitudinal Models in R – The longpower Package and Shiny App
Iddi, S., & Donohue, M. (2022) · The R Journal · doi:10.32614/rj-2022-022 · Cited by 38
“Continuous outcomes in clinical trial data collected longitudinally over time are commonly analyzed using linear mixed models (LMM; Laird and Ware, 1982) or MMRM (Mallinckrodt et al., 2001, 2003).”
MethodCarrión, R. E., McLaughlin, D., Auther, A. M., Olsen, R. H., Correll, C. U., & Cornblatt, B. A. (2015) · Psychological Medicine · doi:10.1017/s0033291715001233 · Cited by 45
“…in the presence of unbalanced designs (i.e. missing observations, inconsistent time intervals) and non-independent correlated data, providing unbiased estimates of covariance parameters (Verbeke & Molenberghs, 2000; Mallinckrodt et al. 2001; Gueorguieva & Krystal, 2004; McCulloch et al. 2008).”
BackgroundMethodPrevention of Missing Data in Clinical Research Studies
Wisniewski, S. R., Leon, A. C., Otto, M. W., & Trivedi, M. H. (2006) · Biological Psychiatry · doi:10.1016/j.biopsych.2006.01.017 · Cited by 45
Bruxel, E. M., Salatino-Oliveira, A., Genro, J., Zeni, C., Polanczyk, G. V., Chazan, R., Rohde, L., & Hutz, M. (2012) · The Pharmacogenomics Journal · doi:10.1038/tpj.2012.25 · Cited by 53
Liu‐Seifert, H., Andersen, S. W., Lipkovich, I. A., Holdridge, K. C., & Siemers, E. (2015) · PLoS ONE · doi:10.1371/journal.pone.0119632 · Cited by 43
Kivitz, A., Fairfax, M., Sheldon, E. A., Xiang, Q., Jones, B. A., Gammaitoni, A. R., & Gould, E. M. (2008) · Clinical Therapeutics · doi:10.1016/j.clinthera.2008.12.015 · Cited by 44
Barnes, S. A., Mallinckrodt, C. H., Lindborg, S. R., & Carter, M. K. (2007) · Pharmaceutical Statistics · doi:10.1002/pst.310 · Cited by 44
“Research [6,13,15] and analytic proof [15,22] have shown that the behavior of LOCF is in fact uncertain, with frequent inflation of Type I error when treatments are not different and overestimation of the magnitude of treatment differences when the treatments are different.”
BackgroundMethodSelf-citationLankford, D. A., Corser, B. C., Zheng, Y., Zhengrong Li, P., Snavely, D. B., Lines, C. R., & Deacon, S. (2008) · SLEEP · doi:10.5665/sleep/31.10.1359 · Cited by 43
van der Wilt, A. A., Giuliani, G., Kubis, C., van Wunnik, B. P. W., Ferreira, I., Breukink, S. O., Lehur, P., Torre, F. L., & Baeten, C. G. M. I. (2017) · British journal of surgery · doi:10.1002/bjs.10590 · Cited by 42
Bradley, A. J., & Lenox‐Smith, A. (2013) · Journal of Psychopharmacology · doi:10.1177/0269881113494937 · Cited by 42
“Studies have demonstrated that differences in drop outs between treatments introduce significant bias in estimations of treatment efficacy using the LOCF methodology (Lane, 2008; Mallinckrodt et al., 2001; Siddiqui et al., 2009).”
BackgroundMethodInfluentialRoberts, D. J., Jenne, C. N., Ball, C. G., Tiruta, C., Léger, C., Xiao, Z. J., Faris, P., McBeth, P. B., Doig, C. J., Skinner, C. R., et al. (2013) · Trials · doi:10.1186/1745-6215-14-141 · Cited by 41
“For longitudinal studies, mixed-effects models have previously been shown to be superior to conventional last-observation-carried-forward approaches for handling missed observations during follow-up [77,78].”
MethodRelationship Between Age and Weight Loss in Noom: Quasi-Experimental Study
DeLuca, L., Toro-Ramos, T., Michaelides, A., Seng, E., & Swencionis, C. (2020) · JMIR Diabetes · doi:10.2196/18363 · Cited by 36
“Linear mixed effects models estimate missing data within the analysis and are robust to data missing at random and not at random [22].”
BackgroundModelling placebo response in depression trials using a longitudinal model with informative dropout
Goméni, R., Lavergne, A., & Merlo‐Pich, E. (2008) · European Journal of Pharmaceutical Sciences · doi:10.1016/j.ejps.2008.10.025 · Cited by 40
Arnold, L. M., Hirsch, I., Sanders, P. W., Ellis, A., & Hughes, B. (2012) · Arthritis & Rheumatism · doi:10.1002/art.34390 · Cited by 42
Lam, R. W. M., & Kennedy, S. H. (2004) · PubMed · Cited by 40
Okada, H., Onda, M., Shoji, M., Sakane, N., Nakagawa, Y., Sozu, T., Kitajima, Y., Tsuyuki, R. T., & Nakayama, T. (2017) · BioScience Trends · doi:10.5582/bst.2017.01256 · Cited by 38
“Furthermore, repeatedly measured home BP data were analysed using the mixedeffect model for repeated measures (MMRM) with the first-order autoregressive structure (AR[1]) (22), where the group, the measurement time, and the interaction of group and measurement time were included as the fixed”
MethodMyin‐Germeys, I., van Aubel, E., Vaessen, T., Steinhart, H., Klippel, A., Lafit, G., Viechtbauer, W., Batink, T., van Winkel, R., van der Gaag, M., et al. (2022) · Psychotherapy and Psychosomatics · doi:10.1159/000522274 · Cited by 46
Efficacy of ziprasidone in dysphoric mania: Pooled analysis of two double-blind studies
Stahl, S. M., Lombardo, I., Loebel, A. D., & Mandel, F. S. (2009) · Journal of Affective Disorders · doi:10.1016/j.jad.2009.06.023 · Cited by 38
“A mixed-model repeated-measures analysis (Mallinckrodt et al., 2001) was used to impute any missing data.”
Wu, E. Q., Birnbaum, H. G., Mareva, M. N., Le, T., Robinson, R. L., Rosen, A. S., & Gelwicks, S. (2006) · Journal of Pain · doi:10.1016/j.jpain.2006.01.443 · Cited by 39
Xu, H., Liu, B., Wu, J., Du, R., Liu, X., Yu, J., & Liu, Z. (2016) · PLoS ONE · doi:10.1371/journal.pone.0150821 · Cited by 39
“The imputation method for missing data that we used, the last observation carried forward method, may result in bias and is less appropriate than multiple imputation [42, 43].”
MethodFurukawa, T. A., Tajika, A., Toyomoto, R., Sakata, M., Luo, Y., Horikoshi, M., Akechi, T., Kawakami, N., Nakayama, T., Kondo, N., et al. (2025) · Nature Medicine · doi:10.1038/s41591-025-03639-1 · Cited by 40
“We used the MMRM 74,75 to estimate the mean difference in change scores on the PHQ-9 for each component while adjusting for missing outcomes.”
Witjes, H., Creinin, M. D., Poromaa, I. S., Nguyen, A. M., & Korver, T. (2015) · The European Journal of Contraception & Reproductive Health Care · doi:10.3109/13625187.2015.1016154 · Cited by 37
Santen, G. W. E., Danhof, M., & Pasqua, O. E. D. (2009) · Journal of Psychiatric Research · doi:10.1016/j.jpsychires.2009.02.001 · Cited by 37
Chung, M. P., Park, M. S., Oh, I., Lee, H. B., Kim, Y. W., Park, J. S., Uh, S. T., Kim, Y. S., Jegal, Y., & Song, J. W. (2020) · Advances in Therapy · doi:10.1007/s12325-020-01328-8 · Cited by 39
Chazan, R., Borowsky, C., Pianca, T. G., Ludwig, H. T., Rohde, L. A., & Polanczyk, G. V. (2011) · Journal of Clinical Psychopharmacology · doi:10.1097/jcp.0b013e318217b4df · Cited by 39
Ulrich, S., Gantenbein, A. R., Zuber, V., Von Wyl, A., Kowatsch, T., & Künzli, H. (2024) · Journal of Medical Internet Research · doi:10.2196/50132 · Cited by 36
“Missing data were managed using LMM, which is based on all observed data and accounts for data missing at random [108-110].”
Natural cubic splines for the analysis of Alzheimer's clinical trials
Donohue, M., Langford, O., Insel, P. S., van Dyck, C. H., Petersen, R. C., Craft, S., Sethuraman, G., Raman, R., Aisen, P. S. S., & Initiative, A. D. N. (2023) · Pharmaceutical Statistics · doi:10.1002/pst.2285 · Cited by 36
Leisman, D. E., Handisides, D. R., Busse, L. W., Chappell, M. C., Chawla, L. S., Filbin, M. R., Goldberg, M. B., Ham, K. R., Khanna, A. K., Ostermann, M., et al. (2024) · Critical Care · doi:10.1186/s13054-024-04910-6 · Cited by 37
“These models have the advantage of being robust to missing data bias, even when data are not missing at random [13].”
BackgroundSocial decline in the psychosis prodrome: Predictor potential and heterogeneity of outcome
Carrión, R. E., Auther, A. M., McLaughlin, D., Addington, J., Bearden, C. E., Cadenhead, K. S., Cannon, T. D., Keshavan, M., Mathalon, D. H., McGlashan, T. H., et al. (2021) · Schizophrenia Research · doi:10.1016/j.schres.2020.09.006 · Cited by 36
“Linear mixed-effects models for repeated measures were used to evaluate group differences between the four subgroups in social functioning (Gueorguieva and Krystal, 2004; Mallinckrodt et al., 2001; McCulloch and Searle, 2001; Verbeke and Molenberghs, 2000).”
MethodType I error rates from likelihood‐based repeated measures analyses of incomplete longitudinal data
Mallinckrodt, C. H., Kaiser, C. J., Watkin, J. G., Detke, M. J., Molenberghs, G., & Carroll, R. J. (2004) · Pharmaceutical Statistics · doi:10.1002/pst.131 · Cited by 38
“These results were consistent with previous studies where MMRM and LOCF were compared in scenarios with MNAR missingness [13,14,20].”
MethodResultInfluentialSelf-citationLevator hiatal area as a risk factor for cystocele recurrence after surgery: a prospective study
Vergeldt, T., Notten, K., Weemhoff, M., van Kuijk, S., Mulder, F., Beets‐Tan, R., Vliegen, R., Gondrie, E., Bergmans, M., Roovers, J., et al. (2015) · BJOG: An International Journal of Obstetrics & Gynaecology · doi:10.1111/1471-0528.13340 · Cited by 35
Boessen, R., Groenwold, R. H. H., Knol, M. J., Grobbee, D. E., & Roes, K. C. B. (2012) · Journal of Affective Disorders · doi:10.1016/j.jad.2012.08.026 · Cited by 36
“(Mallinckrodt et al., 2001).”
Ghaemi, S. N., Sverdlov, O., van Dam, J., Campellone, T. R., & Gerwien, R. W. (2021) · JMIR Formative Research · doi:10.2196/29154 · Cited by 36
“…change in the total PANSS score from baseline to day 85 or last visit, was analyzed using the mixed effects model for repeated measures (MMRM) [25], applied on the intention-to-treat (ITT) set, which included all participants to whom study treatment was assigned by randomization and who had a…”
Tadić, A. (2008) · Neuropsychiatric Disease and Treatment · doi:10.2147/ndt.s2262 · Cited by 37
“…between genotype groups across the treatment period were analyzed using a mixed-effects model repeated-measures methodology (MMRM), as MMRM has been shown to provide highly accurate modeling of treatment outcome while accounting for nonrandom missing data (Mallinckrodt et al 2001, 2003).”
InfluentialDubé, S., Tollefson, G. D., Thase, M. E., Briggs, S. D., Campen, L. E. V., Case, M. G., & Tohen, M. F. (2007) · Bipolar Disorders · doi:10.1111/j.1399-5618.2007.00491.x · Cited by 35
Hogg, D., Kingham, S., Wilson, T., & Ardagh, M. (2016) · Social Science & Medicine · doi:10.1016/j.socscimed.2016.01.025 · Cited by 35
“Research suggests that such likelihood-based mixed-effects repeated measures analyses are the method of choice to account for dropouts in longitudinal studies (Mallinckrodt et al., 2001).”
MethodTripodis, Y., Alosco, M. L., Zirogiannis, N., Gavett, B. E., Chaisson, C. E., Martin, B. M., McClean, M. D., Mez, J., Kowall, N. W., & Stern, R. A. (2017) · Journal of Alzheimer s Disease · doi:10.3233/jad-160585 · Cited by 35
“Missing data were handled through the mixed effect model framework, which has been shown superior to other method due to the use of maximum likelihood estimation procedures [38].”
Inoue, Y., Hirata, K., Uchimura, N., Kuroda, K., Hattori, N., & Takeuchi, M. (2012) · Current Medical Research and Opinion · doi:10.1185/03007995.2012.746217 · Cited by 34
González, R. V. A., Kita, M., Crayton, H. J., Havrdová, E., Margolin, D. H., Lake, S. L., Giovannoni, G., & on behalf of the CARE-MS I and II Investigators (2016) · Multiple Sclerosis Journal · doi:10.1177/1352458516677589 · Cited by 33
Findling, R. L., Youngstrom, E. A., Rowles, B. M., Deyling, E. A., Lingler, J., Stansbrey, R. J., McVoy, M. K., Lytle, S., Calabrese, J. R., & McNamara, N. (2017) · Journal of Child and Adolescent Psychopharmacology · doi:10.1089/cap.2016.0160 · Cited by 33
“These provide highly accurate modeling of treatment outcomes while accounting for nonrandom missing data (i.e., patient dropout) (Gibbons et al. 1993; Mallinckrodt et al. 2001).”
Salatino‐Oliveira, A., Genro, J. P., Zeni, C., Polanczyk, G. V., Chazan, R., Guimarães, A. P., Callegari-Jacques, S. M., Rohde, L. A., & Hutz, M. H. (2011) · Biological Psychiatry · doi:10.1016/j.biopsych.2011.03.025 · Cited by 33
Points to Consider on Missing Data
Watanabe, H., & TASAKI, T. (2006) · Japanese Journal of Biometrics · doi:10.5691/jjb.27.s33 · Cited by 33
Reininghaus, U., Oorschot, M., Moritz, S., Gayer-Anderson, C. E., Kempton, M. J., Valmaggia, L., McGuire, P. K., Murray, R. M., Garety, P. A., Wykes, T., et al. (2018) · Schizophrenia Bulletin · doi:10.1093/schbul/sby116 · Cited by 34
Gosho, M., Hirakawa, A., Noma, H., Maruo, K., & Sato, Y. (2015) · Statistical Methods in Medical Research · doi:10.1177/0962280215597938 · Cited by 31
Semi-parametric and non-parametric methods for clinical trials with incomplete data
O’Brien, P. C., Zhang, D., & Bailey, K. R. (2004) · Statistics in Medicine · doi:10.1002/sim.1963 · Cited by 31
The effect of comprehensive lifestyle intervention or metformin on obesity in young women☆
Lim, S. S., Norman, R. J., Clifton, P. M., & Noakes, M. (2010) · Nutrition Metabolism and Cardiovascular Diseases · doi:10.1016/j.numecd.2009.10.006 · Cited by 31
“In the primary analyses, treatment outcomes were assessed using linear mixed models on all participants who commenced the interventions [21].”
MethodOptimal composite scores for longitudinal clinical trials under the linear mixed effects model
Ard, M. C., Raghavan, N., & Edland, S. D. (2015) · Pharmaceutical Statistics · doi:10.1002/pst.1701 · Cited by 30
“Second, because LME weights can be calculated for known, arbitrary clinical trial designs given sufficient pilot data, the approach can not only be used to determine weights for trials with a longer duration than available pilot data but can also be adapted for the case where the trial endpoint is change from baseline…”
Kępińska, A. P., MacCabe, J. H., Cadar, D., Steptoe, A., Murray, R. M., & Ajnakina, O. (2020) · Translational Psychiatry · doi:10.1038/s41398-020-01114-8 · Cited by 30
Zou, L., Choi, Y., Guizzetti, L., Shu, D., Zou, J., & Zou, G. (2024) · Statistics in Medicine · doi:10.1002/sim.10172 · Cited by 30
“This assumption is well-known in the analysis of longitudinal clinical trials with continuous data as missing at random.”
Lavie, A., Ram, M., Lev, S., Blecher, Y., Amikam, U., Shulman, Y., Avnon, T., Weiner, E., & Many, A. (2018) · BMC Pregnancy and Childbirth · doi:10.1186/s12884-018-1861-7 · Cited by 28
“Mixed models are the preferable method of analysis of repeatedly measured outcomes when there are missing data, the repeated measures are irregularly spaced over time, and the sample is small [51, 52].”
MethodBeuchel, P., Ophoff, J. G., Cramer, C., & Hautzinger, M. (2022) · Teaching and Teacher Education · doi:10.1016/j.tate.2022.103703 · Cited by 46
Seasonal variations of cough reflex sensitivity in elite athletes training in cold air environment
Turmel, J., Bougault, V., & Boulet, L. (2012) · Cough · doi:10.1186/1745-9974-8-2 · Cited by 29
Ritola, V., Lipsanen, J. O., Pihlaja, S., Gummerus, E.-M., Stenberg, J., Saarni, S. E., & Joffe, G. (2021) · Journal of Medical Internet Research · doi:10.2196/29384 · Cited by 31
“This approach generally performs better than a pure last observation carried forward (LOCF) at handling dropout bias, especially in larger samples (n>400 [51]).”
MethodRosencrantz, M. A., Coffler, M. S., Haggan, A., Duke, K. B., Donohue, M., Shayya, R. F., Su, H.-C. I., & Chang, R. J. (2011) · The Journal of Clinical Endocrinology & Metabolism · doi:10.1210/jc.2010-2200 · Cited by 28
“The MMRM revealed the individual doses of hCG at which stimulated 17-OHP responses were significantly greater in PCOS compared with those of normal women, 100 and 250 g (P 0.05).”
MethodInfluentialCross‐validation of optimized composites for preclinical Alzheimer's disease
Donohue, M., Sun, C., Raman, R., Insel, P. S., Aisen, P. S. S., Initiative, N. A. A. D. N., Lifestyle, A. I. B. A., & Initiative, J. A. D. N. (2016) · Alzheimer s & Dementia Translational Research & Clinical Interventions · doi:10.1016/j.trci.2016.12.001 · Cited by 27
“First, the global treatment effect is much more broad than typical MMRMestimand (i.e., ITT contrast at the final visit).”
MethodPaetzold, I., Myin‐Germeys, I., Schick, A., Nelson, B., Velthorst, E., Schirmbeck, F. N., Study, E.-G. H. R., van Os, J., Morgan, C., Hartmann, J., et al. (2021) · Epidemiology and Psychiatric Sciences · doi:10.1017/s2045796021000251 · Cited by 27
“…estimation (H3 and H4) were applied, allowing for the use of all available data under the relatively unrestrictive assumption that data are missing at random and if all variables associated with missing values are included in the model (Little and Rubin, 1987; Mallinckrodt et al ., 2001).”
Kang, Z., Qin, Y., Sun, Y., Lu, Z., Sun, Y., Chen, H., Feng, X., Zhang, Y., Guo, H., Yan, H., et al. (2023) · JAMA Network Open · doi:10.1001/jamanetworkopen.2023.35518 · Cited by 27
“8) Education, median (IQR), y 9 (9-12) 9 (9-12) 9 (9-12) Duration of illness, median (IQR), mo 25 (6-72) 36 (13-79) 36 (12-72) Family history of schizophrenia 7 (6.”
Fenner, A. A., Howie, E. K., Davis, M. C., & Straker, L. M. (2016) · Health and Quality of Life Outcomes · doi:10.1186/s12955-016-0501-z · Cited by 27
“Within the linear mixed model, non-biased estimates were calculated for the missing values using likelihood-based estimation which uses information from surrounding responses and the covariance structure which is an appropriate method in studies with high levels of drop-out and drop-out bias [41].”
MethodKrekels, E., Novakovic, A., Vermeulen, A., Friberg, L. E., & Karlsson, M. (2017) · CPT Pharmacometrics & Systems Pharmacology · doi:10.1002/psp4.12207 · Cited by 27
Development of lung diffusion to adulthood following extremely preterm birth
Satrell, E., Clemm, H. H., Røksund, O. D., Hufthammer, K. O., Thorsen, E., Halvorsen, T., & Vollsæter, M. (2021) · European Respiratory Journal · doi:10.1183/13993003.04103-2020 · Cited by 26
“This was done to reduce any bias caused by missing data and to increase the precision of the estimates [25].”
The handling of missing data in clinical trials
Kenward, M. G. (2013) · Clinical Investigation · doi:10.4155/cli.13.7 · Cited by 27
Intensive Short-Term Dynamic Psychotherapy Trial Therapy
Abbass, A. A., Town, J. M., Ogrodniczuk, J. S., Joffres, M., & Lilliengren, P. (2017) · The Journal of Nervous and Mental Disease · doi:10.1097/nmd.0000000000000684 · Cited by 25
“This form of estimation provides unbiased estimates under the less restrictive assumption of data missing at random (Mallinckrodt et al., 2001), which allows the probability of data being missing to be dependent on both outcome variables (e.”
BackgroundMixed model of repeated measures versus slope models in Alzheimer's disease clinical trials
Donohue, M., & Aisen, P. S. S. (2012) · The journal of nutrition health & aging · doi:10.1007/s12603-012-0047-7 · Cited by 24
The methods for handling missing data in clinical trials influence sample size requirements
Auleley, G.-R., Giraudeau, B., Baron, G., Maillefert, J.-F., Dougados, M., & Ravaud, P. (2004) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2003.09.012 · Cited by 24
A monoamine oxidase B gene variant and short-term antidepressant treatment response
Tadić, A., Rujescu, D., Müller, M. J., Kohnen, R., Stassen, H. H., Dahmen, N., & Szegedi, A. (2007) · Progress in Neuro-Psychopharmacology and Biological Psychiatry · doi:10.1016/j.pnpbp.2007.05.015 · Cited by 24
Nordmo, M., Sinding, A. I., Carlbring, P., Andersson, G., Havik, O. E., & Nordgreen, T. (2015) · Internet Interventions · doi:10.1016/j.invent.2015.10.003 · Cited by 23
“Likelihood-based repeatedmeasures analysis generally outperforms traditional methods like last observation carried forward in accounting for dropout bias (Mallinckrodt et al., 2001).”
MethodLevine, S. Z., & Leucht, S. (2012) · Schizophrenia Research · doi:10.1016/j.schres.2012.08.030 · Cited by 23
the EFACTS or NICOFA study group, Reetz, K., Hilgers, R.-D., Isfort, S., Dohmen, M., Didszun, C., Fedosov, K., Kistermann, J., Mariotti, C., Dürr, A., et al. (2019) · Neurological Research and Practice · doi:10.1186/s42466-019-0038-9 · Cited by 22
Effect of heteroscedasticity between treatment groups on mixed‐effects models for repeated measures
Gosho, M., & Maruo, K. (2018) · Pharmaceutical Statistics · doi:10.1002/pst.1872 · Cited by 22
Sugimoto, T., Araki, A., Fujita, H., Fujita, K., Honda, K., Inagaki, N., Ishida, T., Kato, J., Kishi, M., Kishino, Y., et al. (2024) · The Journal of Prevention of Alzheimer s Disease · doi:10.14283/jpad.2024.117 · Cited by 23
Usall, J., López‐Carrilero, R., Iniesta, R., Roca, M., Caballero, M. I. I., Rodríguez–Jiménez, R., Oliveira, C., Bernardo, M., Corripio, I., Duran‐Sindreu, S., et al. (2014) · The Journal of Clinical Psychiatry · doi:10.4088/jcp.13m08551 · Cited by 21
Lu, K., Jiang, L., & Tsiatis, A. A. (2010) · Biometrics · doi:10.1111/j.1541-0420.2010.01405.x · Cited by 21
“This is reminiscent of the mixedeffects model repeated measures (MMRM) model proposed by Mallinckrodt, Clark, and David (2001), which is particularly suitable for analyzing clinical trial data because subjects in clinical trials are often evaluated at a fixed and relative small number of time…”
MethodWang, G., Liu, L., Li, Y., Aschenbrenner, A. J., Bateman, R. J., Delmar, P., Schneider, L. S. S., Kennedy, R., Cutter, G., & Xiong, C. (2022) · Alzheimer s & Dementia Translational Research & Clinical Interventions · doi:10.1002/trc2.12286 · Cited by 20
Nock, N. L., Dimitropoulos, A., Rao, S. M., Flask, C. A., Schluchter, M., Zanotti, K. M., Rose, P. G., Kirwan, J. P., & Alberts, J. L. (2014) · Contemporary Clinical Trials · doi:10.1016/j.cct.2014.08.008 · Cited by 20
“In terms of handling missing data, we will use the likelihood-based linear mixed modeling approach with baseline values included in the model because it has been shown to be more valid way to deal with dropout in clinical trials as compared to simple imputation procedures such as last observation carried forward [87].”
Method
Metadata
- Authors
- Mallinckrodt, C. H., Clark, W. S., & David, S. R.
- Affiliations
- Eli Lilly (United States) (US)
- Venue
- Journal of Biopharmaceutical Statistics
- Publisher
- Informa UK Limited
- Published
- 2001-01-01
- Volume
- 11
- Issue
- 1-2
- Pages
- 9-21
- ISSN
- 1054-3406 (ISSN-L)
- 1520-5711
- OpenAlex
- W2073155558
- Cited by
- 398
- References
- 14
- Citations by year
- 2026: 12 · 2025: 13 · 2024: 21 · 2023: 12 · 2022: 27 · 2021: 19 · 2020: 20 · 2019: 13 · 2018: 14 · 2017: 14 · 2016: 18 · 2015: 21 · 2014: 16 · 2013: 23 · 2012: 19
- FWCI
- 11.96
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Journal of Biopharmaceutical Statistics (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Clinical Trials
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Keywords
- mixed models, last observation carried forward, missing data, non-ignorable missingness, treatment effect estimation, longitudinal data, randomized controlled trials, standard error estimation
- MeSH terms
- Analysis of Variance, Humans, Longitudinal Studies, Patient Dropouts, Models, Statistical, Bias, Confidence Intervals, Randomized Controlled Trials as Topic
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