A Comparison of the General Linear Mixed Model and Repeated Measures ANOVA Using a Dataset with Multiple Missing Data Points
The DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
Longitudinal methods are the methods of choice for researchers who view their phenomena of interest as dynamic. Although statistical methods have remained largely fixed in a linear view of biology and behavior, more recent methods, such as the general linear mixed model (mixed model), can be used to analyze dynamic phenomena that are often of interest to nurses. Two strengths of the mixed model are (1) the ability to accommodate missing data points often encountered in longitudinal datasets and (2) the ability to model nonlinear, individual characteristics. The purpose of this article is to demonstrate the advantages of using the mixed model for analyzing nonlinear, longitudinal datasets with multiple missing data points by comparing the mixed model to the widely used repeated measures ANOVA using an experimental set of data. The decision-making steps in analyzing the data using both the mixed model and the repeated measures ANOVA are described.
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
“Importantly, the chosen analytic approach, linear mixed models, is robust to missing data.”
From Associations Between Self-Monitoring and Weight Change in Behavioral Weight Loss Interventions (2019) · cites this paper as Krueger & Tian, 2004
In the citing paper
“Missing weights were not imputed because the proposed analyses accommodate multiple missing data points by including a random effect of subject (Edwards, 2000; Krueger & Tian, 2004).”
From Associations Between Self-Monitoring and Weight Change in Behavioral Weight Loss Interventions (2019) · cites this paper as Krueger & Tian, 2004
In the citing paper
“However, since we encountered more missing values for cortisol levels and heart rate than anticipated, we decided to conduct our main analyses using mixed-effects regression models with maximum likelihood estimation because these models were both a better fit to the data and better equipped to handle missingness in the data set [46].”
From Self-soothing touch and being hugged reduce cortisol responses to stress: A randomized controlled trial on stress, physical touch, and social identity (2021) · cites this paper as [46]
In the citing paper
“An important advantage of the mixed model over repeated measures ANOVA is that the modeling of the individual participant variables can accommodate multiple missing data points in longitudinal datasets (55).”
In the citing paper
“Although mixed-effects REML is robust to missing data (55), a sensitivity analysis was also conducted by imputing missing data for the primary outcome (DASS-21) using multiple-imputation by chained equations (MICE) (57).”
Citations
Cites
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. (2000) · Springer Series in Statistics · doi:10.1007/978-1-4419-0300-6 · Cited by 2,646
The international encyclopedia of education
Watson, K. (1994) · International Journal of Educational Development · doi:10.1016/0738-0593(94)90060-4 · Cited by 1,487
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<2349::aid-sim667>3.0.co;2-e · Cited by 1,222
Using SAS PROC MIXED to Fit Multilevel Models, Hierarchical Models, and Individual Growth Models
Singer, J. D. (1998) · Journal of Educational and Behavioral Statistics · doi:10.2307/1165280 · Cited by 1,092
Are there behavioural states in the human fetus?
Nijhuis, J. G., Prechtl, H. F. R., Martin, C. B., & Bots, R. S. G. M. (1982) · Early Human Development · doi:10.1016/0378-3782(82)90106-2 · Cited by 808
Statistical Methods for the Analysis of Repeated Measurements
Davis, C. S. (2002) · Springer Texts in Statistics · doi:10.1007/b97287 · Cited by 577
Gottlieb, G. (1998) · Psychological Review · doi:10.1037/0033-295x.105.4.792-802 · Cited by 489
WILLETT, J. B., SINGER, J. D., & MARTIN, N. C. (1998) · Development and Psychopathology · doi:10.1017/s0954579498001667 · Cited by 423
Reading Statistics and Research
Huck, S. W. (2013) · Cited by 302
Research works printed but not linked: 1
- 10.1002/(SICI)1098-240X(199602)19:1<75::AID-NUR8>3.0.CO;2-I · doi:10.1002/(sici)1098-240x(199602)19:1<75::aid-nur8>3.0.co;2-i
Cited by
Rey, N. L., Steiner, J. A., Maroof, N., Luk, K. C., Madaj, Z., Trojanowski, J. Q., Lee, V. M.-Y., & Brundin, P. (2016) · Journal of Experimental Medicine · doi:10.1084/jem.20160368 · Cited by 388
“Both of these features should result in superior model performance and accuracy (Krueger and Tian, 2004).”
BackgroundThe Effects of Interactive Latency on Exploratory Visual Analysis
Liu, Z., & Heer, J. (2014) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2014.2346452 · Cited by 326
“As no single subject experienced all combinations of factors, repeated measures ANOVA is subject to sampling bias and higher chances of type I error [32] .”
BackgroundInfluentialRey, N. L., George, S., Steiner, J. A., Madaj, Z., Luk, K. C., Trojanowski, J. Q., Lee, V. M.-Y., & Brundin, P. (2018) · Acta Neuropathologica · doi:10.1007/s00401-017-1792-9 · Cited by 215
“The inclusion of the random intercepts accounts for the auto-correlation in these data and ultimately yields better model performance and increased accuracy [30].”
Descilo, T., Vedamurtachar, A., Gerbarg, P. L., Nagaraja, D., Gangadhar, B. N., Damodaran, B., Adelson, B., Braslow, L. H., Marcus, S., & Brown, R. P. (2010) · Acta Psychiatrica Scandinavica · doi:10.1111/j.1600-0447.2009.01466.x · Cited by 210
“Mixed effects regression models can describe each individual s pattern of change and accommodate missing data points and different numbers of observations per subject (45).”
BackgroundGhosh, A., Tyson, T., George, S., Hildebrandt, E. N., Steiner, J. A., Madaj, Z., Schulz, E., Machiela, E., McDonald, W. G., Escobar Galvis, M. L., et al. (2016) · Science Translational Medicine · doi:10.1126/scitranslmed.aag2210 · Cited by 189
“Both of these features should result in superior model performance and accuracy (95).”
BackgroundMachine Learning in Nutrition Research
Kirk, D., Kok, E., Tufano, M., Tekinerdogan, B., Feskens, E. J. M., & Camps, G. (2022) · Advances in Nutrition · doi:10.1093/advances/nmac103 · Cited by 178
“Certain approaches in traditional statistics and ML can handle missing data well, including linear mixed models, decision trees, kNN, and XGBoost, sometimes even when missing data are as high as 20% (159, 160).”
MethodWobrock, T., Guse, B., Cordes, J., Wölwer, W., Winterer, G., Gaebel, W., Langguth, B., Landgrebe, M., Eichhammer, P., Frank, E., et al. (2015) · Biological Psychiatry · doi:10.1016/j.biopsych.2014.10.009 · Cited by 170
Rowe, M., Bellamy, C., Baranoski, M., Wieland, M., O'Connell, M. J., Benedict, P., Davidson, L., Buchanan, J., & Sells, D. (2007) · Psychiatric Services · doi:10.1176/ps.2007.58.7.955 · Cited by 174
Muth, C., Bales, K. L., Hinde, K., Maninger, N., Mendoza, S. P., & Ferrer, E. (2016) · Educational and Psychological Measurement · doi:10.1177/0013164415580432 · Cited by 165
“In light of our small-sample focus, we draw from Krueger and Tian’s (2004) research, which similarly examines LME’s facility for modeling around small, unbalanced, longitudinal data.”
MethodPakyz, A. L., Oinonen, M. J., & Polk, R. E. (2009) · Antimicrobial Agents and Chemotherapy · doi:10.1128/aac.01535-08 · Cited by 150
“Use of the mixed model enabled examination of relationships across time, with missing data points ( 10 ).”
MethodVirtual reality: A new method to investigate cognitive load during navigation
Armougum, A., Orriols, É., Gaston‐Bellegarde, A., Marle, C. J.-L., & Piolino, P. (2019) · Journal of Environmental Psychology · doi:10.1016/j.jenvp.2019.101338 · Cited by 176
Logerstedt, D. S., Lynch, A. D., Axe, M. J., & Snyder‐Mackler, L. (2012) · Knee Surgery Sports Traumatology Arthroscopy · doi:10.1007/s00167-012-1929-2 · Cited by 133
“To describe the longitudinal outcomes, a mixed model ANOVA with maximum likelihood estimation method was chosen over a general linear model due to its ability to handle missing data [20, 31].”
MethodGeurts, J. W., Smits, H., Kemler, M. A., Brunner, F., Kessels, A. G. H., & van Kleef, M. (2013) · Neuromodulation Technology at the Neural Interface · doi:10.1111/ner.12024 · Cited by 124
“To take into account that the outcomes are correlated within the pain scores of one patient, a general linear mixed model was used to examine the trend in time (11,12).”
MethodMagarey, A., Perry, R. A., Baur, L. A., Steinbeck, K. S., SAWYER, M. G., Hills, A. P., Wilson, G. T., Lee, A., & Daniels, L. (2011) · PEDIATRICS · doi:10.1542/peds.2009-1432 · Cited by 134
Dreisoerner, A., Junker, N. M., Schlotz, W., Heimrich, J., Bloemeke, S., Ditzen, B., & van Dick, R. (2021) · Comprehensive Psychoneuroendocrinology · doi:10.1016/j.cpnec.2021.100091 · Cited by 118
“because these models were both a better fit to the data and better equipped to handle missingness in the data set [46].”
MethodMcKendrick, R. D., Ayaz, H., Olmstead, R., & Parasuraman, R. (2013) · NeuroImage · doi:10.1016/j.neuroimage.2013.05.103 · Cited by 136
“Furthermore linear mixed effects models allow for time to be modeled as a continuous variable, therefore temporal change can also be modeled nonlinearly (Baayen et al., 2008; Krueger and Tian, 2004; Laird and Ware, 1982).”
Analysis of longitudinal data from animals where some data are missing in SPSS
Duricki, D. A., Soleman, S., & Moon, L. (2016) · Nature Protocols · doi:10.1038/nprot.2016.048 · Cited by 107
Zhou, M., Fukuoka, Y., Mintz, Y., Goldberg, K., Kaminsky, P., Flowers, E., & Aswani, A. (2018) · JMIR mHealth and uHealth · doi:10.2196/mhealth.9117 · Cited by 111
“LMM implicitly imputes missing data by interpolation and is a common approach to deal with missing data in physical activity interventions [56-60].”
Eakin, E., Lawler, S., WINKLER, E. A. H., & Hayes, S. C. (2011) · Annals of Behavioral Medicine · doi:10.1007/s12160-011-9324-7 · Cited by 122
“Mixed models were used, with random intercepts for each individual and for each hospital, to accommodate repeated measures without requiring complete case analysis [47] and to correct for clustering within hospitals.”
MethodGarzke, J., Ismar, S. M. H., & Sommer, U. J. (2014) · Oecologia · doi:10.1007/s00442-014-3130-4 · Cited by 131
“(Cottingham et al. 2005; Krueger and Tian 2004).”
Oberpriller, J., Leite, M. D. S., & Pichler, M. (2022) · Ecology and Evolution · doi:10.1002/ece3.9062 · Cited by 133
“…analysis (Wainwright et al. 2007; Boisgontier & Cheval 2016) because they allow simultaneous analysis of variance at different hierarchical levels (Krueger & Tian 2004; Boisgontier & Cheval 2016), handle unbalanced study designs better (Swallow & Monahan 1984; Lindstrom & Bates 1988; Pinheiro &…”
BackgroundWho Is (Still) Looking After Mom and Dad? Few Improvements in Care Aides’ Quality-of-Work Life
Chamberlain, S. A., Hoben, M., Squires, J. E., Cummings, G. G., Norton, P., & Estabrooks, C. A. (2018) · Canadian Journal on Aging / La Revue canadienne du vieillissement · doi:10.1017/s0714980818000338 · Cited by 123
“In general, values generated from a linear mixed model are the most conservative test of significance and demonstrate the statistically significant differences between the samples, given dependence (Krueger & Tian, 2004; Singer, 1998).”
BackgroundFoster, K., Fethney, J., McKenzie, H., Fisher, M., Harkness, E. L., & Kozlowski, D. (2017) · Nurse Education Today · doi:10.1016/j.nedt.2017.05.008 · Cited by 90
Pereira, M. J., Comans, T. A., Sjøgaard, G., Straker, L. M., Melloh, M., O’Leary, S. P., Chen, X., & Johnston, V. (2018) · Scandinavian Journal of Work Environment & Health · doi:10.5271/sjweh.3760 · Cited by 148
“These were used due to the longitudinal design of the study and to accommodate missing data points, which occur frequently in longitudinal studies (25).”
A role for metamemory in cognitive offloading
Hu, X., Luo, L., & Fleming, S. M. (2019) · Cognition · doi:10.1016/j.cognition.2019.104012 · Cited by 121
“In contrast, linear mixed effect models can handle missing data and incorporate all of the existing data into the model (Krueger & Tian, 2004).”
MethodFang, Y., Forger, D. B., Frank, E., Sen, S., & Goldstein, C. A. (2021) · npj Digital Medicine · doi:10.1038/s41746-021-00400-z · Cited by 107
Walker, E. A., Redfern, A., & Oleson, J. (2019) · Journal of Speech Language and Hearing Research · doi:10.1044/2018_jslhr-l-astm-18-0250 · Cited by 110
“The LMM approach has a number of advantages, particularly when researchers are working with dynamic longitudinal data sets (Krueger & Tian, 2004).”
BackgroundMethodInfluentialEquivalence and Noninferiority Testing in Regression Models and Repeated-Measures Designs
Mascha, E. J., & Sessler, D. I. (2011) · Anesthesia & Analgesia · doi:10.1213/ane.0b013e318206f872 · Cited by 101
Kalmbach, D. A., Fang, Y., Arnedt, J. T., Cochran, A. L., Deldin, P. J., Kaplin, A. I., & Sen, S. (2018) · Journal of General Internal Medicine · doi:10.1007/s11606-018-4373-2 · Cited by 113
Hasan, A., Guse, B., Cordes, J., Wölwer, W., Winterer, G., Gäebel, W., Langguth, B., Landgrebe, M., Eichhammer, P., Frank, E., et al. (2015) · Schizophrenia Bulletin · doi:10.1093/schbul/sbv142 · Cited by 113
Acute Physiological Stress and Mortality Following Fire in a Long-Unburned Longleaf Pine Ecosystem
O’Brien, J. J., Hiers, J. K., Mitchell, R. J., Varner, J. M., & Mordecai, K. (2010) · Fire Ecology · doi:10.4996/fireecology.0602001 · Cited by 94
Determinants of personal, indoor and outdoor VOC concentrations: An analysis of the RIOPA data
Su, F., Mukherjee, B., & Batterman, S. (2013) · Environmental Research · doi:10.1016/j.envres.2013.08.005 · Cited by 91
“Linear mixed-effect models (LMMs) that incorporated fixed and random effects and repeated measures (Krueger and Tian, 2004) were estimated for outdoor, indoor and personal measurements using the variables selected by the stepwise models.”
MethodUsing multilevel models for the analysis of event-related potentials
Volpert‐Esmond, H. I., Page‐Gould, E., & Bartholow, B. D. (2021) · International Journal of Psychophysiology · doi:10.1016/j.ijpsycho.2021.02.006 · Cited by 99
Warby, S. A., Ford, J. J., Hahne, A. J., Watson, L., Balster, S. M., Lenssen, R., & Pizzari, T. (2017) · The American Journal of Sports Medicine · doi:10.1177/0363546517734508 · Cited by 97
“Continuous data were analyzed with linear mixed models, given its advantages in modeling repeated measures over time and adjusting for baseline scores.(26) Missing continuous data were accounted for by restricted maximum likelihood estimation within the linear mixed models.”
MethodMangroves Enhance Reef Fish Abundance at the Caribbean Regional Scale
Serafy, J. E., Shideler, G. S., Araújo, R. J., & Nagelkerken, I. (2015) · PLoS ONE · doi:10.1371/journal.pone.0142022 · Cited by 85
The Effect of a Whey Protein Supplement on Bone Mass in Older Caucasian Adults
Kerstetter, J. E., Bihuniak, J. D., Brindisi, J., Sullivan, R., Mangano, K. M., Larocque, S., Kotler, B. M., Simpson, C. A., Cusano, A. M., Gaffney‐Stomberg, E., et al. (2015) · The Journal of Clinical Endocrinology & Metabolism · doi:10.1210/jc.2014-3792 · Cited by 96
Narayan, C. R., & McDermott, L. C. (2016) · The Journal of the Acoustical Society of America · doi:10.1121/1.4944634 · Cited by 98
“Although mixed-effects models are generally considered robust with longitudinal data with missing values (cf. Krueger and Tian, 2004; Verbeke and Molenberghs, 2009, p. 215), we nonetheless entertain the possibility that the significant effect of time in the model is an artifact of the attrition of…”
BackgroundRestorative effects of urban park soundscapes on children’s psychophysiological stress
Shu, S., & Ma, H. (2020) · Applied Acoustics · doi:10.1016/j.apacoust.2020.107293 · Cited by 94
Haugaasen, M., Toering, T., & Jordet, G. (2014) · Psychology of sport and exercise · doi:10.1016/j.psychsport.2014.02.007 · Cited by 97
Effect of Client-Therapist Gender Match on the Therapeutic Relationship: An Exploratory Analysis
Bhati, K. S. (2014) · Psychological Reports · doi:10.2466/21.02.pr0.115c23z1 · Cited by 79
“…because it has the ability to accommodate an unbalanced data set (in this case, diff erent numbers of participants in each group) and to accommodate observations conducted with a fl exible time schedule ( Krueger & Tian, 2004 ; in this case, observations occurred at varying sessions and numbers).”
BackgroundBreaks in Sitting Time: Effects on Continuously Monitored Glucose and Blood Pressure
Bhammar, D. M., Sawyer, B. J., Tucker, W. J., & Gaesser, G. A. (2017) · Medicine & Science in Sports & Exercise · doi:10.1249/mss.0000000000001315 · Cited by 85
Hasan, S., van Hamersveld, K. T., de Mheen, P. J. M., Kaptein, B. L., Nelissen, R. G. H. H., & Toksvig‐Larsen, S. (2020) · The Bone & Joint Journal · doi:10.1302/0301-620x.102b8.bjj-2020-0054.r1 · Cited by 74
Meditation in a Deep South Prison: A Longitudinal Study of the Effects of Vipassana
Perelman, A. M., Miller, S. L., Clements, C. B., Rodriguez, A., Allen, K., & Cavanaugh, R. (2012) · Journal of Offender Rehabilitation · doi:10.1080/10509674.2011.632814 · Cited by 73
“LMM is an analysis method that treats each observation point individually and controls for the effect of participant, thus allowing the use of data from participants for whom some observations may be missing (Krueger & Tian, 2004).”
MethodPaskins, K. E., Bowyer, A., Megill, W., & Scheibe, J. S. (2007) · Journal of Experimental Biology · doi:10.1242/jeb.02747 · Cited by 73
“Owing to the number of missing data points, the typical multivariate ANOVA could not be applied to our data, and so a general mixed model (Krueger and Tian, 2004) was applied to both take-off and landing forces, with range as a fixed factor and squirrel ID a random factor.”
MethodInfluentialDowling, K., Simpkin, A. J., & Barry, M. M. (2019) · Journal of Youth and Adolescence · doi:10.1007/s10964-019-00987-3 · Cited by 103
Motor tract integrity predicts walking recovery
Soulard, J., Huber, C., Baillieul, S., Thuriot, A., Renard, F., Broche, B. A., Krainik, A., Vuillerme, N., Jaillard, A. S., & on behalf of the ISIS-HERMES Group (2020) · Neurology · doi:10.1212/wnl.0000000000008755 · Cited by 68
Undurraga, J. A., Carlyon, R. P., Wouters, J. M., & Wieringen, A. V. (2013) · Journal of the Association for Research in Otolaryngology · doi:10.1007/s10162-013-0377-0 · Cited by 67
“LME models were chosen since they can deal with unbalanced data, complex modeling of random effects variables, and can account for nonsphericity (Krueger and Tian, 2004; Baayen et al., 2008; Wierda et al., 2010; Newman et al., 2011).”
MethodFreitag, J., Ford, J. J., Bates, D., Boyd, R. L., Hahne, A. J., Wang, Y., Cicuttini, F., Huguenin, L., Norsworthy, C. J., & Shah, K. (2015) · BMJ Open · doi:10.1136/bmjopen-2015-009332 · Cited by 67
Associations Between Self-Monitoring and Weight Change in Behavioral Weight Loss Interventions
Goldstein, S. P., Goldstein, C. M., Bond, D. S., Raynor, H. A., Wing, R. R., & Thomas, J. G. (2019) · Health Psychology · doi:10.1037/hea0000800 · Cited by 63
“Missing weights were not imputed because the proposed analyses accommodate multiple missing data points by including a random effect of subject (Edwards, 2000; Krueger & Tian, 2004).”
Racinais, S., Buchheit, M., & Girard, O. (2014) · Frontiers in Physiology · doi:10.3389/fphys.2014.00142 · Cited by 77
“This procedure has ability to accommodate missing data (Krueger and Tian, 2004).”
BackgroundFive-year longitudinal treatment outcomes of the ISTAR Comprehensive Stuttering Program
Langevin, M., Kully, D., Teshima, S., Hagler, P., & Narasimha Prasad, N. G. (2010) · Journal of Fluency Disorders · doi:10.1016/j.jfludis.2010.04.002 · Cited by 64
Heise, M. J., Mon, S. K., & Bowman, L. C. (2022) · Developmental Cognitive Neuroscience · doi:10.1016/j.dcn.2022.101070 · Cited by 71
“…variables (e.g., anxiety levels), there are Type II errors M.J. Heise et al. Developmental Cognitive Neuroscience 54 (2022) 101070 in models with a single predictor and Type I errors when there are multiple predictors (Irwin and McClelland, 2003; Krueger and Tian, 2004; Maxwell and Delaney, 1993).”
BackgroundMindful Parenting Training in a Clinical Versus Non-Clinical Setting: An Explorative Study
Potharst, E. S., Baartmans, J. M. D., & Bögels, S. M. (2018) · Mindfulness · doi:10.1007/s12671-018-1021-1 · Cited by 74
“…pre-test and follow-up (main effect of time using dummy codes), and differences in improvements over time between settings (interaction effect of setting × time) were tested using multilevel regression models that are known to accommodate missing data (Bagiella et al. 2000; Krueger and Tian 2004).”
MethodA Deeper Look at the NASA TLX and Where It Falls Short
McKendrick, R. D., & Cherry, E. (2018) · Proceedings of the Human Factors and Ergonomics Society Annual Meeting · doi:10.1177/1541931218621010 · Cited by 61
“Further, these model’s assumptions are robust to missing data, unequal numbers of observations per experimental condition, unequal measurement distance between time points, and better estimation of population effects (Baayen et al., 2008; Krueger & Tian, 2004; Laird & Ware, 1982).”
BackgroundLevy, D. M., Wobbrock, J. O., Kaszniak, A. W., & Ostergren, M. (2012) · Graphics Interface · Cited by 92
The effect of oxytocin on biological motion perception in dogs (Canis familiaris)
Kovács, K., Kis, A., Kanizsàr, O., Hernádi, A., Gácsi, M., & Topál, J. (2016) · Animal Cognition · doi:10.1007/s10071-015-0951-4 · Cited by 64
Batterman, S., Su, F., Li, S., Mukherjee, B., & Jia, C. (2014) · PubMed · Cited by 61
Oehler, C., Görges, F., Rogalla, M., Rummel‐Kluge, C., & Hegerl, U. (2020) · Journal of Medical Internet Research · doi:10.2196/15361 · Cited by 61
“This approach was adopted to make the best use of incomplete data while minimizing the bias to the parameter estimations [38,39].”
Albers, P. H., Bojsen-Møller, K. N., Dirksen, C., Serup, A. K., Steenberg, D. E., Frystyk, J., Clausen, T. R., Kiens, B., Richter, E. A., Madsbad, S., et al. (2015) · American Journal of Physiology-Regulatory, Integrative and Comparative Physiology · doi:10.1152/ajpregu.00228.2014 · Cited by 63
“This model is an appropriate statistical model when dealing with missing data points (refer to Table 1 for variation in the number of tissue biopsies throughout the study) (35).”
MethodParsons, D. N., Cordier, R., Lee, H., Falkmer, T., & Vaz, S. M. A. (2018) · Journal of Autism and Developmental Disorders · doi:10.1007/s10803-018-3734-3 · Cited by 74
Post-hatch heat warms adult beaks: irreversible physiological plasticity in Japanese quail
Burness, G., Huard, J. R., Malcolm, E., & Tattersall, G. J. (2013) · Proceedings of the Royal Society B Biological Sciences · doi:10.1098/rspb.2013.1436 · Cited by 55
Mid-Task Break Improves Global Integration of Functional Connectivity in Lower Alpha Band
Li, J., Lim, J., Chen, Y. S., Wong, K., Thakor, N. V., Bezerianos, A., & Sun, Y. (2016) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2016.00304 · Cited by 69
“Statistical Analysis Linear mixed model (LMM) (Krueger and Tian, 2004) with block and session as fixed effects and subject label as random effect was used to compare means of behavioral measures and connectivity metrics to determine whether there were statistically significant effects of blocks [two levels: the first…”
MethodInfluentialDelayed intramuscular human neurotrophin-3 improves recovery in adult and elderly rats after stroke
Duricki, D. A., Hutson, T. H., Kathe, C., Soleman, S., Gonzalez‐Carter, D., Petruska, J. C., Shine, H. D., Chen, Q., Wood, T., Bernanos, M., et al. (2015) · Brain · doi:10.1093/brain/awv341 · Cited by 56
Xiao, R., Shida-Tokeshi, J., Vanderbilt, D. L., & Smith, B. A. (2018) · PLoS ONE · doi:10.1371/journal.pone.0190276 · Cited by 59
Ami, D., Mereghetti, P., Leri, M., Giorgetti, S., Natalello, A., Doglia, S. M., Stefani, M., & Bucciantini, M. (2018) · Scientific Reports · doi:10.1038/s41598-018-30995-5 · Cited by 57
Fatigue in Gynecological Cancer Patients During and After Anticancer Treatment
Prue, G., Allen, J. M., Gracey, J. H., Rankin, J. P., & Cramp, F. L. (2009) · Journal of Pain and Symptom Management · doi:10.1016/j.jpainsymman.2009.06.011 · Cited by 54
“The RMM was chosen as it can be used to describe the temporal changes of a dependent variable in a data set with missing data, and it is capable of treating time as a categorical variable or a continuous variable.(23) To address the final aim of the study to examine the variables associated with fatigue in gynecologic…”
MethodZhou, Y., Li, G., Li, D., Cui, H., & Ning, Y. (2018) · Journal of Psychopharmacology · doi:10.1177/0269881118756062 · Cited by 56
“The linear mixed model can make full use of information of missing repeated measurement data (Krueger and Tian, 2004), because there were 10 patients who withdrew in this study and the data of the last visit was missing.”
Palacios, J. E., Richards, D., Palmer, R., Coudray, C., Hofmann, S. G., Palmieri, P. A., & Frazier, P. (2018) · JMIR Mental Health · doi:10.2196/11467 · Cited by 58
“Repeated measures ANOVA has been criticized because it uses listwise deletion [23], whereas LMM allows for more data points and subjects to be included in the model [24].”
MethodGratz, K. L., Dixon-Gordon, K. L., & Tull, M. T. (2014) · Personality Disorders: Theory, Research, and Treatment · doi:10.1037/per0000062 · Cited by 51
“…in te nd ed so le ly fo r th e pe rs on al us e of th e in di vi du al us er an d is no t to be di ss em in at ed br oa dl y. missing values can contribute to the estimation of the residual error and random intercept terms (Krueger & Tian, 2004), resulting in an ITT sample included in all analyses.”
BackgroundGuo, X., Tavakoli, A., Angulo, A. V., Robartes, E., Chen, T. D., & Heydarian, A. (2022) · Transportation Research Part F Traffic Psychology and Behaviour · doi:10.1016/j.trf.2022.11.015 · Cited by 59
“LMM facilitates the analysis as it has the ability to (1) characterize group and individual behavior patterns in a formal way, (2) acknowledge both group and individual differences, and (3) incorporate additional covariates [34].”
Transitions into and out of homelessness among street-involved youth in a Canadian setting
Cheng, T., Wood, E., Feng, C. X., Mathias, S., Montaner, J. S. G., Kerr, T. H., & DeBeck, K. (2013) · Health & Place · doi:10.1016/j.healthplace.2013.06.003 · Cited by 54
“The GLMM method was used in order to model group and individual differences simultaneously (Krueger and Tian, 2004), and describe the change in individual trajectories over time (Finucane et al.”
MethodImpact of a Supervised Worksite Exercise Program on Back and Core Muscular Endurance in Firefighters
Mayer, J. M., Quillen, W. S., Verna, J. L., Chen, R., Lunseth, P. A., & Dagenais, S. (2014) · American Journal of Health Promotion · doi:10.4278/ajhp.130228-quan-89 · Cited by 51
“A linear mixed effects model was selected because the sphericity assumption required for a repeated measures analysis of variance was violated, data were missing from the follow-up time points, and it accounted for the hierarchical structure and correlated measurements.(27) For the linear mixed effects model, the fixe…”
MethodLam, E. J., Gálvez, M. E., Cánovas, M., Montofré, Í. L., & Keith, B. (2017) · Journal of Soils and Sediments · doi:10.1007/s11368-017-1835-9 · Cited by 51
“Repeatedmeasurements ANOVA has not been used due to the low flexibility of this approach and to its sensitivity to missing data points (Krueger and Tian 2004).”
MethodUlaganathan, S., Read, S. A., Collins, M. J., & Vincent, S. J. (2019) · Experimental Eye Research · doi:10.1016/j.exer.2019.107850 · Cited by 55
Lee, J. E., Kahana, B., & Kahana, E. F. (2015) · Aging & Mental Health · doi:10.1080/13607863.2015.1013920 · Cited by 58
“…such as repeated measures of ANOVA, multilevel modeling is helpful for analyzing change using longitudinal data as it makes use of all available data from individual and emphasizes individual trajectories rather than average value at each occasion (Krueger & Tian, 2004; Singer & Willett, 2003).”
MethodDixon–Gordon, K. L., Turner, B. J., Rosenthal, M. Z., & Chapman, A. L. (2017) · Behavior Therapy · doi:10.1016/j.beth.2017.03.001 · Cited by 57
Perrier, J., Viard, A., Lévy, C., Morel, N., Allouache, D., Noal, S., Joly, F., Eustache, F., & Giffard, B. (2018) · Brain Imaging and Behavior · doi:10.1007/s11682-018-9991-0 · Cited by 51
Stott, D., Papastefanou, I., Paraschiv, D., Clark, K., & Kametas, N. A. (2017) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.17341 · Cited by 47
Holder, N. D., Holliday, R. P., Williams, R. C., Mullen, K. L., & Surís, A. (2017) · Cognitive Behaviour Therapy · doi:10.1080/16506073.2017.1357750 · Cited by 48
“…linear modeling (HLM) was used to analyze the data because it handles unbalanced designs and missing data efficiently, allowing the number of observations to vary across therapists more effectively than a standard repeated measure analysis of variance (Edwards, 2000; Krueger & Tian, 2004).”
MethodApplying mixed‐effects modeling to single‐subject designs: An introduction
DeHart, W. B., & Kaplan, B. A. (2019) · Journal of the Experimental Analysis of Behavior · doi:10.1002/jeab.507 · Cited by 48
Longitudinal Speech Recognition in Noise in Children: Effects of Hearing Status and Vocabulary
Walker, E. A., Sapp, C., Oleson, J., & McCreery, R. W. (2019) · Frontiers in Psychology · doi:10.3389/fpsyg.2019.02421 · Cited by 46
“This issue of inconsistent time points is a common obstacle in longitudinal research studies, as participants often start late, drop out, or skip test visits (Krueger and Tian, 2004).”
BackgroundFrancis, S. E. B., Shawyer, F., Cayoun, B., Enticott, J., & Meadows, G. N. (2022) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2022.815170 · Cited by 45
“An important advantage of the mixed model over repeated measures ANOVA is that the modeling of the individual participant variables can accommodate multiple missing data points in longitudinal datasets (55).”
MethodDo Speed and Proximity Affect Human-Robot Collaboration with an Industrial Robot Arm?
Story, M., Webb, P., Fletcher, S., Tang, G., Jaksic, C., & Carberry, J. (2022) · International Journal of Social Robotics · doi:10.1007/s12369-021-00853-y · Cited by 51
Donor Quality of Life up to Two Years After Living Donor Liver Transplantation
Kröncke, S., Nashan, B., Fischer, L., Erim, Y., & Schulz, K. (2013) · Transplantation · doi:10.1097/01.tp.0000438206.04348.b2 · Cited by 45
“mixed-effects model analysis was performed (27, 28).”
Hotta, G. H., Couto, A. G. D. A., Cools, A. M. J., McQuade, K. J., & de Oliveira, A. S. (2020) · Musculoskeletal Science and Practice · doi:10.1016/j.msksp.2020.102171 · Cited by 44
Khojasteh, N., & Won, A. S. (2021) · Frontiers in Virtual Reality · doi:10.3389/frvir.2021.643331 · Cited by 48
“Such models have advantages over repeated measure ANOVAs, such as handling missing values (e.g., for participants who did not fi nish all fi ve sessions, see Krueger and Tian (2004) for details).”
BackgroundFossé, Q., Poulard, T., Nierat, M., Virolle, S., Morawiec, É., Hogrel, J., Similowski, T., Demoule, A., Gennisson, J., Bachasson, D., et al. (2020) · Critical Care · doi:10.1186/s13054-020-03338-y · Cited by 47
“Linear mixed models were chosen over traditional two-way repeated ANOVAs given their ability to handle unbalanced data [33].”
MethodKemmerer, S. K., Sack, A. T., de Graaf, T. A., ten Oever, S., Weerd, P. D., & Schuhmann, T. (2022) · Brain Research · doi:10.1016/j.brainres.2022.147834 · Cited by 44
Overmeer, T., Peterson, G., Landén Ludvigsson, M., & Peolsson, A. (2016) · Medicine · doi:10.1097/md.0000000000004430 · Cited by 42
Wayfinding in ageing and Alzheimer's disease within a virtual senior residence: study protocol
Davis, R., & Ohman, J. M. (2016) · Journal of Advanced Nursing · doi:10.1111/jan.12945 · Cited by 47
“Also, it allows for the modeling of nonlinear changes in the dependent variables (Krueger & Tian 2004).”
Andela, C. D., Repping‐Wuts, H., Stikkelbroeck, N. M. M. L., Pronk, M. C., Tiemensma, J., Hermus, A. R., Kaptein, A. A., Pereira, A. M., Kamminga, N. G. A., & Biermasz, N. R. (2017) · European Journal of Endocrinology · doi:10.1530/eje-16-1015 · Cited by 45
Borges, L. M., Holliday, R. P., Barnes, S. M., Bahraini, N. H., Kinney, A. R., Forster, J. E., & Brenner, L. A. (2021) · PLoS ONE · doi:10.1371/journal.pone.0260033 · Cited by 47
“, repeated measure analysis of variance) [21,22].”
Socio‐economic benefits from protected areas in southeastern Australia
Heagney, E., Kovac, M., Fountain, J., & Conner, N. (2015) · Conservation Biology · doi:10.1111/cobi.12554 · Cited by 50
“A GLMM is considered best practice for longitudinal studies because it can accommodate missing data (Krueger & Tian 2004) and enables simultaneous analysis of both fixed and random effects (Heck et al. 2010).”
MethodBadrov, M. B., Park, S. Y., Yoo, J., Hieda, M., Okada, Y., Jarvis, S. S., Stickford, A. S. L., Best, S. A., Nelson, D. B., & Fu, Q. (2018) · Hypertension · doi:10.1161/hypertensionaha.118.12137 · Cited by 41
Energetic consequences of plunge diving in gannets
Green, J. A., White, C. R., Bunce, A., Frappell, P., & Butler, P. (2009) · Endangered Species Research · doi:10.3354/esr00223 · Cited by 41
“…a general linear mixed model (GLMM) with time as a fixed ordinal factor and bird ID and dive number (#, nested within bird ID) as random nominal factors (see Krueger & Tian 2004 for a comparison of GLMM and RM methods for the analysis of longitudinal data). α was set at 0.05 for all comparisons.”
InfluentialWell-Being Reduces COVID-19 Anxiety: A Three-Wave Longitudinal Study in China
Wang, Z., Luo, S., Xu, J., Wang, Y., Yun, H., Zhan, H., Zhan, H., & Wang, Y. (2021) · Journal of Happiness Studies · doi:10.1007/s10902-021-00385-2 · Cited by 41
“…results: (1) data with a relatively high rate of nonrandom missing responses, (2) high variability among participants, and (3) the fact that the response of the participants might depend on their past making the data nonindependent (Baayen et al., 2008; Bagiella et al., 2000; Krueger & Tian, 2004).”
BackgroundChapman, A. L., Rosenthal, M. Z., Dixon–Gordon, K. L., Turner, B. J., & Kuppens, P. (2016) · Journal of Personality Disorders · doi:10.1521/pedi_2016_30_264 · Cited by 43
Helms, C. M., Rau, A. R., Shaw, J. K., Stull, C., Gonzales, S. W., & Grant, K. A. (2014) · Psychopharmacology · doi:10.1007/s00213-013-3417-x · Cited by 37
van Keizerswaard, J., de Loos, A. D., Louwers, Y. V., & Laven, J. S. E. (2022) · Fertility and Sterility · doi:10.1016/j.fertnstert.2022.01.014 · Cited by 45
Models for the analysis of repeated continuous outcome measures in clinical trials
Livera, A. M. D., Zaloumis, S. G., & Simpson, J. A. (2013) · Respirology · doi:10.1111/resp.12217 · Cited by 37
Metadata
- Authors
- Krueger, C., & Tian, L.
- Affiliations
- University of Florida Health (US)
- University of Florida (US)
- Corresponding author
- Krueger, Charlene
- Venue
- Biological Research For Nursing
- Publisher
- SAGE Publications
- Published
- 2004-10
- Volume
- 6
- Issue
- 2
- Pages
- 151-157
- ISSN
- 1099-8004 (ISSN-L)
- 1552-4175
- OpenAlex
- W2113087290
- Cited by
- 561
- References
- 23
- Citations by year
- 2026: 37 · 2025: 45 · 2024: 52 · 2023: 33 · 2022: 52 · 2021: 54 · 2020: 43 · 2019: 42 · 2018: 36 · 2017: 30 · 2016: 34 · 2015: 23 · 2014: 19 · 2013: 17 · 2012: 11
- FWCI
- 2.36
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- journals.sagepub.com/page/policies/text-and-data-mining-license (tdm)
- Locations
- Biological Research For Nursing (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Life Sciences › Agricultural and Biological Sciences › Agronomy and Crop Science › Agriculture, Soil, Plant Science
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Applications
- Keywords
- general linear mixed model, repeated measures ANOVA, missing data, longitudinal analysis, model comparison, nursing research
- MeSH terms
- Analysis of Variance, Female, Heart Rate, Fetal, Humans, Longitudinal Studies, Pregnancy, Linear Models
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.