Missing Data in Randomized Clinical Trials for Weight Loss: Scope of the Problem, State of the Field, and Performance of Statistical Methods
Open accessThe DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
BACKGROUND: Dropouts and missing data are nearly-ubiquitous in obesity randomized controlled trails, threatening validity and generalizability of conclusions. Herein, we meta-analytically evaluate the extent of missing data, the frequency with which various analytic methods are employed to accommodate dropouts, and the performance of multiple statistical methods. METHODOLOGY/PRINCIPAL FINDINGS: We searched PubMed and Cochrane databases (2000-2006) for articles published in English and manually searched bibliographic references. Articles of pharmaceutical randomized controlled trials with weight loss or weight gain prevention as major endpoints were included. Two authors independently reviewed each publication for inclusion. 121 articles met the inclusion criteria. Two authors independently extracted treatment, sample size, drop-out rates, study duration, and statistical method used to handle missing data from all articles and resolved disagreements by consensus. In the meta-analysis, drop-out rates were substantial with the survival (non-dropout) rates being approximated by an exponential decay curve (e(-lambdat)) where lambda was estimated to be .0088 (95% bootstrap confidence interval: .0076 to .0100) and t represents time in weeks. The estimated drop-out rate at 1 year was 37%. Most studies used last observation carried forward as the primary analytic method to handle missing data. We also obtained 12 raw obesity randomized controlled trial datasets for empirical analyses. Analyses of raw randomized controlled trial data suggested that both mixed models and multiple imputation performed well, but that multiple imputation may be more robust when missing data are extensive. CONCLUSION/SIGNIFICANCE: Our analysis offers an equation for predictions of dropout rates useful for future study planning. Our raw data analyses suggests that multiple imputation is better than other methods for handling missing data in obesity randomized controlled trials, followed closely by mixed models. We suggest these methods supplant last observation carried forward as the primary method of analysis.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures



Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Dropout during lifestyle intervention studies is unfortunately a common phenomenon, and general weight loss programmes have reported discontinuation rates of around 40% (Elobeid et al., 2009).”
From Improvements in PCOS characteristics and phenotype severity during a randomized controlled lifestyle intervention (2021) · cites this paper as Elobeid et al., 2009
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Whenever appropriate, we are going to use multiple imputation methods [71].”
In the citing paper
“With a ratio of 1:1:1, the required sample was 42 in each group. With an expected drop-out proportion of 40% [40], 60 participants in each group were needed for the study.”
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Multiple Imputation for Nonresponse in Surveys
Rubin, D. B. (1987) · Wiley Series in Probability and Statistics · doi:10.1002/9780470316696 · Cited by 20,701
Statistical Analysis With Missing Data
Lahiff, M., Little, R. J. A., & Rubin, D. B. (1989) · Journal of the American Statistical Association · doi:10.2307/2289883 · Cited by 17,265
Prevalence of Overweight and Obesity in the United States, 1999-2004
Ogden, C. L., Carroll, M. D., Curtin, L. R., McDowell, M. A., Tabak, C. J., & Flegal, K. M. (2006) · JAMA · doi:10.1001/jama.295.13.1549 · Cited by 8,720
Analysis of Incomplete Multivariate Data
Schafer, J. L. (1997) · doi:10.1201/9781439821862 · Cited by 6,012
Analysis of Incomplete Multivariate Data
Booth, D. E. (2000) · Technometrics · doi:10.1080/00401706.2000.10486013 · Cited by 5,627 · cited 3×
“Lastly, even if the MI model is incorrect, inferences made from the model of interest tend to remain valid [9].”
BackgroundMethodLittell, R. C., Milliken, G. A., Stroup, W. W., Wolfinger, R. D., & Schabenberger, O. (2006) · CERN Document Server (European Organization for Nuclear Research) · Cited by 2,924
Years of Life Lost Due to Obesity
Fontaine, K. R., Redden, D. T., Wang, C., Westfall, A. O., & Allison, D. B. (2003) · JAMA · doi:10.1001/jama.289.2.187 · Cited by 2,495 · cited 1×
“Obesity is associated with and believed to cause adverse conditions such as cardiovascular disease, stroke, type 2 diabetes mellitus, certain forms of cancer [2], and decreased longevity [3].”
BackgroundSelf-citationMiscellanea. Small-sample degrees of freedom with multiple imputation
Barnard, J. (1999) · Biometrika · doi:10.1093/biomet/86.4.948 · Cited by 829 · cited 2×
“The data were then imputed by assuming a monotone missing data pattern using the regression method proposed by Rubin [11].”
MethodRandomized Trial of Lifestyle Modification and Pharmacotherapy for Obesity
Wadden, T. A., Berkowitz, R. I., Womble, L. G., Sarwer, D. B., Phelan, S., Cato, R. K., Hesson, L. A., Osei, S. Y., Kaplan, R., & Stunkard, A. J. (2005) · New England Journal of Medicine · doi:10.1056/nejmoa050156 · Cited by 794 · cited 2×
“10 DPP [6] 2103 242 48 months Metformin 9 11 NPY-1 [26] 206 159 12 Neuropeptide Y5R 5”
BackgroundCalle, E. E., & Thun, M. J. (2004) · Oncogene · doi:10.1038/sj.onc.1207751 · Cited by 769
Research works printed but not linked: 1
- Coffey CS Steiner DJ Baker BA Mullinax C Allison DB 2002 Safety of an herbal formulation including ephedra alkaloids dosed intermittently or continuously for weight control. FASEB 16(4) A649 A649
Cited by
Fuller, N. R., Colagiuri, S., Schofield, D., Olson, A. D., Shrestha, R., Holzapfel, C., Wolfenstetter, S. B., Holle, R., Ahern, A. L., Hauner, H., et al. (2013) · International Journal of Obesity · doi:10.1038/ijo.2012.139 · Cited by 2,117
Abed, H. S., Wittert, G. A., Leong, D. P., Shirazi, M. G., Bahrami, B., Middeldorp, M. E., Lorimer, M. F., Lau, D. H., Antic, N. A., Brooks, A. G., et al. (2013) · JAMA · doi:10.1001/jama.2013.280521 · Cited by 776
Allison, D. B., Gadde, K. M., Garvey, W. T., Peterson, C. A., Schwiers, M. L., Najarian, T., Tam, P. Y., Troupin, B., & Day, W. W. (2012) · Obesity · doi:10.1038/oby.2011.330 · Cited by 711
“This dropout rate is consistent with what one would expect at 56 weeks in obesity trials based on a published meta-analytic prediction equation (24) and lower than the 50% dropout recently reported with two other phase 3 obesity RCTs (33,34).”
ResultSelf-citationMultiple Imputation: A Flexible Tool for Handling Missing Data
Li, P., Stuart, E. A., & Allison, D. B. (2015) · JAMA · doi:10.1001/jama.2015.15281 · Cited by 621
Self-citationScreening and brief intervention for obesity in primary care: a parallel, two-arm, randomised trial
Aveyard, P., Lewis, A., Tearne, S., Hood, K., Christian-Brown, A., Adab, P., Begh, R., Jolly, K., Daley, A., Farley, A., et al. (2016) · The Lancet · doi:10.1016/s0140-6736(16)31893-1 · Cited by 297
Singh, N. A., Quine, S., Clemson, L. M., Williams, E. J., Williamson, D. A., Stavrinos, T. M., Grady, J. N., Perry, T. J., Lloyd, B. D., Smith, E. U. R., et al. (2012) · Journal of the American Medical Directors Association · doi:10.1016/j.jamda.2011.08.005 · Cited by 274
Josse, A. R., Atkinson, S. A., Tarnopolsky, M. A., & Phillips, S. M. (2011) · The Journal of Nutrition · doi:10.3945/jn.111.141028 · Cited by 187
“In accordance with recently suggested practices for randomized weight loss trials (39), we conducted an intentto-treat analysis where missing data values were imputed using modelbased multiple imputation.”
MethodAhern, A. L., Wheeler, G. M., Aveyard, P., Boyland, E. J., Halford, J. C. G., Mander, A. P., Woolston, J., Thomson, A. M., Tsiountsioura, M., Cole, D., et al. (2017) · The Lancet · doi:10.1016/s0140-6736(17)30647-5 · Cited by 218
Garvey, W. T., Ryan, D. H., Henry, R., Bohannon, N. J. V., Toplak, H., Schwiers, M., Troupin, B., & Day, W. W. (2014) · Diabetes Care · doi:10.2337/dc13-1518 · Cited by 215
“To accommodate missing data, multiple imputation (MI) was applied to all end points where missing data were apparent using, specifically, a 2-step imputation process with m = 5 imputations per step (29).”
MethodBest, J. R., Chiu, B. K., Liang Hsu, C., Nagamatsu, L. S., & Liu-Ambrose, T. (2015) · Journal of the International Neuropsychological Society · doi:10.1017/s1355617715000673 · Cited by 201
“This approach has been shown to provide less biased estimates and to increase generalizability in comparison to deletion approaches that remove individuals with missing follow-up data (Elobeid et al., 2009).”
ResultBischoff, S. C., Damms-Machado, A., Betz, C., Herpertz, S., Legenbauer, T., Löw, T., Wechsler, J. G., Bischoff, G., Austel, A., & Ellrott, T. (2012) · International Journal of Obesity · doi:10.1038/ijo.2011.107 · Cited by 168
Lintvedt, O. K., Griffiths, K. M., Sørensen, K., Østvik, A. R., Wang, C. E. A., Eisemann, M., & Waterloo, K. (2013) · Clinical Psychology & Psychotherapy · doi:10.1002/cpp.770 · Cited by 157
Attrition in developmental psychology: A review of modern missing data reporting and practices
Nicholson, J. S., Deboeck, P. R., & Howard, W. (2016) · International Journal of Behavioral Development · doi:10.1177/0165025415618275 · Cited by 192
Franklin, J. M., Schneeweiß, S., Polinski, J. M., & Rassen, J. A. (2013) · Computational Statistics & Data Analysis · doi:10.1016/j.csda.2013.10.018 · Cited by 187
“Merging this concept with simulation techniques has led to several studies of methods performance that use real observed data augmented with simulated data (Elobeid et al., 2009; Gadbury et al., 2008).”
MethodSharing health data: good intentions are not enough
Pisani, E., & AbouZahr, C. (2010) · Bulletin of the World Health Organization · doi:10.2471/blt.09.074393 · Cited by 135
Shuxian, W., Renzaho, A. M. N., Hall, B. J., Shi, L., Ling, L., & Chen, W. L. (2020) · The Lancet Psychiatry · doi:10.1016/s2215-0366(20)30422-3 · Cited by 138
Bell, K. E., Snijders, T., Zulyniak, M., Kumbhare, D., Parise, G., Chabowski, A., & Phillips, S. M. (2017) · PLOS ONE · doi:10.1371/journal.pone.0181387 · Cited by 99
Egan, S. J., van Noort, E., Chee, A., Kane, R. T., Hoiles, K. J., Shafran, R., & Wade, T. D. (2014) · Behaviour Research and Therapy · doi:10.1016/j.brat.2014.09.009 · Cited by 101
Brown, A. W., Li, P., Brown, M. M. B., Kaiser, K. A., Keith, S. W., Oakes, J. M., & Allison, D. B. (2015) · American Journal of Clinical Nutrition · doi:10.3945/ajcn.114.105072 · Cited by 104
Self-citationDeFina, L. F., Marcoux, L. G., Devers, S. M., Cleaver, J. P., & Willis, B. L. (2011) · The American Journal of Clinical Nutrition · doi:10.3945/ajcn.110.002741 · Cited by 89
“The issue of the dropout rate in weight-loss trials is problematic, with a recent review predicting that a good retention rate would be 63% at 12 mo (35).”
BackgroundBest (but oft-forgotten) practices: missing data methods in randomized controlled nutrition trials
Li, P., & Stuart, E. A. (2018) · American Journal of Clinical Nutrition · doi:10.1093/ajcn/nqy271 · Cited by 92
“A review of 121 RCTs for weight loss suggests that the drop-out rates range from 0% to 80% and increase with the duration of the trials (2).”
BackgroundNikles, J., Mitchell, G. K., Schlüter, P. J., Good, P. D., Hardy, J. R., Rowett, D. S., Shelby‐James, T., Vohra, S., & Currow, D. C. (2010) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2010.05.009 · Cited by 93
“The estimated dropout rate at 1 year was 37% in a meta-analysis of 121 obesity studies [30].”
BackgroundZonisamide for Weight Reduction in Obese Adults: A 1-Year Randomized Controlled Trial
Gadde, K. M., Kopping, M. F., Wagner, H. R., Yonish, G. M., Allison, D. B., & Bray, G. A. (2012) · Archives of Internal Medicine · doi:10.1001/2013.jamainternmed.99 · Cited by 79
“Many past imputation strategies, including last observation carried forward (LOCF) and completer analysis, often provide biased results(12) and are no longer favored relative to full likelihood-based and multiple imputation procedures, both of which are less subject to bias and inconsistencies under satisfying assumpt…”
Self-citationJiskoot, G., Dietz de Loos, A., Beerthuizen, A., Timman, R., Busschbach, J., & Laven, J. (2020) · PLOS ONE · doi:10.1371/journal.pone.0233876 · Cited by 76
“With an expected drop-out proportion of 40% [40], 60 participants in each group were needed for the study.”
BackgroundMethodJanssen, V. R., Gucht, V. D., van Exel, H. J., & Maes, S. (2013) · Journal of Behavioral Medicine · doi:10.1007/s10865-012-9489-y · Cited by 101
“Multiple imputation is a missing-data technique that calculates plausible estimates of missing values using the other outcome and control variables as predictors, and has been shown to be more robust than other methods of handling missing data in trials (Elobeid et al., 2009).”
MethodBehavioral weight loss for the management of menopausal hot flashes: a pilot study
Thurston, R. C., Ewing, L. J., Low, C. A., Christie, A. J., & Levine, M. D. (2014) · Menopause The Journal of The North American Menopause Society · doi:10.1097/gme.0000000000000274 · Cited by 79
Haufe, S., Haas, V., Utz, W., Birkenfeld, A. L., Jeran, S., Böhnke, J., Mähler, A., Luft, F. C., Schulz-Menger, J., Boschmann, M., et al. (2013) · Diabetes Care · doi:10.2337/dc13-0102 · Cited by 72
“Based onmathematical models estimating discontinuation rates in dietary intervention studies (38,39), the rate in our study is in the expected range.”
BackgroundShin, H., Shin, J., Liu, P., Dutton, G. R., Abood, D. A., & Ilich, J. Z. (2011) · Nutrition Research · doi:10.1016/j.nutres.2011.09.022 · Cited by 81
“This method is widely used in many weight loss studies to handle missing data [19].”
MethodDealing with missing outcome data in meta‐analysis
Mavridis, D., & White, I. R. (2020) · Research Synthesis Methods · doi:10.1002/jrsm.1349 · Cited by 65
“Some authors argue that the ITT principle requires missing values to be imputed, using methods such as last observation carried forward (LOCF) or multiple imputation.(8) From a statistical perspective, any analysis of a study with missing data makes an assumption about the missing data.”
Nilsen, V., Bakke, P. S., & Gallefoss, F. (2011) · BMC Public Health · doi:10.1186/1471-2458-11-893 · Cited by 66
“A meta analysis of 121 pharmaceutical randomised controlled trials with weight loss or weight gain prevention as major end points, found a drop-out rate of 37% at one year [29].”
MethodThe limits and challenges of antiobesity pharmacotherapy
Gadde, K. M., & Atkins, K. D. (2020) · Expert Opinion on Pharmacotherapy · doi:10.1080/14656566.2020.1748599 · Cited by 65
“High attrition introduces a serious bias and the results can be uninterpretable regardless of how sophisticated the imputation procedures are, when primary outcome data are missing for half of the study participants [78, 79].”
BackgroundSelf-citationEffects of Calorie Restriction in Obese Older Adults: The CROSSROADS Randomized Controlled Trial
Ard, J. D., Gower, B., Hunter, G., Ritchie, C. S., Roth, D. L., Goss, A., Wingo, B. C., Bodner, E. V., Brown, C. J., Bryan, D., et al. (2016) · The Journals of Gerontology Series A: Biological Sciences and Medical Sciences · doi:10.1093/gerona/glw237 · Cited by 64
“We used a multiple imputation strategy using PROC MI and PROC MIANALYZE in SAS to create eight data sets to impute missing data at 6 and 12 months because it makes use of the broad array of data available to produce unbiased parameter estimates (28,29).”
MethodWharton, S., Astrup, A., Endahl, L., Lean, M. E. J., Satylganova, A., Skovgaard, D., Wadden, T. A., & Wilding, J. P. H. (2021) · International Journal of Obesity · doi:10.1038/s41366-020-00733-x · Cited by 58
Schneider, K. L., Panza, E., Handschin, B., Ma, Y., Busch, A. M., Waring, M. E., Appelhans, B. M., Whited, M. C., Keeney, J., Kern, D., et al. (2016) · Behavior Therapy · doi:10.1016/j.beth.2015.10.005 · Cited by 62
“Elobeid et al. (2009) examined different strategies for dealing with missing data, including mixed models and last observation carried forward in weight loss trials.”
37 DEPRESSION SCORES PREDICT ADHERENCE IN A DIETARY WEIGHT LOSS INTERVENTION TRIAL
Somerset, S. M., Graham, L., & Markwell, K. (2011) · Atherosclerosis Supplements · doi:10.1016/j.clnu.2011.04.004 · Cited by 63
Janssen, V. R., Gucht, V. D., van Exel, H. J., & Maes, S. (2012) · European Journal of Preventive Cardiology · doi:10.1177/2047487312441728 · Cited by 59
“Multiple imputation is a missingdata technique that calculates plausible estimates of missing values using the other outcome and control variables as predictors and has been shown to be more robust than other methods of handling missing data in trials.(44) Because the data showed an arbitrary missing data pattern, the…”
MethodCaldwell, A. E., Gorczyca, A. M., Bradford, A. P., Nicklas, J. M., Montgomery, R. N., Smyth, H., Pretzel, S. M., Nguyen, T. B., DeSanto, K., Ernstrom, C. J., et al. (2024) · Fertility and Sterility · doi:10.1016/j.fertnstert.2024.02.038 · Cited by 57
Hjelmesaeth, J. S., Rosenvinge, J. H., Gade, H., & Friborg, O. (2018) · Obesity Surgery · doi:10.1007/s11695-018-3471-x · Cited by 51
Batterham, M. J., Tapsell, L. C., & Charlton, K. E. (2015) · Obesity Research & Clinical Practice · doi:10.1016/j.orcp.2015.05.005 · Cited by 46
Imputation strategies for missing binary outcomes in cluster randomized trials
Ma, J., Akhtar-Danesh, N., Dolovich, L., Thabane, L., & the CHAT investigators (2011) · BMC Medical Research Methodology · doi:10.1186/1471-2288-11-18 · Cited by 45
“These amounts of missingness were chosen to cover the range of possible missingness in practice [30].”
Weight change among people randomized to minimal intervention control groups in weight loss trials
Johns, D. J., Hartmann‐Boyce, J., Jebb, S. A., Aveyard, P., & on behalf of the Behavioural Weight Management Review Group (2016) · Obesity · doi:10.1002/oby.21255 · Cited by 45
“It is conceivable that multiple imputation at the individual level could be more conservative than BOCF, but a study that used several methods of imputing for missing weight data in trials of interventions for weight loss found no great differences between complete case data only and multiple imputation for missing da…”
ResultGoals in Nutrition Science 2015–2020
Allison, D. B., Bassaganya-Riera, J., Burlingame, B., Brown, A. W., le Coutre, J., Dickson, S. L., van Eden, W., Garssen, J., Hontecillas, R., Khoo, C. S. H., et al. (2015) · Frontiers in Nutrition · doi:10.3389/fnut.2015.00026 · Cited by 45
Self-citationAbed, H. S., Nelson, A. J., Richardson, J. D., Worthley, S. G., Vincent, A. D., Wittert, G., & Leong, D. P. (2015) · American Heart Journal · doi:10.1016/j.ahj.2015.02.008 · Cited by 47
Jørgensen, A. W., Lundstrøm, L. H., Wetterslev, J., Astrup, A., & Gøtzsche, P. C. (2014) · PLoS ONE · doi:10.1371/journal.pone.0111964 · Cited by 40
“Thereare more reliable techniques for handling missing data [8], and they can also be used when missingness is MAR. Attention has been drawn to the multiple imputation (MI) technique [9], which for some time has been recommended for handling missing data in obesity trials [2].”
InfluentialA Pilot Study of the 8-Week Mindful Self-Compassion Training Program in a Chinese Community Sample
Finlay‐jones, A. L., Xie, Q., Huang, X., Ma, X., & Guo, X. (2017) · Mindfulness · doi:10.1007/s12671-017-0838-3 · Cited by 51
“The GLMM maximum likelihood procedure maximizes statistical power and reduces attrition-related bias by using all of the data available at each assessment (Elobeid et al. 2009; Kwok et al. 2008).”
MethodDietz de Loos, A. L. P., Jiskoot, G., Timman, R., Beerthuizen, A., Busschbach, J. J. V., & Laven, J. S. E. (2021) · Reproductive BioMedicine Online · doi:10.1016/j.rbmo.2021.05.008 · Cited by 39
Gewandter, J. S., McDermott, M. P., McKeown, A., Smith, S. M., Williams, M. R., Hunsinger, M., Farrar, J., Turk, D. C., & Dworkin, R. H. (2014) · Pain · doi:10.1016/j.pain.2014.06.018 · Cited by 39
“Few systematic studies have assessed the quality or clarity of reporting of methods to accommodate missing data in randomized clinical trials (RCTs) [2,6,11,31,32], and none of these studies has specifically investigated pain trials.”
Backgroundvan Wier, M. F., Dekkers, J. C., Hendriksen, I. J. M., Heymans, M. W., Ariëns, G. A. M., Pronk, N. P., Smid, T., & van Mechelen, W. (2011) · Journal of Occupational & Environmental Medicine · doi:10.1097/jom.0b013e31821f2bbb · Cited by 39
Johnston, B. C., & Guyatt, G. H. (2016) · The American Journal of Clinical Nutrition · doi:10.3945/ajcn.115.123315 · Cited by 36
Buckland, N. J., Camidge, D., Croden, F., Lavin, J., Stubbs, R. J., Hetherington, M. M., Blundell, J. E., & Finlayson, G. (2018) · Journal of Nutrition · doi:10.1093/jn/nxy041 · Cited by 49
“For secondary outcomes (weight, body composition, and health markers), analyses were conducted on participants who completed the trial (completers analyses) and on an intention-to-treat (ITT) basis with the use of last observation carried forward (LOCF) for missing data (38) (carrying a baseline observation forward re…”
Vorland, C. J., Brown, A. W., Dawson, J., Dickinson, S., Golzarri‐Arroyo, L., Hannon, B. A., Heo, M., Heymsfield, S. B., Jayawardene, W. P., Kahathuduwa, C. N., et al. (2021) · International Journal of Obesity · doi:10.1038/s41366-021-00909-z · Cited by 43
Self-citationRees, C. S., Anderson, R., Kane, R. T., & Finlay‐jones, A. L. (2016) · JMIR Mental Health · doi:10.2196/mental.5363 · Cited by 43
“This optimizes statistical power and reduces sampling bias associated with subject attrition [38,39], making it suitable for research on Internet-based interventions, which often demonstrate high dropout rates [40].”
A randomised controlled trial of the 5:2 diet
Hájek, P., Przulj, D., Pesola, F., McRobbie, H. J., Peerbux, S., Phillips‐Waller, A., Bisal, N., & Smith, K. M. (2021) · PLoS ONE · doi:10.1371/journal.pone.0258853 · Cited by 39
Two-Year Results of Translating the Diabetes Prevention Program Into an Urban, Underserved Community
Piatt, G. A., Seidel, M. C., Chen, H.-Y., Powell, R. O., & Zgibor, J. C. (2012) · The Diabetes Educator · doi:10.1177/0145721712458834 · Cited by 34
Nederveen, J. P., Mastrolonardo, A. J., Xhuti, D., Di Carlo, A., Manta, K., Fuda, M. R., & Tarnopolsky, M. A. (2023) · Nutrients · doi:10.3390/nu15173693 · Cited by 33
“This is in accordance with recently suggested practices for randomized weight loss trials [77].”
ResultLiving Well with Pain: Development and Preliminary Evaluation of the Valued Living Scale
Jensen, M. P., Vowles, K. E., Johnson, L. E., & Gertz, K. J. (2015) · Pain Medicine · doi:10.1111/pme.12802 · Cited by 33
Gohlke, J. M., Dhurandhar, E. J., Correll, C. U., Morrato, E. H., Newcomer, J. W., Remington, G., Nasrallah, H. A., Crystal, S., Nicol, G., & Allison, D. B. (2012) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2012.00062 · Cited by 37
“Additionally, it should be noted that the type of analysis used affects power, and that mixed models and multiple imputation have comparable power, and are preferred to LOCF methods (Elobeid et al., 2009).”
BackgroundMethodInfluentialKothari, R., Barker, C., Pistrang, N., Rozental, A., Egan, S., Wade, T., Allcott-Watson, H., Andersson, G., & Shafran, R. (2019) · Journal of Behavior Therapy and Experimental Psychiatry · doi:10.1016/j.jbtep.2019.03.007 · Cited by 32
“Multiple imputation was used to manage missing data for ITT analysis as this has been shown to be superior to last observation carried forward (Elobeid et al., 2009).”
MethodAhern, A. L., Breeze, P. R., Fusco, F., Sharp, S. J., Islam, N., Wheeler, G., Hill, A. J., Hughes, C. A., Duschinsky, R., Thomas, C., et al. (2022) · The Lancet Public Health · doi:10.1016/s2468-2667(22)00226-2 · Cited by 42
de Vos, B. C., Landsmeer, M. L. A., van Middelkoop, M., Oei, E. H. G., Krul, M., Bierma‐Zeinstra, S., & Runhaar, J. (2017) · Rheumatology · doi:10.1093/rheumatology/kex145 · Cited by 33
Kaiser, K. A., Affuso, O., Beasley, T. M., & Allison, D. B. (2012) · International Journal of Obesity · doi:10.1038/ijo.2011.25 · Cited by 31
Self-citationBell, K. E., Fang, H., Snijders, T., Allison, D. J., Zulyniak, M. A., Chabowski, A., Parise, G., Phillips, S. M., & Heisz, J. J. (2019) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2019.00107 · Cited by 29
“…total energy expenditure; TG, triglycerides; TNF-α, tumor necrosis factor alpha; VO2peak, peak oxygen uptake. including omega-3 (n−3) PUFA, have lower dementia rates (Scarmeas et al., 2006) and better cognitive function (Féart et al., 2009) compared to populations consuming typical Western diets.”
BackgroundSelf-citationAn initial evaluation of a weight loss intervention for individuals who engage in emotional eating
Goldbacher, E., La Grotte, C., Komaroff, E., Vander Veur, S., & Foster, G. D. (2016) · Journal of Behavioral Medicine · doi:10.1007/s10865-015-9678-6 · Cited by 30
“While the intent-to-treat, multiple-imputation analytic strategy is a conservative statistical approach to handling this type of situation (Elobeid et al., 2009), participant drop-out may have still affected the ability to draw definitive conclusions about treatment effects or group”
MethodTapsell, L. C., Batterham, M. J., Charlton, K. E., Neale, E. P., Probst, Y., O’Shea, J. E., Thorne, R., Zhang, Q., & Louie, J. C. Y. (2013) · BMC Public Health · doi:10.1186/1471-2458-13-1231 · Cited by 36
“These methods are the most commonly used in weight loss studies [30].”
MethodBarha, C. K., Liu-Ambrose, T. Y. L., Best, J. R., Yaffe, K. S., & Rosano, C. (2018) · Neurobiology of Aging · doi:10.1016/j.neurobiolaging.2018.10.021 · Cited by 34
“This approach has been shown to provide less biased estimates and to increase generalizability in comparison to deletion approaches that remove individuals with missing follow-up data (Elobeid et al., 2009).”
ResultAnstey, K. J., Bahar‐Fuchs, A., Herath, P. M., Rebok, G. W., & Cherbuin, N. (2013) · Trials · doi:10.1186/1745-6215-14-60 · Cited by 33
Morgan, P. J., Collins, C. E., Lubans, D. R., Callister, R., Lloyd, A., Plotnikoff, R. C., Burrows, T. L., Barnes, A. T., Pollock, E. R., Fletcher, R. J., et al. (2019) · Translational Behavioral Medicine · doi:10.1093/tbm/ibz031 · Cited by 31
Analyzing weight loss intervention studies with missing data: Which methods should be used?
Batterham, M. J., Tapsell, L. C., & Charlton, K. E. (2013) · Nutrition · doi:10.1016/j.nut.2013.01.017 · Cited by 31
“These assumptions are not possible to test in real clinical studies, although it is likely that data in weight loss trials are MAR or MNAR.”
Influentialvan Wier, M. F., Dekkers, J. C., Bosmans, J. E., Heymans, M. W., Hendriksen, I. J. M., Pronk, N. P., van Mechelen, W., & van Tulder, M. W. (2012) · International Journal of Behavioral Nutrition and Physical Activity · doi:10.1186/1479-5868-9-112 · Cited by 37
“A modeling study estimated that 50% of participants in weight control studies will have dropped out after two years, which is comparable to the dropout we found [42].”
MethodResultGagné, M. E., Légaré, F., Moisan, J., & Boulet, L. (2017) · PLoS ONE · doi:10.1371/journal.pone.0170055 · Cited by 32
Current pharmacotherapy for obesity: extrapolation of clinical trials data to practice
Gadde, K. M. (2014) · Expert Opinion on Pharmacotherapy · doi:10.1517/14656566.2014.890590 · Cited by 29
“Other imputation procedures such as the multiple imputation might be more suitable for RCTs in obesity, but there are limitations to all imputations, especially when primary outcome data are missing for half of the randomized patients [64].”
BackgroundSelf-citationStructured Home-Based Exercise Versus Invasive Treatment
Lamberti, N., Malagoni, A. M., Ficarra, V., Basaglia, N., Manfredini, R., Zamboni, P., Mascoli, F., & Manfredini, F. (2015) · Angiology · doi:10.1177/0003319715618481 · Cited by 26
“An intention-to-treat analysis was conducted using multiple imputations to calculate the missing data for participants who did not complete the study.(23) We compared intragroup outcome measures using the paired Student t test.”
MethodThe genomics of micronutrient requirements
Monteiro, J. P., Kussmann, M., & Kaput, J. (2015) · Genes & Nutrition · doi:10.1007/s12263-015-0466-2 · Cited by 28
“The ultimate benefits of N-of-1 trials may derive from the reality that interventions of whatever type rarely work in everyone (March et al. 1994; Nikles et al. 2006; Elobeid et al. 2009).”
Statistical plasmode simulations–Potentials, challenges and recommendations
Schreck, N., Slynko, A., Saadati, M., & Benner, A. (2024) · Statistics in Medicine · doi:10.1002/sim.10012 · Cited by 34
“Elobeid et al 35 employs plasmode data sets to analyze the performance of several statistical methods used to handle missing data in obesity randomized controlled trials.”
MethodPerdew, M., Liu, S., Rhodes, R. E., Ball, G. D. C., Mâsse, L. C., Hartrick, T., Strange, K. S., & Naylor, P. (2020) · Childhood Obesity · doi:10.1089/chi.2020.0236 · Cited by 23
“31 34 Therefore, we used the BOCF method in our study.”
Fuller, N. R., Williams, K., Shrestha, R. N., Ahern, A. L., Holzapfel, C., Hauner, H., Jebb, S. A., & Caterson, I. D. (2014) · Clinical Obesity · doi:10.1111/cob.12057 · Cited by 26
“Consistent with weight loss trials, there was a large dropout rate (42%), which might be expected for a study of 12 months (9,27).”
BackgroundUsing data mining to predict success in a weight loss trial
Batterham, M. J., Tapsell, L. C., Charlton, K. E., O’Shea, J. E., & Thorne, R. (2017) · Journal of Human Nutrition and Dietetics · doi:10.1111/jhn.12448 · Cited by 25
“%) in the present study compared to others conducted by our research group and other facilities (41,42) .”
ResultGilbertson, N. M., Mandelson, J. A., Hilovsky, K. L., Akers, J. D., Hargens, T. A., Wenos, D. L., & Edwards, E. S. (2019) · European Journal of Applied Physiology · doi:10.1007/s00421-019-04137-2 · Cited by 21
de Vos, B. C., Runhaar, J., van Middelkoop, M., Krul, M., & Bierma‐Zeinstra, S. (2016) · American Journal of Clinical Nutrition · doi:10.3945/ajcn.116.133512 · Cited by 27
Arterburn, L. M., Coleman, C. D., Kiel, J., Kelley, K., Mantilla, L. B., Frye, N., Sanoshy, K. D., & Cook, C. M. (2018) · Obesity Science & Practice · doi:10.1002/osp4.312 · Cited by 18
“Analyses with and without single (last-observation carried forward, LOCF) and multiple imputation (MI, (16)) were also conducted for the primary endpoint.”
MethodAngiotensin Converting Enzyme (ACE): A Marker for Personalized Feedback on Dieting
Tejpal, S., Sanghera, N., Manoharan, V., Planas-Iglesias, J., Bastie, C. C., & Klein‐Seetharaman, J. (2020) · Nutrients · doi:10.3390/nu12030660 · Cited by 16
“Thus, an approach to weight loss is needed that is more directly linked to the desired outcome, weight loss, itself [11,19].”
BackgroundDrew, R. J., Morgan, P. J., Collins, C. E., Callister, R., KAY‐LAMBKIN, F. J., Kelly, B. J., & Young, M. D. (2021) · Annals of Behavioral Medicine · doi:10.1093/abm/kaab109 · Cited by 16
Dutton, G. R., Gowey, M. A., Tan, F., Zhou, D., Ard, J. D., Perri, M. G., & Lewis, C. E. (2017) · International Journal of Behavioral Nutrition and Physical Activity · doi:10.1186/s12966-017-0564-1 · Cited by 18
“Due to these missing follow-up weight data and based on current recommendations for handling such data in weight loss trials [34], primary and secondary analyses were conducted based on multiple imputation in which we imputed the missing month 16 values 100 times to create 100 complete data sets, applied the desired a…”
MethodGraham, J., Tudor, K., Jebb, S. A., Lewis, A. L., Tearne, S., Adab, P., Begh, R. A., Jolly, K. B., Daley, A., Farley, A., et al. (2019) · BMC Medicine · doi:10.1186/s12916-019-1284-y · Cited by 18
The mixed-meal tolerance test as an appetite assay: methodological and practical considerations
King, J. A., Thackray, A. E., Gibbons, C., Martins, C., Broom, D. R., Stensel, D. J., Papamargaritis, D., Arsenyadis, F., Finlayson, G., Whelehan, G., et al. (2025) · International Journal of Obesity · doi:10.1038/s41366-025-01866-7 · Cited by 19
Bogen, S., Legenbauer, T., Bogen, T., Gest, S., Jensch, T., Schneider, S., & Holtmann, M. H. (2013) · Trials · doi:10.1186/1745-6215-14-178 · Cited by 17
“For missing values, the multiple imputations (MI) technique will be used, because a recent meta-analysis for RCTs in obesity found this to have modest superiority to fitting mixed linear models or using last observation carried forward (LOCF) methods [76].”
MethodCui, Z., Stevens, J., Truesdale, K. P., Zeng, D., French, S. A., & Gordon‐Larsen, P. (2016) · PLoS ONE · doi:10.1371/journal.pone.0167288 · Cited by 19
Can commitment contracts boost participation in public health programmes?
Savani, M. M. (2019) · Journal of Behavioral and Experimental Economics · doi:10.1016/j.socec.2019.101457 · Cited by 30
“By this measure, 18% of observations lacked an outcome measure, which is in line with other weight loss studies (Elobeid et al., 2009).9 Attrition is higher in the comparison group than the contract group (22% compared to 14%, p=0.169).”
ResultInfluentialBell, K. E., Snijders, T., Zulyniak, M. A., Kumbhare, D., Parise, G., Chabowski, A., & Phillips, S. M. (2018) · Applied Physiology, Nutrition, and Metabolism · doi:10.1139/apnm-2017-0533 · Cited by 13
Buckland, N. J., Camidge, D., Croden, F., Myers, A., Lavin, J., Stubbs, R. J., Blundell, J. E., & Finlayson, G. (2019) · British Journal Of Nutrition · doi:10.1017/s000711451900179x · Cited by 16
“also conducted to account for participants who did not complete the study, provided that data were available (no data were available for participants who withdrew before completing the early test meal sessions)(30).”
BackgroundKerrigan, S. G., Call, C. C., Schaumberg, K., Forman, E. M., & Butryn, M. L. (2018) · Translational Behavioral Medicine · doi:10.1093/tbm/ibx038 · Cited by 14
Kerrigan, S. G., Clark, M. H., Convertino, A. D., Forman, E. M., & Butryn, M. L. (2017) · Journal of Behavioral Medicine · doi:10.1007/s10865-017-9883-6 · Cited by 14
“Missing data were handled using multiple imputation and five imputed datasets, as has been suggested elsewhere (Batterham et al., 2017; Elobeid et al., 2009; Gadbury et al., 2003).”
van der Voet, J. A., Schiphof, D., Vroegindeweij, D., Oei, E. H. G., Bierma‐Zeinstra, S., & Runhaar, J. (2023) · Seminars in Arthritis and Rheumatism · doi:10.1016/j.semarthrit.2023.152170 · Cited by 10
Kinsey, A. W., Gowey, M. A., Tan, F., Zhou, D., Ard, J. D., Affuso, O., & Dutton, G. R. (2018) · Ethnicity and Health · doi:10.1080/13557858.2018.1493435 · Cited by 12
“Intention-to-treat analyses were used and missing values for month 16 weight were imputed using multiple imputation (Elobeid et al. 2009).”
MethodDas, S. K., Bukhari, A. S., Taetzsch, A., Ernst, A. K., Rogers, G. T., Gilhooly, C. H., Hatch‐McChesney, A., Blanchard, C. M., Livingston, K. A., Silver, R. E., et al. (2021) · American Journal of Clinical Nutrition · doi:10.1093/ajcn/nqab259 · Cited by 16
Self-citationKaiser, K. A., Affuso, O., Desmond, R. A., & Allison, D. B. (2014) · Frontiers in Nutrition · doi:10.3389/fnut.2014.00025 · Cited by 13
Self-citationTudor, K., Tearne, S., Jebb, S. A., Lewis, A. L., Adab, P., Begh, R. A., Jolly, K. B., Daley, A., Farley, A., Lycett, D., et al. (2020) · Clinical Obesity · doi:10.1111/cob.12418 · Cited by 12
“were weighed, which is higher than the typical follow-up in similar weight loss trials (63%).(20) Whilst we planned these exploratory analyses(17) these subgroup”
ResultJones, R. A. P., Mueller, J., Sharp, S. J., Griffin, S. J., & Ahern, A. L. (2022) · Obesity · doi:10.1002/oby.23570 · Cited by 12
Henninger, S. H., Fibieger, A. Y., Magkos, F., & Ritz, C. (2023) · Nutrients · doi:10.3390/nu15071646 · Cited by 12
“However, it should be noted that the drop-out rate in this study is no different from what has been seen in the past for weight management trials [36,37].”
ResultMethodological quality of behavioural weight loss studies: a systematic review
Lemon, S. C., Wang, M. L., Haughton, C. F., Estabrook, D. P., Frisard, C., & Pagoto, S. (2016) · Obesity Reviews · doi:10.1111/obr.12412 · Cited by 12
“The authors concluded that multiple imputation and model based approaches are the most appropriate for weight loss trials (30).”
Background
Metadata
- Authors
- Elobeid, M. A., Padilla, M. A., McVie, T., Thomas, O., Brock, D. W., Musser, B., Lu, K., Coffey, C. S., Desmond, R. A., St-Onge, M.-P., Gadde, K. M., Heymsfield, S. B., & Allison, D. B.
- Affiliations
- University of Alabama at Birmingham (US)
- Merck & Co., Inc., Rahway, NJ, USA (United States) (US)
- Duke University (US)
- Corresponding author
- Allison, David B.
- ORCID
- Venue
- PLoS ONE
- Publisher
- Public Library of Science (PLoS)
- Published
- 2009-08-13
- Volume
- 4
- Issue
- 8
- Pages
- e6624
- ISSN
- 1932-6203 (ISSN-L)
- PMC
- PMC2720539
- OpenAlex
- W2086313861
- Cited by
- 158
- References
- 25
- Citations by year
- 2026: 7 · 2025: 7 · 2024: 9 · 2023: 3 · 2022: 8 · 2021: 9 · 2020: 10 · 2019: 15 · 2018: 10 · 2017: 10 · 2016: 11 · 2015: 13 · 2014: 8 · 2013: 11 · 2012: 12
- FWCI
- 7.47
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- PLoS ONE (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- DukeSpace (Duke University) (submittedVersion, cc-by-nc-nd)
- Funders
- National Institutes of Health
- National Heart, Lung, and Blood Institute (T32HL007457)
- National Institute of Diabetes and Digestive and Kidney Diseases (P30DK056336)
- National Institute of Arthritis and Musculoskeletal and Skin Diseases (R01AR052658)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Clinical Trials
- Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
- Keywords
- missing data, dropout, obesity, weight loss, weight gain prevention, randomized controlled trials, last observation carried forward, multiple imputation, mixed models, exponential decay model
- MeSH terms
- Data Interpretation, Statistical, Humans, Obesity, Weight Loss, 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
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.