Problems in Dealing with Missing Data and Informative Censoring in Clinical Trials

Overview

Journal Curr Control Trials Cardiovasc Med

Specialty Cardiology & Vascular Diseases

Date 2002 May 3

PMID 11985778

Citations 56

Authors

Weichung Shih

Affiliations

Soon will be listed here.

Abstract

Acommon problem in clinical trials is the missing data that occurs when patients do not complete the study and drop out without further measurements. Missing data cause the usual statistical analysis of complete or all available data to be subject to bias. There are no universally applicable methods for handling missing data. We recommend the following: (1) Report reasons for dropouts and proportions for each treatment group; (2) Conduct sensitivity analyses to encompass different scenarios of assumptions and discuss consistency or discrepancy among them; (3) Pay attention to minimize the chance of dropouts at the design stage and during trial monitoring; (4) Collect post-dropout data on the primary endpoints, if at all possible; and (5) Consider the dropout event itself an important endpoint in studies with many.

Citing Articles

Prioritizing attributes of approaches to analyzing patient-centered outcomes that are truncated due to death in critical care clinical trials: a Delphi study.

Bahti M, Kahan B, Li F, Harhay M, Auriemma C Trials. 2025; 26(1):15.

PMID: 39794867 PMC: 11721323. DOI: 10.1186/s13063-024-08673-x.

Assessing the Feasibility and Efficacy of Virtual Reality Navigational Training for Older Adults.

Xu T, Mostafavi A, Boot W, Czaja S, Kalantari S Innov Aging. 2025; 9(1):igae099.

PMID: 39781245 PMC: 11705671. DOI: 10.1093/geroni/igae099.

Informative censoring in externally controlled clinical trials: a potential source of bias.

Rudra Gupta T, Schwartz D, Saha R, Wen P, Rahman R, Trippa L ESMO Open. 2025; 10(1):104094.

PMID: 39754980 PMC: 11758402. DOI: 10.1016/j.esmoop.2024.104094.

Imputation of Missing Data for Time-to-Event Endpoints Using Retrieved Dropouts.

Wang S, Frederich R, Mancuso J Ther Innov Regul Sci. 2023; 58(1):114-126.

PMID: 37805643 PMC: 10764582. DOI: 10.1007/s43441-023-00575-5.

A three-arm randomized controlled trial using ecological momentary intervention, community health workers, and video feedback at family meals to improve child cardiovascular health: the Family Matters study design.

Berge J, Trofholz A, Aqeel M, Norderud K, Tate A, Fertig A BMC Public Health. 2023; 23(1):708.

PMID: 37072737 PMC: 10112996. DOI: 10.1186/s12889-023-15504-2.

References

Hogan J, Laird N . Model-based approaches to analysing incomplete longitudinal and failure time data. Stat Med. 1997; 16(1-3):259-72. DOI: 10.1002/(sici)1097-0258(19970215)16:3<259::aid-sim484>3.0.co;2-s. View

Shih W, Quan H . Testing for treatment differences with dropouts present in clinical trials--a composite approach. Stat Med. 1997; 16(11):1225-39. DOI: 10.1002/(sici)1097-0258(19970615)16:11<1225::aid-sim548>3.0.co;2-y. View

Gould A . A new approach to the analysis of clinical drug trials with withdrawals. Biometrics. 1980; 36(4):721-7. View

Downs J, Clearfield M, Tyroler H, Whitney E, Kruyer W, Langendorfer A . Air Force/Texas Coronary Atherosclerosis Prevention Study (AFCAPS/TEXCAPS): additional perspectives on tolerability of long-term treatment with lovastatin. Am J Cardiol. 2001; 87(9):1074-9. DOI: 10.1016/s0002-9149(01)01464-3. View

Lubsen J, Just H, Hjalmarsson A, La Framboise D, Remme W, Dumont J . Effect of pimobendan on exercise capacity in patients with heart failure: main results from the Pimobendan in Congestive Heart Failure (PICO) trial. Heart. 1996; 76(3):223-31. PMC: 484511. DOI: 10.1136/hrt.76.3.223. View

Lachin J . Worst-rank score analysis with informatively missing observations in clinical trials. Control Clin Trials. 1999; 20(5):408-22. DOI: 10.1016/s0197-2456(99)00022-7. View

Diamond J, Krakoff L, Goldman A, Coplan N, Gharavi A, Martin K . Comparison of two calcium blockers on hemodynamics, left ventricular mass, and coronary vasodilatory in advanced hypertension. Am J Hypertens. 2001; 14(3):231-40. DOI: 10.1016/s0895-7061(00)01267-x. View

Schluchter M . Methods for the analysis of informatively censored longitudinal data. Stat Med. 1992; 11(14-15):1861-70. DOI: 10.1002/sim.4780111408. View

Ferdinand K, Saini R, Lewin A, Yellen L, Barbosa J, KUSHNIR E . Efficacy and safety of omapatrilat with hydrochlorothiazide for the treatment of hypertension in subjects nonresponsive to hydrochlorothiazide alone. Am J Hypertens. 2001; 14(8 Pt 1):788-93. DOI: 10.1016/s0895-7061(01)01294-8. View

10.

Zanchetti A, Omboni S . Comparison of candesartan versus enalapril in essential hypertension. Italian Candesartan Study Group. Am J Hypertens. 2001; 14(2):129-34. DOI: 10.1016/s0895-7061(00)01240-1. View

11.

Murray G, Findlay J . Correcting for the bias caused by drop-outs in hypertension trials. Stat Med. 1988; 7(9):941-6. DOI: 10.1002/sim.4780070905. View

12.

Finkelstein D, Schoenfeld D . Combining mortality and longitudinal measures in clinical trials. Stat Med. 1999; 18(11):1341-54. DOI: 10.1002/(sici)1097-0258(19990615)18:11<1341::aid-sim129>3.0.co;2-7. View

13.

Cowley A, Wiens B, Segal R, Rich M, Santanello N, Dasbach E . Randomised comparison of losartan vs. captopril on quality of life in elderly patients with symptomatic heart failure: the losartan heart failure ELITE quality of life substudy. Qual Life Res. 2000; 9(4):377-84. DOI: 10.1023/a:1008948930206. View

14.

Wei L, Shih W . Partial imputation approach to analysis of repeated measurements with dependent drop-outs. Stat Med. 2001; 20(8):1197-214. DOI: 10.1002/sim.778. View

15.

McKenney J, McCormick L, Schaefer E, Black D, WATKINS M . Effect of niacin and atorvastatin on lipoprotein subclasses in patients with atherogenic dyslipidemia. Am J Cardiol. 2001; 88(3):270-4. DOI: 10.1016/s0002-9149(01)01639-3. View

16.

Wu M, Albert P, Wu B . Adjusting for drop-out in clinical trials with repeated measures: design and analysis issues. Stat Med. 2001; 20(1):93-108. DOI: 10.1002/1097-0258(20010115)20:1<93::aid-sim655>3.0.co;2-2. View