Sensitivity analysis for clinical trials with missing continuous outcome data using controlled multiple imputation: A practical guide

Suzie Cro, Tim P Morris, Michael G Kenward, James R Carpenter, Suzie Cro, Tim P Morris, Michael G Kenward, James R Carpenter

Abstract

Missing data due to loss to follow-up or intercurrent events are unintended, but unfortunately inevitable in clinical trials. Since the true values of missing data are never known, it is necessary to assess the impact of untestable and unavoidable assumptions about any unobserved data in sensitivity analysis. This tutorial provides an overview of controlled multiple imputation (MI) techniques and a practical guide to their use for sensitivity analysis of trials with missing continuous outcome data. These include δ- and reference-based MI procedures. In δ-based imputation, an offset term, δ, is typically added to the expected value of the missing data to assess the impact of unobserved participants having a worse or better response than those observed. Reference-based imputation draws imputed values with some reference to observed data in other groups of the trial, typically in other treatment arms. We illustrate the accessibility of these methods using data from a pediatric eczema trial and a chronic headache trial and provide Stata code to facilitate adoption. We discuss issues surrounding the choice of δ in δ-based sensitivity analysis. We also review the debate on variance estimation within reference-based analysis and justify the use of Rubin's variance estimator in this setting, since as we further elaborate on within, it provides information anchored inference.

Keywords: clinical trials; controlled multiple imputation; missing data; multiple imputation; sensitivity analysis.

© 2020 The Authors. Statistics in Medicine published by John Wiley & Sons, Ltd.

References

REFERENCES

    1. Morris TP, Kahan BC, White IR. Choosing sensitivity analyses for randomised trials: principles. BMC Med Res Methodol. 2014;14(1):11. .
    1. Committee for Medicinal Products for Human Use. Guideline on Missing Data in Confirmatory Clinical Trials. London: Eurpoean Medicines Agency; 2010. .
    1. National Research Council. The prevention and treatment of missing data in clinical trials. panel on handling missing data in clinical trials. Committee on National Statistics, Division of Behavioural and Social Sciences Education. Washington, DC: The National Academies Press; 2010.
    1. Molenberghs G, Kenward MG. Missing Data in Clinical Studies. New York, NY: Wiley; 2007.
    1. Carpenter JR, Kenward MG. Multiple Imputation and its Application. New York, NY: Wiley; 2013.
    1. Molenberghs G, Fitzmaurice G, Kenward MG, Tsiatis A, Verbeke G. Handbook of Missing Data Methodology. Boca Raton, FL: Chapman & Hall/CRC Handbooks of Modern Statistical MethodsTaylor & Francis; 2014.
    1. Bell ML, Fiero M, Horton NJ, Chiu-Hsieh H. Handling missing data in RCTs, a review of the top medical journals. BMC Med Res Methodol. 2014;14(1):118.
    1. Powney M, Williamson P, Kirkham J, Kolamunnage-Dona R. A review of the handling of missing longitudinal outcome data in clinical trials. Trials. 2014;15:237. .
    1. Ich, C. H. M. P. ICH E9 (R1) addendum on estimands and sensitivity analysis in clinical trials to the guideline on statistical principles for clinical trials. Proceedings of the International Conference on Harmonisation of Technical Requirements for Registration of Pharmaceuticals for Human Use; 2019.
    1. Ratitch B. Missing data in clinical trials: from clinical assumptions to statistical analysis using pattern mixture models. Pharmaceutical Stat. 2013;12(6):337-347. .
    1. Carpenter JR, Roger JH, Kenward MG. Analysis of longitudinal trials with protocol deviation: a framework for relevant, accessible assumptions and inference via multiple imputation. J Biopharmaceut Stat. 2013;23(6):1352-1371.
    1. Mallinckrodt C, Roger J, Chuang-Stein C, et al. Recent Developments in the Prevention and Treatment of Missing Data. Therapeut Innovat Regulat Sci. 2014;48(1):68-80. .
    1. Mallinckrodt CH. Preventing and treating missing data in longitudinal clinical trials: a practical guide. Practical Guides to Biostatistics and Epidemiology. Cambridge, MA: Cambridge University Press; 2013.
    1. O'Kelly M, Ratitch B. Multiple Imputation. New York, NY: John Wiley & Sons Ltd; 2014:284-319.
    1. Ayele BT, Lipkovich I, Molenberghs G, Mallinckrodt CH. A multiple-imputation-based approach to sensitivity analyses and effectiveness assessments in longitudinal clinical trials. J Biopharmaceut Stat. 2014;24(2):211-228.
    1. Kenward MG. Controlled multiple imputation methods for sensitivity analyses in longitudinal clinical trials with dropout and protocol deviation. Clin Investigat. 2015;5(3):311-320.
    1. Philipsen A, Jans T, Graf E, et al. Effects of group psychotherapy, individual counseling, methylphenidate, and placebo in the treatment of adult attention-deficit/hyperactivity disorder: a randomized clinical trial. JAMA Psychiat. 2015;72(12):1199-1210. .
    1. Jans T, Jacob C, Warnke A, et al. Does intensive multimodal treatment for maternal ADHD improve the efficacy of parent training for children with ADHD? a randomized controlled multicenter trial. J Child Psychol Psychiatry. 2015;56(12):1298-1313. .
    1. Billings LK, Doshi A, Gouet D, et al. Efficacy and safety of IDegLira versus basal-bolus insulin therapy in patients with type 2 diabetes uncontrolled on metformin and basal insulin; DUAL VII randomized clinical trial. Diabet Care. 2018;41(5):1009-1016. .
    1. Atri A, Frolich L, Ballard C, et al. Effect of idalopirdine as adjunct to cholinesterase inhibitors on change in cognition in patients with Alzheimer disease: three randomized clinical trials. JAMA. 2018;319(2):130-142. .
    1. Chan S, Cornelius VR, Chen T, et al. Atopic Dermatitis Anti-IgE Paediatric Trial (ADAPT): the role of anti-IgE in severe Paediatric Eczema: study protocol for a randomised controlled trial. Trials. 2017;18(1):136. .
    1. Chen T, Chan S, Lack G, Cro S, Cornelius VR. The role of anti-IgE (omalizumab/Xolair) in the management of severe recalcitrant paediatric atopic eczema (ADAPT): statistical analysis plan. Trials. 2017;18(1):231. .
    1. Chan S, Cornelius V, Cro S, Harper JI, Lack G. Treatment Effect of Omalizumab on Severe Pediatric Atopic Dermatitis: The ADAPT Randomized Clinical Trial. JAMA Pediatr. 2020;174(1):29-37. .
    1. Vickers AJ, Rees RW, Zollman CE, et al. Acupuncture for chronic headache in primary care: large, pragmatic, randomised trial. BMJ. 2004;328(7442):744. .
    1. Vickers AJ. Whose data set is it anyway? sharing raw data from randomized trials. Trials. 2006;7:15-15. .
    1. Rubin DB. Inference and missing data. Biometrika. 1976;63(3):581-592.
    1. Wilson E, Free C, Morris TP, et al. Internet-accessed sexually transmitted infection (e-STI) testing and results service: a randomised, single-blind, controlled trial. PLOS Med. 2017;14(12):1-20. .
    1. Little RJA, Rubin DB. Statistical Analysis with Missing Data. New York, NY: John Wiley & Son, Inc; 1987.
    1. Rubin DB. Multiple Imputation for Nonreponse in Surveys. Wiley Series in Probability and Mathematical Statistics. New York, NY: John Wiley & Sons; 1987.
    1. Meng XL. Multiple-imputation inferences with uncongenial sources of input. Stat Sci. 1994;9(4):538-558.
    1. Royston P, Carlin JB, White IR. Multiple imputation of missing values: new features for mim. Stat J. 2009;9(2):252-264.
    1. Rubin DB. Multiple imputations in sample surveys - a phenomenological Bayesian approach to nonresponse. Paper presented at: Proceedings of the Survey Research Methods Section of the American Statistical Association; 1978:20-28.
    1. Rubin DB. Multiple imputation after 18+ years. J Am Stat Assoc. 1996;91(434):473-489.
    1. Little RJA, Yau L. Intent-to-treat analysis for longitudinal studies with drop-outs. Biometrics. 1996;52(4):1324-1333.
    1. Schafer JL. Analysis of Incomplete Multivariate Data. Boca Raton, FL: Chapman & Hall; 1997.
    1. Buuren S, Boshuizen HC, Knook DL. Multiple imputation of missing blood pressure covariates in survival analysis. Stat Med. 1999;18(6):681-694. <681::AID-SIM71>;2-R.
    1. White IR, Royston P, Wood AM. Multiple imputation using chained equations: issues and guidance for practice. Stat Med. 2011;30(4):377-399. .
    1. Hippel PT. How many imputations do you need? a two-stage calculation using a quadratic rule. Sociolog Methods Res. 2018;1(1):1-20. .
    1. Van Buuren S. Multiple imputation of discrete and continuous data by fully conditional specification. Stat Methods Med Res. 2007;16(3):219-242. .
    1. Little RJA. Pattern-mixture models for multivariate incomplete data. J Am Stat Assoc. 1993;88(421):125-134.
    1. Carpenter JR, Kenward MG. Missing data in randomised controlled trials - a practical guide; 2008. . Accessed June 2014.
    1. Daniels MJ, Hogan JW. Missing Data in Longitudinal Studies Strategies for Bayesian Modelling and Sensitivity Analysis. Monographs on Statistics and Applied Probability. Boca Raton, FL: Chapman & Hall; 2008.
    1. White IR, Horton NJ, Carpenter JR, Pocock SJ. Strategy for intention to treat analysis in randomised trials with missing outcome data. British Med J. 2011;342:d40.
    1. Yan X, Lee S, Li N. Missing data handling methods in medical device clinical trials. J Biopharmaceut Stat. 2009;19(6):1085-1098.
    1. Cro S, Morris TP, Kenward MG, Carpenter JR. Reference-based sensitivity analysis via multiple imputation for longitudinal trials with protocol deviation. Stat J. 2016;16(2):443-463(21).
    1. Roger JH. miwithd; SAS code for reference based multiple imputation; 2012. . Accessed July 15 2016.
    1. Roger JH., Barnett C., Drury T. The five macros; SAS code for reference based multiple imputation; 2017. . Accessed February 16, 2018.
    1. Seaman SR, White IR, Leacy FP. Comment on, analysis of longitudinal trials with protocol deviations, a framework for relevant, accessible assumptions, and inference via multiple imputation, by Carpenter, Roger and Kenward. J Biopharmaceut Stat. 2014;24(6):1358-1362.
    1. Carpenter JR, Roger JH, Cro S, Kenward MG. Response to comments by seaman et al. on analysis of longitudinal trials with protocol deviation, a framework for relevant, accessible assumptions, and inference via multiple imputation. J Biopharmaceut Stat. 2014;24(6):1363-1369.
    1. Lu K. An analytic method for the placebo-based pattern- mixture model. Stat Med. 2014;33(7):1134-1145. .
    1. Ayele BT, Lipkovich I, Molenberghs G, Mallinckrodt CH. A multiple-imputation-based approach to sensitivity analyses and effectiveness assessments in longitudinal clinical trials. J Biopharmaceut Stat. 2014;24(2):211-228. .
    1. Cro S, Carpenter JR, Kenward MG. Information-anchored sensitivity analysis: theory and application. J Royal Stat Soc Ser A (Stat Soc). 2019;182(3):623-645.
    1. White IR, Carpenter JR, Evans S, Schroter S. Eliciting and using expert opinions about dropout bias in randomized controlled trials. Clin Trials. 2007;4:125-139.
    1. Mason Alexina J, Gomes Manuel, Grieve Richard, Ulug Pinar, Powell Janet T, Carpenter James. Development of a practical approach to expert elicitation for randomised controlled trials with missing health outcomes: Application to the IMPROVE trial. Clin Trials 2017;14(4):357-367. PMID: 28675302, .
    1. White Ian R., Joseph Royes, Best Nicky. A causal modelling framework for reference-based imputation and tipping point analysis in clinical trials with quantitative outcome. J Biopharmaceut Stat 2020;30(2):334-350. PMID: 31718423, .
    1. Rehal S. Implications of Missing Data in Tuberculosis Non-inferiority Clinical Trials (PhD Thesis). London, UK: University College London, University of London; 2018.
    1. Keene ON, Roger JH, Hartley BF, Kenward MG. Missing data sensitivity analysis for recurrent event data using controlled imputation. Pharm Stat. 2014;13(4):258-264. .
    1. Akacha M, Ogundimu EO. Sensitivity analyses for partially observed recurrent event data. Pharmaceut Stat. 2015;15(1):4-14. .
    1. Gao F, Liu GF, Zeng D, et al. Control-based imputation for sensitivity analyses in informative censoring for recurrent event data. Pharm Stat. 2017;16(6):424-432. .
    1. Jackson D, White IR, Seaman S, Evans H, Baisley K, Carpenter J. Relaxing the independent censoring assumption in the Cox proportional hazards model using multiple imputation. Stat Med. 2014;33(27):4681-4694. .
    1. Atkinson A. Reference Based Sensitivity Analysis for Time-to-Event Data (PhD thesis). London, UK: Department of Medical Statistics, London School of Hygiene & Tropical Medicine, University of London; 2018.
    1. Atkinson A, Kenward MG, Clayton T, Carpenter JR. Reference-based sensitivity analysis for time-to-event data. Pharmaceut Stat. 2019;18:645-658. .
    1. Lu K, Li D, Koch GG. Comparison between two controlled multiple imputation methods for sensitivity analyses of time-to-event data with possibly informative censoring. Stat Biopharmaceut Res. 2015;7(3):199-213. .
    1. Lipkovich I, Ratitch B, O'Kelly M. Sensitivity to censored-at-random assumption in the analysis of time-to-event endpoints. Pharmaceut Stat. 2016;15(3):216-229. .
    1. Tang Y. Controlled pattern imputation for sensitivity analysis of longitudinal binary and ordinal outcomes with nonignorable dropout. Stat Med. 2018;37(9):1467-1481. .
    1. White IR, Thompson SG. Adjusting for partially missing baseline measurements in randomized trials. Stat Med. 2005;24(7):993-1007. .
    1. Schroter S, Black N, Evans S, Carpenter JR, Fiona G, Smith R. Effects of training on quality of peer review: randomised controlled trial. BMJ. 2004;328(7441):673. .

Source: PubMed

Sponsorit ja yhteistyökumppanit

Sairaudet

Huumeiden interventiot

3
Tilaa