SPECIAL ISSUE PAPER

Trimmed means for symptom trials with dropouts

Corresponding Author

Thomas Permutt

[email protected]

Division of Biometrics II, Office of Biostatistics, Office of Translational Sciences, Center for Drug Evaluation and Research, U.S. Food and Drug Administration, Silver Spring, Maryland, U.S.A.

Correspondence to: Thomas Permutt, Division of Biometrics II, Office of Biostatistics, Office of Translational Sciences, Center for Drug Evaluation and Research, U.S. Food and Drug Administration.

E-mail: [email protected]

Search for more papers by this author

Feng Li,

Feng Li

Division of Biometrics II, Office of Biostatistics, Office of Translational Sciences, Center for Drug Evaluation and Research, U.S. Food and Drug Administration, Silver Spring, Maryland, U.S.A.

Search for more papers by this author

Thomas Permutt,

Corresponding Author

Thomas Permutt

[email protected]

Division of Biometrics II, Office of Biostatistics, Office of Translational Sciences, Center for Drug Evaluation and Research, U.S. Food and Drug Administration, Silver Spring, Maryland, U.S.A.

Correspondence to: Thomas Permutt, Division of Biometrics II, Office of Biostatistics, Office of Translational Sciences, Center for Drug Evaluation and Research, U.S. Food and Drug Administration.

E-mail: [email protected]

Search for more papers by this author

Feng Li,

Feng Li

Division of Biometrics II, Office of Biostatistics, Office of Translational Sciences, Center for Drug Evaluation and Research, U.S. Food and Drug Administration, Silver Spring, Maryland, U.S.A.

Search for more papers by this author

First published: 15 August 2016

https://doi.org/10.1002/pst.1768

Citations: 34

Share a link

Email
Wechat
Bluesky

Abstract

Dropouts from randomized trials, often for lack of efficacy or toxicity, have usually been handled as 'missing data'. We suggest that they are instead complete observations, just not numeric ones. We propose an exact test of the hypothesis of no drug effect, taking all randomized patients into account, based on a readily interpretable statistic. The method also copes with a drug that is toxic in some patients but beneficial to others, a difficult problem for standard methods. A robust conclusion of efficacy can be drawn with no assumptions other than randomization. Published 2016. This article is a U.S. Government work and is in the public domain in the USA

References

1 National Research Council. The prevention and treatment of missing data in clinical trials. National Academies Press: Washington, 2010.
Google Scholar
2Shih WJ, Quan H. Testing for treatment differences with dropouts present in clinical trials–A composite approach. Statistics in Medicine 1997; 16: 1225–1239.
10.1002/(SICI)1097-0258(19970615)16:11<1225::AID-SIM548>3.0.CO;2-Y
CAS PubMed Web of Science® Google Scholar
3Kenward MG. The handling of missing data in clinical trials. Clinical Investigation 2013; 3: 241–250.
10.4155/cli.13.7
CAS Google Scholar
4Tukey J. Memorandum reports 31-34. Statistical Research Group, Princeton University, 1946.
Google Scholar
5Huber PJ. Robust estimation of a location parameter. Annals of Mathematical Statistics 1964; 35: 73–101.
10.1214/aoms/1177703732
Web of Science® Google Scholar
6Bickel PJ. On some robust estimates of location. Annals of Mathematical Statistics 1965; 36: 847–858.
10.1214/aoms/1177700058
Web of Science® Google Scholar
7Stigler SM. The asymptotic distribution of the trimmed mean. Annals of Statistics 1973; 1: 472–477.
10.1214/aos/1176342412
Web of Science® Google Scholar
8Gould AL. A new approach to the analysis of clinical drug trials with withdrawals. Biometrics 1980; 36: 721–727.
10.2307/2556126
CAS PubMed Web of Science® Google Scholar
9Brown MB. A test for the difference between two treatments in a continuous measure of outcome when there are dropouts. Controlled Clinical Trials 1992; 13: 213–225.
10.1016/0197-2456(92)90004-J
CAS PubMed Web of Science® Google Scholar
10Pincus T, Amara I, Koch GG. Continuous indices of Core Data Set measures in rheumatoid arthritis clinical trials: lower responses to placebo than seen with categorical responses with the American College of Rheumatology 20% criteria. Arthritis & Rheumatism 2005; 52: 1031–1036.
10.1002/art.20995
CAS PubMed Web of Science® Google Scholar
11Farrar JT, Dworkin RH, Max MB. Use of the cumulative proportion of responders analysis graph to present pain data over a range of cut-off points: making clinical trial data more understandable. Journal of Pain and Symptom Management 2006; 31: 369–377.
10.1016/j.jpainsymman.2005.08.018
PubMed Web of Science® Google Scholar
12Permutt T, Buenconsejo J. Responder analysis in analgesic trials: you can have it both ways. Proceedings of the Joint Statistical Meetings: Minneapolis, 2005.
Google Scholar
13Permutt T. A taxonomy of estimands for regulatory clinical trials with discontinuations. Statistics in Medicine 2015: n/a–n/a. DOI: 10.1002/sim.6841.
10.1002/sim.6841
Web of Science® Google Scholar
14Senn S, Stevens L, Chaturvedi N. Repeated measures in clinical trials: simple strategies for analysis using summary measures. Statistics in Medicine 2000; 19: 861–877.
10.1002/(SICI)1097-0258(20000330)19:6<861::AID-SIM407>3.0.CO;2-F
CAS PubMed Web of Science® Google Scholar
15Bamia C, White IR, Kenward MG. Some consequences of assuming simple patterns for the treatment effect over time in a linear mixed model. Statistics in Medicine 2013; 32: 2585–2594.
10.1002/sim.5707
CAS PubMed Web of Science® Google Scholar
16Mallinckrodt C, Roger J, Chuang-Stein C, Molenberghs G, O'Kelly M, Ratitch B, Janssens M, Bunouf P. Recent developments in the prevention and treatment of missing data. Therapeutic Innovation & Regulatory Science 2013; 48(1): 369–382.
Web of Science® Google Scholar
17Leuchs A-K, Zinserling J, Brandt A, Wirtz D. Choosing appropriate estimands in clinical Trials. Therapeutic Innovation & Regulatory Science 2015; 49(4): 584–592.
10.1177/2168479014567317
PubMed Web of Science® Google Scholar

Citing Literature

Volume16, Issue1

Special Issue:Estimands

January/February 2017

Pages 20-28

Trimmed means for symptom trials with dropouts

Abstract

References

Citing Literature

References

Information

About Wiley Online Library

Help & Support

Opportunities

Connect with Wiley

Trimmed means for symptom trials with dropouts

Abstract

References

Citing Literature

References

Related

Information