DELTA2 guidance on choosing the target difference and undertaking and reporting the sample size calculation for a randomised controlled trial

被引：23

作者：

Cook, Jonathan A. ^{[1
]}

Julious, Steven A. ^{[2
]}

Sones, William ^{[1
]}

Hampson, Lisa V. ^{[3
,4
]}

Hewitt, Catherine ^{[5
]}

Berlin, Jesse A. ^{[6
]}

Ashby, Deborah ^{[7
]}

Emsley, Richard ^{[8
]}

Fergusson, Dean A. ^{[9
]}

Walters, Stephen J. ^{[2
]}

Wilson, Edward C. F. ^{[10
,11
]}

Maclennan, Graeme ^{[12
]}

Stallard, Nigel ^{[13
]}

Rothwell, Joanne C. ^{[2
]}

Bland, Martin ^{[5
]}

Brown, Louise ^{[14
]}

Ramsay, Craig R. ^{[15
]}

Cook, Andrew ^{[16
,17
]}

Armstrong, David ^{[18
]}

Altman, Doug ^{[1
]}

Vale, Luke D. ^{[19
]}

机构：

[1] Univ Oxford, Ctr Stat Med, Nuffield Dept Orthopaed Rheumatol & Musculoskelet, Botnar Res Ctr,Nuffield Orthopaed Ctr, Windmill Rd, Oxford OX3 7LD, England

[2] Univ Sheffield, Med Stat Grp, ScHARR, Regent Court, 30 Regent St, Sheffield S1 4DA, S Yorkshire, England

[3] Novartis, Stat Methodol & Consulting, Basel, Switzerland

[4] Univ Lancaster, Dept Math & Stat, Lancaster LA1 4YF, England

[5] Univ York, Dept Hlth Sci, Seebohm Rowntree Bldg, York YO10 5DD, N Yorkshire, England

[6] Johnson & Johnson, 1125 Trenton Harbourton Rd, Titusville, NJ 08933 USA

[7] Imperial Coll London, Imperial Clin Trials Unit, Sch Publ Hlth, Stadium House,68 Wood Lane, London W12 7RH, England

[8] Kings Coll London, Dept Biostat & Hlth Informat, Inst Psychiat Psychol & Neurosci, De Crespigny Pk,Denmark Hill, London SE5 8AF, England

[9] Ottawa Hosp, Clin Epidemiol Program, Res Inst, Ottawa, ON, Canada

[10] Univ Cambridge, Cambridge Ctr Hlth Serv Res, Inst Publ Hlth, Forvie Site,Robinson Way, Cambridge CB2 0SR, England

[11] Univ Cambridge, Cambridge Clin Trials Unit, Inst Publ Hlth, Forvie Site,Robinson Way, Cambridge CB2 0SR, England

[12] Univ Aberdeen, Ctr Healthcare Randomised Trials CHaRT, Hlth Sci Bldg,Hlth Sci Bldg,Foresterhill, Aberdeen AB25 2D, Scotland

[13] Univ Warwick, Warwick Med Sch Stat & Epidemiol, Coventry CV4 7AL, W Midlands, England

[14] UCL, MRC Clin Trials Unit, Inst Clin Trials & Methodol, 2nd Floor 90 High Holborn, London WC1V 6LJ, England

[15] Univ Aberdeen, Hlth Serv Res Unit, Hlth Sci Bldg Foresterhill, Aberdeen AB25 2ZD, Scotland

[16] Univ Southampton, Publ Hlth Med, Wessex Inst, Alpha House,Enterprise Rd, Southampton SO16 7NS, Hants, England

[17] Univ Southampton, Hlth Technol Assessment, Wessex Inst, Alpha House,Enterprise Rd, Southampton SO16 7NS, Hants, England

[18] Kings Coll London, Sch Populat Hlth & Environm Sci, Fac Life Sci & Med, Addison House,Guys Campus, London SE1 1UL, England

[19] Newcastle Univ, Hlth Econ Grp, Inst Hlth & Soc, Newcastle Upon Tyne NE2 4AX, Tyne & Wear, England

来源：

TRIALS | 2018年 / 19卷

关键词：

CLINICALLY IMPORTANT DIFFERENCE; ESTIMANDS;

D O I：

10.1186/s13063-018-2884-0

中图分类号：

R-3 [医学研究方法]; R3 [基础医学];

学科分类号：

1001 ;

摘要：

BackgroundA key step in the design of a RCT is the estimation of the number of participants needed in the study. The most common approach is to specify a target difference between the treatments for the primary outcome and then calculate the required sample size. The sample size is chosen to ensure that the trial will have a high probability (adequate statistical power) of detecting a target difference between the treatments should one exist.The sample size has many implications for the conduct and interpretation of the study. Despite the critical role that the target difference has in the design of a RCT, the way in which it is determined has received little attention. In this article, we summarise the key considerations and messages from new guidance for researchers and funders on specifying the target difference, and undertaking and reporting a RCT sample size calculation. This article on choosing the target difference for a randomised controlled trial (RCT) and undertaking and reporting the sample size calculation has been dual published in the BMJ and BMC Trials journalsMethodsThe DELTA(2) (Difference ELicitation in TriAls) project comprised five major components: systematic literature reviews of recent methodological developments (stage 1) and existing funder guidance (stage 2); a Delphi study (stage 3); a two-day consensus meeting bringing together researchers, funders and patient representatives (stage 4); and the preparation and dissemination of a guidance document (stage 5).Results and DiscussionThe key messages from the DELTA(2) guidance on determining the target difference and sample size calculation for a randomised caontrolled trial are presented. Recommendations for the subsequent reporting of the sample size calculation are also provided.

引用

页数：8

共 32 条

[21]

Julious S.A., 2010, SAMPLE SIZES CLIN TR

[22]

National Institute for Health Research, INVOLVE

[23] Bayesian techniques for sample size determination in clinical trials: a short review [J].