Dynamic borrowing through empirical power priors that control type I error

被引:26
作者
Nikolakopoulos, Stavros [1 ]
van der Tweel, Ingeborg [1 ]
Roes, Kit C. B. [1 ]
机构
[1] Univ Med Ctr, Julius Ctr Hlth Sci & Primary Care, Dept Biostat & Res Support, Utrecht, Netherlands
关键词
Clinical trials; Dynamic borrowing; Power priors; Type I error; CLINICAL-TRIALS; HISTORICAL INFORMATION; SPINAL-ANESTHESIA; SAMPLE-SIZE; BUPIVACAINE; CLONIDINE; MODELS; BAYES;
D O I
10.1111/biom.12835
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
In order for historical data to be considered for inclusion in the design and analysis of clinical trials, prospective rules are essential. Incorporation of historical data may be of particular interest in the case of small populations where available data is scarce and heterogeneity is not as well understood, and thus conventional methods for evidence synthesis might fall short. The concept of power priors can be particularly useful for borrowing evidence from a single historical study. Power priors employ a parameter [0,1] that quantifies the heterogeneity between the historical study and the new study. However, the possibility of borrowing data from a historical trial will usually be associated with an inflation of the type I error. We suggest a new, simple method of estimating the power parameter suitable for the case when only one historical dataset is available. The method is based on predictive distributions and parameterized in such a way that the type I error can be controlled by calibrating to the degree of similarity between the new and historical data. The method is demonstrated for normal responses in a one or two group setting. Generalization to other models is straightforward.
引用
收藏
页码:874 / 880
页数:7
相关论文
共 20 条
  • [1] SAMPLING AND BAYES INFERENCE IN SCIENTIFIC MODELING AND ROBUSTNESS
    BOX, GEP
    [J]. JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES A-STATISTICS IN SOCIETY, 1980, 143 : 383 - 430
  • [2] Committee for medicinal products for human use (CHMP), 2006, GUID CLITR TRIALS SM
  • [3] Evaluating water quality using power priors to incorporate historical information
    Duan, YY
    Ye, KY
    Smith, EP
    [J]. ENVIRONMETRICS, 2006, 17 (01) : 95 - 106
  • [4] Checking for Prior-Data Conflict
    Evans, Michael
    Moshonov, Hadas
    [J]. BAYESIAN ANALYSIS, 2006, 1 (04): : 893 - 914
  • [5] No solution yet for combining two independent studies in the presence of heterogeneity
    Gonnermann, Andrea
    Framke, Theodor
    Grohennig, Anika
    Koch, Armin
    [J]. STATISTICS IN MEDICINE, 2015, 34 (16) : 2476 - 2480
  • [6] Adaptive power priors with empirical Bayes for clinical trials
    Gravestock, Isaac
    Held, Leonhard
    [J]. PHARMACEUTICAL STATISTICS, 2017, 16 (05) : 349 - 360
  • [7] Hierarchical Commensurate and Power Prior Models for Adaptive Incorporation of Historical Information in Clinical Trials
    Hobbs, Brian P.
    Carlin, Bradley P.
    Mandrekar, Sumithra J.
    Sargent, Daniel J.
    [J]. BIOMETRICS, 2011, 67 (03) : 1047 - 1056
  • [8] Ibrahim JG, 2000, STAT SCI, V15, P46
  • [9] On optimality properties of the power prior
    Ibrahim, JG
    Chen, MH
    Sinha, D
    [J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2003, 98 (461) : 204 - 213
  • [10] The power prior: theory and applications
    Ibrahim, Joseph G.
    Chen, Ming-Hui
    Gwon, Yeongjin
    Chen, Fang
    [J]. STATISTICS IN MEDICINE, 2015, 34 (28) : 3724 - 3749