A comparison of imputation strategies in cluster randomized trials with missing binary outcomes

被引:12
作者
Caille, Agnes [1 ,2 ,3 ,4 ]
Leyrat, Clemence [1 ,2 ,3 ]
Giraudeau, Bruno [1 ,2 ,3 ,4 ]
机构
[1] INSERM, U1153, Paris, France
[2] INSERM, CIC 1415, 2 Bd Tonnelle, F-37044 Tours 9, France
[3] CHRU Tours, Tours, France
[4] Univ Francois Rabelais Tours, PRES Ctr, Val de Loire Univ, Tours, France
关键词
cluster randomized trial; missing data; outcome; multiple imputation; MULTIPLE-IMPUTATION; CLINICAL-TRIALS; CORRELATION-COEFFICIENT; INTRACLASS CORRELATION; TREAT; INTENTION; DESIGN; MODELS;
D O I
10.1177/0962280214530030
中图分类号
R19 [保健组织与事业(卫生事业管理)];
学科分类号
摘要
In cluster randomized trials, clusters of subjects are randomized rather than subjects themselves, and missing outcomes are a concern as in individual randomized trials. We assessed strategies for handling missing data when analysing cluster randomized trials with a binary outcome; strategies included complete case, adjusted complete case, and simple and multiple imputation approaches. We performed a simulation study to assess bias and coverage rate of the population-averaged intervention-effect estimate. Both multiple imputation with a random-effects logistic regression model or classical logistic regression provided unbiased estimates of the intervention effect. Both strategies also showed good coverage properties, even slightly better for multiple imputation with a random-effects logistic regression approach. Finally, this latter approach led to a slightly negatively biased intracluster correlation coefficient estimate but less than that with a classical logistic regression model strategy. We applied these strategies to a real trial randomizing households and comparing ivermectin and malathion to treat head lice.
引用
收藏
页码:2650 / 2669
页数:20
相关论文
共 47 条
  • [1] Altman Douglas G, 2009, Open Med, V3, pe51
  • [2] A comparison of imputation techniques for handling missing predictor values in a risk model with a binary outcome
    Ambler, Gareth
    Omar, Rumana Z.
    Royston, Patrick
    [J]. STATISTICAL METHODS IN MEDICAL RESEARCH, 2007, 16 (03) : 277 - 298
  • [3] A comparison of the statistical power of different methods for the analysis of cluster randomization trials with binary outcomes
    Austin, Peter C.
    [J]. STATISTICS IN MEDICINE, 2007, 26 (19) : 3550 - 3565
  • [4] Analysis of dichotomous outcome data for community intervention studies
    Bellamy, SL
    Gibberd, R
    Hancock, L
    Howley, P
    Kennedy, B
    Klar, N
    Lipsitz, S
    Ryan, L
    [J]. STATISTICAL METHODS IN MEDICAL RESEARCH, 2000, 9 (02) : 135 - 159
  • [5] Robustness of a multivariate normal approximation for imputation of incomplete binary data
    Bernaards, Coen A.
    Belin, Thomas R.
    Schafer, Joseph L.
    [J]. STATISTICS IN MEDICINE, 2007, 26 (06) : 1368 - 1382
  • [6] The design of simulation studies in medical statistics
    Burton, Andrea
    Altman, Douglas G.
    Royston, Patrick
    Holder, Roger L.
    [J]. STATISTICS IN MEDICINE, 2006, 25 (24) : 4279 - 4292
  • [7] Dichotomizing a continuous outcome in cluster randomized trials: impact on power
    Caille, Agnes
    Leyrat, Clemence
    Giraudeau, Bruno
    [J]. STATISTICS IN MEDICINE, 2012, 31 (24) : 2822 - 2832
  • [8] Determinants of the intracluster correlation coefficient in cluster randomized trials: the case of implementation research
    Campbell, MK
    Fayers, PM
    Grimshaw, JM
    [J]. CLINICAL TRIALS, 2005, 2 (02) : 99 - 107
  • [9] CONSORT statement: extension to cluster randomised trials
    Campbell, MK
    Elbourne, DR
    Altman, DG
    [J]. BMJ-BRITISH MEDICAL JOURNAL, 2004, 328 (7441): : 702 - 708
  • [10] Carpenter JamesR., 2013, MULTIPLE IMPUTATION