Imputing missing standard deviations in meta-analyses can provide accurate results.

BACKGROUND AND OBJECTIVES Many reports of randomized controlled trials (RCTs) fail to provide standard deviations (SDs) of their continuous outcome measures. Some meta-analysts substitute them by those reported in other studies, either from another meta-analysis or from other studies in the same meta-analysis. But the validity of such practices has never been empirically examined. METHODS We compared the actual standardized mean difference (SMD) of individual RCTs and the meta-analytically pooled SMD of all RCTs against those based on the above-mentioned two imputation methods in two meta-analyses of antidepressants. RESULTS Two meta-analyses included 39 RCTs of fluoxetine (n = 3,681) and 25 RCTs of amitriptyline (n = 1,832), which had actually reported means and SDs of the Hamilton Rating Scale for Depression. According to either of the two proposed imputation methods, the agreement between actual SMDs and imputed SMDs for individual RCTs was very good with ANOVA intraclass correlation coefficients between 0.61 and 0.97. The agreement between the actual pooled SMD and the imputed one was even better, with minimal differences in both their point estimates and 95% confidence intervals. CONCLUSION For a systematic review where some of the identified trials do not report SDs, it appears safe to borrow SDs from other studies.

[1]  D. Streiner,et al.  Antidepressant plus benzodiazepine for major depression. , 2000, The Cochrane database of systematic reviews.

[2]  Peter A. Lachenbruch,et al.  Some unsolved practical problems in discriminant analysis , 1975 .

[3]  Fluoxetine versus other types of pharmacotherapy for depression , 2013 .

[4]  D. Streiner,et al.  Antidepressants plus benzodiazepines for major depression , 2001 .

[5]  B. Everitt,et al.  Statistical methods for rates and proportions , 1973 .

[6]  C. R.J.,et al.  Statistics with Confidence (2nd ed.) , 2003 .

[7]  J. Fleiss,et al.  Statistical methods for rates and proportions , 1973 .

[8]  M. Hotopf,et al.  Amitriptyline versus other types of pharmacotherapy for depression. , 2003, The Cochrane database of systematic reviews.

[9]  J. Cutler,et al.  Variance imputation for overviews of clinical trials with continuous response. , 1992, Journal of clinical epidemiology.

[10]  R. Joffe,et al.  Antidepressant Treatment of Depression: A Metaanalysis , 1996, Canadian journal of psychiatry. Revue canadienne de psychiatrie.

[11]  M. Hotopf,et al.  Fluoxetine versus other types of pharmacotherapy for depression. , 2005, The Cochrane database of systematic reviews.

[12]  I Russell,et al.  Statistics--with confidence? , 1991, The British journal of general practice : the journal of the Royal College of General Practitioners.

[13]  N. Laird,et al.  Meta-analysis in clinical trials. , 1986, Controlled clinical trials.

[14]  Cindy Farquhar,et al.  3 The Cochrane Library , 1996 .

[15]  M. Åsberg,et al.  A New Depression Scale Designed to be Sensitive to Change , 1979, British Journal of Psychiatry.

[16]  Kenneth W. Wachter,et al.  The Future of Meta-Analysis , 1991 .

[17]  D. Moher,et al.  The Revised CONSORT Statement for Reporting Randomized Trials: Explanation and Elaboration , 2001, Annals of Internal Medicine.

[18]  M. Hamilton.  A RATING SCALE FOR DEPRESSION , 1960, Journal of neurology, neurosurgery, and psychiatry.

[19]  Larry V. Hedges,et al.  Directions for future methodology. , 1990 .

[20]  M. Smithson.  Statistics with confidence , 2000 .

[21]  Gordon H Guyatt,et al.  Can we individualize the 'number needed to treat'? An empirical study of summary effect measures in meta-analyses. , 2002, International journal of epidemiology.

[22]  J. Sterne,et al.  Publication and related bias in meta-analysis: power of statistical tests and prevalence in the literature. , 2000, Journal of clinical epidemiology.