TY - JOUR
T1 - Statistical reporting in randomized controlled trials from the dermatology literature
T2 - A review of 44 dermatology journals
AU - McClean, M.
AU - Silverberg, J. I.
PY - 2015/7
Y1 - 2015/7
N2 - Background The validity of randomized controlled trials (RCTs) is determined by several statistical factors. Objectives To determine the level of recent statistical reporting in RCTs from the dermatology literature. Methods We searched MEDLINE for all RCTs published between 1 May 2013 and 1 May 2014 in 44 dermatology journals. Results Two hundred and ten articles were screened, of which 181 RCTs from 27 journals were reviewed. Primary study outcomes were met in 122 (67·4%) studies. Sample size calculations and beta values were reported in 52 (28·7%) and 48 (26·5%) studies, respectively, and nonsignificant findings were supported in only 31 (17·1%). Alpha values were reported in 131 (72·4%) of studies with 45 (24·9%) having two-sided P-values, although adjustment for multiple statistical tests was performed in only 16 (9·9% of studies with ≥ two statistical tests performed). Sample size calculations were performed based on a single outcome in 44 (86·3%) and multiple outcomes in six (11·8%) studies. However, among studies that were powered for a single primary outcome, 20 (45·5%) made conclusions based on multiple primary outcomes. Twenty-one (41·2%) studies relied on secondary/unspecified outcomes. There were no differences for primary outcome being met (Chi-square, P = 0·29), sample size calculations (P ≥ 0·55), beta values (P = 0·89), alpha values (P = 0·65), correction for multiple statistical testing (P = 0·59), two-sided alpha (P = 0·64), support of nonsignificant findings (Fisher's exact, P = 0·23) based on the journal's impact factor. Conclusions Levels of statistical reporting are low in RCTs from the dermatology literature. Future work is needed to improve these levels of reporting. What's already known about this topic? Previous studies have found varied levels of statistical reporting across different medical specialties. What does this study add? The present study demonstrates a low level of statistical reporting in randomized controlled trials from the dermatology literature.
AB - Background The validity of randomized controlled trials (RCTs) is determined by several statistical factors. Objectives To determine the level of recent statistical reporting in RCTs from the dermatology literature. Methods We searched MEDLINE for all RCTs published between 1 May 2013 and 1 May 2014 in 44 dermatology journals. Results Two hundred and ten articles were screened, of which 181 RCTs from 27 journals were reviewed. Primary study outcomes were met in 122 (67·4%) studies. Sample size calculations and beta values were reported in 52 (28·7%) and 48 (26·5%) studies, respectively, and nonsignificant findings were supported in only 31 (17·1%). Alpha values were reported in 131 (72·4%) of studies with 45 (24·9%) having two-sided P-values, although adjustment for multiple statistical tests was performed in only 16 (9·9% of studies with ≥ two statistical tests performed). Sample size calculations were performed based on a single outcome in 44 (86·3%) and multiple outcomes in six (11·8%) studies. However, among studies that were powered for a single primary outcome, 20 (45·5%) made conclusions based on multiple primary outcomes. Twenty-one (41·2%) studies relied on secondary/unspecified outcomes. There were no differences for primary outcome being met (Chi-square, P = 0·29), sample size calculations (P ≥ 0·55), beta values (P = 0·89), alpha values (P = 0·65), correction for multiple statistical testing (P = 0·59), two-sided alpha (P = 0·64), support of nonsignificant findings (Fisher's exact, P = 0·23) based on the journal's impact factor. Conclusions Levels of statistical reporting are low in RCTs from the dermatology literature. Future work is needed to improve these levels of reporting. What's already known about this topic? Previous studies have found varied levels of statistical reporting across different medical specialties. What does this study add? The present study demonstrates a low level of statistical reporting in randomized controlled trials from the dermatology literature.
UR - http://www.scopus.com/inward/record.url?scp=84947044868&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84947044868&partnerID=8YFLogxK
U2 - 10.1111/bjd.13907
DO - 10.1111/bjd.13907
M3 - Review article
C2 - 25989239
AN - SCOPUS:84947044868
VL - 173
SP - 172
EP - 183
JO - British Journal of Dermatology
JF - British Journal of Dermatology
SN - 0007-0963
IS - 1
ER -