Prescott and Civil (1) present the results of statistical reviews of 100 consecutive manuscripts submitted to Injury during 2010-2012.
Of the 100 manuscripts suggestions for improvement were made for 90 (90%). Inappropriate analyses were identified in 47 (47%) manuscripts, and other errors were seen in 45 (45%).
The reviews identified a wide range of statistical problems, but many of these can be easily avoided. The authors suggest that using reporting guidelines could reduce the number of papers requiring corrections.
1. Prescott RJ, Civil I. Lies, damn lies and statistics: Errors and omission in papers submitted to Injury 2010-2012. Injury 2013;44:6-11.