Errors in the Archives of Dermatology and the Journal of the American Academy of Dermatology from January through December 2003.

OBJECTIVE To assess the frequency of statistical errors in the dermatology literature. DESIGN Original studies published in the Archives of Dermatology and the Journal of the American Academy of Dermatology from January through December 2003 were analyzed for correctness of statistical methods and reporting of the results. RESULTS Of 364 studies published, 155 included statistical analysis. Of these, 59 (38.1%) contained errors in the methods or omissions in reporting of the statistical results. Fourteen percent of the articles with statistical analysis contained errors in the methods used (considered to be more significant errors), 26.5% contained errors in the presentation of the results, and 2.6% contained errors in both. CONCLUSIONS The misuse of statistical methods is prevalent in the dermatology literature, and the appropriate use of these methods is an integral component of all studies. Readers should critically analyze the methods and results of studies published in the dermatology literature.