The numbers game: evaluation of statistics by obstetrics & gynecology.

Abstract

Statistical analysis has become integral to the planning, conduct, and reporting of modern medical research. Attention to the statistical aspects of manuscripts submitted to Obstetrics & Gynecology goes back approximately 40 years and the process used in their evaluation has evolved over that time. For the past 20 years, submissions with any type of statistics and being seriously considered for acceptance have routinely been reviewed by a Statistical Editor who judges the work on a number of statistical and design characteristics. Findings of the statistical design review (which has been done by one Statistical Editor over the entire 20-year period) are integrated into the editorial decision about acceptance. The statistical review generally leads to rejection of approximately 16-25% of manuscripts and in a larger proportion, it identifies less serious problems, the correction of which improves the final product.