[Statistics in the clinical research on drugs. A study of original articles emanating from Spanish centers]

The aim of this study was to evaluate statistical analysis reported in clinical investigation articles of Spanish drugs.

Original articles provided by Spanish centers and indexed in EMBASE in 1975, 1980, 1985 and 1990 were studied. The type of statistics used, their description and different aspects of results presentation are reported.

Two hundred eighty-eight articles were studied of which 73.3% used inferential statistics with 57.3% presenting an adequate description of the same. The most frequently used statistical tests were bivariant techniques, mainly the Student's t test (33.7%) and chi square test (28.8%). The complexity of the statistical tests increased progressively in the years reviewed being greater in the articles published in foreign journals. The results were presented adequately and in a comprehensive form in 40% of the cases. Confidence intervals were used in 22.2% in the presentation of the results. In 49.1% of the articles statistical significance favored the group receiving the therapy studied. Of the 46.6% which did not present differences only 9.3% the statistical power was calculated.

Although an improvement was observed in the years evaluated, the articles on clinical drug investigation carried out in Spanish centers still present insufficient information on statistical methodology, particularly in those published in Spanish journals.