Appropriate analysis and presentation of data is a must for good clinical practice

Abstract

Good Clinical Practice (GCP) is defined as an international ethical and scientific quality standard for designing, conducting, monitoring, auditing, analyzing and reporting trials that involve the participation of human subjects. This paper focuses mainly on the issues that need attention at the time of statistical analysis and reporting of results. Findings from a review of published articles in Turkey are also presented. The types of variables, the distributions of variables, the number of groups compared, the dependency structure among these groups and the primary goal of the analysis determine the appropriate method to be selected for the statistical analysis. The review of a stratified sample of research articles from 60 journals published in 1992 in Turkey revealed that in 56% of the cases the statistical methods were improper or inadequate. In 15% of the articles the authors failed to select an appropriate design for the proposed aim mentioned in the manuscript. Despite the recent improvements, the necessity and the value of performing and presenting research according to the international standards remains to be assimilated better by Turkish investigators.