Background and Objectives: This study was designed to evaluate the impact of a short biostatistics course on knowledge and performance of statistical analysis by biomedical researchers in Africa. It is recognized that knowledge of biostatistics is essential for understanding and interpretation of modern scientific literature and active participation in the global research enterprise. Unfortunately, it has been observed that basic education of African scholars may be deficient in applied mathematics including biostatistics.
Materials and Methods: Forty university affiliated biomedical researchers from South Africa volunteered for a 4-day short-course where participants were exposed to lectures on descriptive and inferential biostatistics and practical training on using a statistical software package for data analysis. A quantitative questionnaire was used to evaluate participants' statistical knowledge and performance pre- and post-course. Changes in knowledge and performance were measured using objective and subjective criteria. Data from completed questionnaires were captured and analyzed using Statistical Package for Social Sciences. Participants' pre- and post-course data were compared using nonparametric Wilcoxon signed ranks tests for nonnormally distributed variables. A P < 0.05 was considered statistically significant.
Results: Baseline testing of statistical knowledge showed a median score of 0, with 75th percentile at 28.6%, and a maximum score of 71.4%. Postcourse evaluation revealed improvement in participants' core knowledge with the median score increasing to 28.5%; and the 75th percentile score to 85.7%; signifying improved understanding of statistical concepts and ability to carry out data analyses.
Conclusions: This study just showed poor baseline knowledge of biostatistics among postgraduate scholars and health science researchers in this cohort and highlights the potential benefits of short-courses in biostatistics to improve the knowledge and skills of biomedical researchers and scholars in Africa.