A better understanding of statistical data analysis enhances the capacity of postgraduate students and junior researchers to meaningfully engage in conducting quality research by developing appropriate research proposals, design of studies, collection, and analysis of data for meaningful reporting. Ph.D. and MSc students are heavily involved in large-scale experiments or surveys that sometimes lead to complex designs and to subsequent messy data. Figuring out how to handle data resulting from such experiments/surveys takes time, and getting appropriate assistance is difficult. The students are also constrained on how to effectively analyze data using appropriate statistical software, interpret the results and communicate well to the target audience. In recognition of these shortcomings, this course was structured to encompass broad biometrical needs that would equip the postgraduate students with the skills required in conducting their research efficiently and effectively. The content incorporated in this course was drawn from broader topics ranging from planning experiments/surveys, designing, and implementing experiments, and conducting data analysis. The students were also exposed to R programming language for data management, analysis, and reporting

Given that most commercial statistical software is expensive, R a free statistical programming language has become a very powerful statistical tool among researchers worldwide.  Most universities worldwide are moving away from commercial software such as SAS, STATA, and SPSS to free open-source software, especially R and Python. According to the TIOBE index, R is popularly ranked 8th among scholarly users throughout the world (Nayeemuddin, 2019). R has a numerals number of advantages that support anyone who is interested in data analysis and any user can quickly learn R whether a data scientist or not.

The course was targeted at postgraduate students but not limited to in any of the following fields: Plant Breeding, Crop and Horticultural Sciences, Animal Sciences, Agricultural Economics, Plant Protection, Food Science, Natural Resource Management, Aquaculture, and Fisheries Sciences.

The aim of this training was to build research capacity for the next generation of African scientists to achieve the following: understand the various biometrical components pertaining to design and analysis of experiments/surveys; apply various statistical techniques correctly at all stages of research and report the results effectively. The training equipped postgraduate students with the skills and knowledge in use of R programming language for data management, analysis, and presentation of results in a format that would ensure their wide dissemination as peer reviewed publications and policy formulation. It was expected that this training would provide hands-on skills for the students to improve the quality of their research publications. The training would also be an opportunity for postgraduate students to prepare their draft thesis.

The following modules, which cover the whole range of applied biometrics, say, from basic concepts to computing and results presentation provided a framework for the training material. The topics concentrated on introducing statistical concepts in a non-theoretical way, with computer-based practical being used to illustrate the different concepts. These were highly practical topics intended to increase the participants’ awareness of biometrical techniques for data management and analysis in their own specialist areas. The students were grouped according to their area of interest and given assignments with data related to their area followed by presentations at the end of the day which were conducted online.

The training modules included: Introduction to R programming language, Research design, data collection and Management, Exploratory data analysis, Linear models, Generalized linear models, Analysis of repeated measures, Multivariate analysis, Analysis of multi-environment trials (MET).