My research in the department will contribute to the advancement of statistical methodology for prediction models in the context of diagnosis and prognosis in primary care. I am particularly interested in developing methods that are robust to common design and data problems such as small sample sizes and missing data. My statistical vision is the dissemination of statistical solutions to complex design and data problems in an easily accessible and usable software format (R packages).
My previous research experience has spanned the development, analysis, and reporting of interventional (both human and entomological) and observational studies in malaria and early learning. My statistical methodological interests include correlated data analysis (longitudinal, time series, clustered, multivariate and spatial), missing data handling methods, and sample size estimation for power and precision.
My current research will inform the diagnosis and prognosis of covid-19, lower tract respiratory infections and sepsis.