Using interrupted time series analysis to evaluate the impact of 10-valent pneumococcal conjugate vaccine on pneumonia admissions in Kilifi, Kenya

Two statistical methodologies are available to estimate the intervention effect in interrupted time series: segmented regression and intervention analysis. Michael aims to examine the relative performance of each method in terms of bias, variance and mean square error by simulating monthly rates of pneumonia admissions. He will then use the most appropriate method to estimate the impact of 10-valent pneumococcal conjugate vaccine on the incidence of pneumonia admissions in Kilifi County Hospital. Michael will be mentored and supervised by Professor Anthony Scott and Dr Christian Bottomley of London School of Hygiene and Tropical Medicine.

This grant was awarded under the scheme's previous name of Master's Fellowships in Public Health and Tropical Medicine.