The aim of this study is to estimate the wind energy potential at four locations in Burundi: Bujumbura, Gisozi, Gitega and Mpota. For this endeavour, some commonly used statistical probability distribution functions (PDFs) (i.e., Burr, Gamma, Lognormal, Normal, Rayleigh and Weibull) are assessed in the modelling of around 20 years of daily wind speed data measured at the four locations. The parameters for each PDF are estimated using the Maximum likelihood method and goodness-of-fit tests are used to assess how well the PDFs fit the data. It is found that the Burr distribution fits all the data at 0.05 significance level. Finally, computed Burr parameters for monthly wind speed datasets are used to estimate the mean monthly wind power density (WPD) at each location. Results obtained show that Bujumbura has high potential for wind energy harvesting