Many developing country governments seek to improve the productivity and export competitiveness of their SME sectors. We will run a randomized experiment to test whether improving management practices can achieve these goals, in the context of a government-sponsored management technical assistance program in one middle-income country. A treatment group of 100 firms will receive a diagnostic of their management practices, 190 hours of technical assistance, and then participate in a trade fair, while a control group of 100 firms will receive the diagnostic and trade fair only. Rich administrative data on export transactions will enable us to track whether this program leads to firms being more likely to export, diversifying what they export and where they export to, and improving export productivity. A key methodological innovation is the comparison of a Bayesian impact evaluation framework to a frequentist approach, highlighting what we can learn from each in a sample of modest size.