Reproducibility of economic research has attracted considerable attention in recent years. So far, the discussion has focused on reproducibility of empirical analyses. This paper addresses a further aspect of reproducibility, the reproducibility of computational experiments. We examine the current situation in econometrics and derive a set of guidelines from our findings. To illustrate how computational experiments could be conducted and reported we present an example from time series econometrics that explores the finite-sample power of certain structural change tests.
