LOCPROJ: Stata module to estimate Local Projections

locproj estimates linear and non-linear Impulse Response Functions (IRF) based on the local projections methodology first proposed by Jordà (2005). The procedure allows easily implementation of several options used in the growing literature of local projections. It generates temporary variables with the necessary transformations of the response variable in order to estimate the IRF in the desired transformation option, such as levels, logs, differences, log-differences, cumulative changes or cumulative log-differences. It allows choosing different estimation methods for both time series and panel data, including some instrumental variables methods . It also allows the use of marginal effects instead of regression coefficients, which is highly convenient when the response variable is binary and the user wants to estimate the response as a probability. It reports the IRF, together with its standard error and confidence interval, as an output matrix and through an IRF graph. The user can easily choose different options for the desired IRF graph, as well as several other options to save and use the results. The module also includes a post-estimation command called lpgraph that allows plotting together IRFs estimated by different models.