Replicating Sachs and Warner's Working Papers on the Resource Curse

This article reports on my attempt to replicate Sachs and Warner's 1995 and 1997 resource curse working papers. The 1995 paper is not replicable for lack of a data archive. Pure replication of the 1997 paper is achieved. Statistical replication determines that the proposed institutional causes of the resource curse are not robust to country sample. Scientific replication shows that findings of a resource curse are not sensitive to different measures of resource intensiveness, though they are sensitive to estimation technique. Typographical errors in the published paper reveal the value of researchers making both their data and code available.