Economics research considered unreplicable

Andrew C. Chang and Phillip Li undertook a study of "67 papers published in 13 well-regarded economics journals" for the US Federal Reserve and attempted to replicate their conclusions, using the code and data-sets provided by the authors: in two-thirds of cases, they were unable to replicate the findings without help with the authors; with the help of authors, they were still only able to replicate 49% of the papers. (more…)