1. Helgason (2016) asks this critical question in relation to KL&W's claims: “However, in their simulation analysis they do not provide a comparison with the most relevant counterfactual: Namely, whether assuming that data is stationary or integrated while it is actually fractionally integrated is preferable to employing an uncertain estimate of fractional integration and proceeding accordingly.”
2. For now, Stata only allows use of the inferior EML estimator. Both Robinson's and Geweke's estimators are available in RATS. A wider array of fractional methods may also be found in either R or Matlab. R is open source. Economists using fractional methods are generally quite generous in sharing their Matlab code.
3. The Dynamics of the Partisan Gender Gap
4. Enders Walter . 2004. Applied econometric time series. 2nd ed. New York: Wiley.