Predictive Ability Tests with Possibly Overlapping Models (with Valentina Corradi and Daniel Gutknecht) - Economics Seminar
Event Date: 23 November 2022
Speaker: Jack Fosten, Lecturer, King's College London Business School
Time: 4-5:15pm
Location: Please contact Rachel Hill (r.hill@strath.ac.uk) for Zoom details
Abstract: "This paper provides novel tests for comparing out-of-sample predictive ability of two or more competing models that are possibly overlapping. The tests do not require pre-testing, and importantly are valid under different out-of-sample estimation schemes, under dynamic mis-specification, and under general loss functions used for forecast evaluation. In pairwise model comparisons, the test is constructed by adding a random perturbation to both the numerator and denominator of a standard Diebold-Mariano test statistic, which prevents degeneracy in the presence of overlapping models, but becomes asymptotically negligible otherwise. A similar idea is used to develop a superior predictive ability test for the comparison of multiple models to a benchmark. We establish the first order validity of block bootstrap critical values which are simple to compute."
Published: 3 November 2022