NEW MSE TESTS FOR EVALUATING FORECASTING PERFORMANCE: EMPIRICS AND BOOTSTRAP

Two asymptotically valid out-of-sample MSE tests have been developed by Diebold-Mariano (1995) and Stock-Watson (1999). The empirical usefulness of the tests is illustrated through a U.S. wheat model estimated with fixed, recursive and rolling forecasting schemes. Bootstrap methods are adopted to reflect small sample size effect on tests.


Issue Date:
2001
Publication Type:
Conference Paper/ Presentation
PURL Identifier:
http://purl.umn.edu/20686
Total Pages:
17
Series Statement:
Selected Paper




 Record created 2017-04-01, last modified 2017-08-24

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)