Preview |
PDF, English
Download (588kB) | Terms of use |
Abstract
We derive new tests for proper calibration of multivariate density forecasts based on Rosenblatt probability integral transforms. These tests have the advantage that they i) do not depend on the ordering of variables in the forecasting model, ii) are applicable to densities of arbitrary dimensions, and iii) have superior power relative to existing approaches. We furthermore develop adjusted tests that allow for estimated parameters and, consequently, can be used as in-sample specification tests. We demonstrate the problems of existing tests and how our new approaches can overcome those using Monte Carlo Simulation as well as two applications based on multivariate GARCH-based models for stock market returns and on a macroeconomic Bayesian vectorautoregressive model.
Document type: | Working paper |
---|---|
Series Name: | Discussion Paper Series, University of Heidelberg, Department of Economics |
Volume: | 0608 |
Place of Publication: | Heidelberg |
Date Deposited: | 08 Mar 2016 09:03 |
Date: | March 2016 |
Number of Pages: | 41 |
Faculties / Institutes: | The Faculty of Economics and Social Studies > Alfred-Weber-Institut for Economics |
DDC-classification: | 330 Economics |
Uncontrolled Keywords: | density calibration, goodness-of-fit test, predictive density, Rosenblatt transformation |
Series: | Discussion Paper Series / University of Heidelberg, Department of Economics |