eprintid: 20376
rev_number: 14
eprint_status: archive
userid: 2744
dir: disk0/00/02/03/76
datestamp: 2016-03-08 09:03:10
lastmod: 2016-04-18 13:28:49
status_changed: 2016-03-08 09:03:10
type: workingPaper
metadata_visibility: show
creators_name: Dovern, Jonas
creators_name: Manner, Hans
title: Order Invariant Evaluation of Multivariate Density Forecasts
subjects: 330
divisions: 181000
keywords: density calibration, goodness-of-fit test, predictive density, Rosenblatt transformation
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.
date: 2016-03
id_scheme: DOI
id_number: 10.11588/heidok.00020376
schriftenreihe_cluster_id: sr-3
schriftenreihe_order: 0608
ppn_swb: 857214128
own_urn: urn:nbn:de:bsz:16-heidok-203762
language: eng
bibsort: DOVERNJONAORDERINVAR201603
full_text_status: public
series: Discussion Paper Series, University of Heidelberg, Department of Economics
volume: 0608
place_of_pub: Heidelberg
pages: 41
citation:   Dovern, Jonas ; Manner, Hans  (2016) Order Invariant Evaluation of Multivariate Density Forecasts.  [Working paper]     
document_url: https://archiv.ub.uni-heidelberg.de/volltextserver/20376/1/dovern_manner_2016_dp608.pdf