An empirical confirmation of the superior performance of MIDAS over ARIMAX

An empirical confirmation of the superior performance of MIDAS over ARIMAX

© Springer International Publishing AG 2016. A new model (MIDAS) for forecasting economic data has been proposed recently to take into account of more relevant information than the ARIMAX model. However, in order to convince econometricians to use MIDAS instead of ARIMAX, at least some evidence from...

Full description

Saved in:
Bibliographic Details
Main Authors: Tanaporn Tungtrakul, Natthaphat Kingnetr, Songsak Sriboonchitta
Format: Book Series
Published: 2018
Subjects:
Computer Science
Mathematics
Online Access:https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85005976075&origin=inward
http://cmuir.cmu.ac.th/jspui/handle/6653943832/55575
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Chiang Mai University
id th-cmuir.6653943832-55575
record_format dspace
spelling th-cmuir.6653943832-555752018-09-05T03:06:50Z An empirical confirmation of the superior performance of MIDAS over ARIMAX Tanaporn Tungtrakul Natthaphat Kingnetr Songsak Sriboonchitta Computer Science Mathematics © Springer International Publishing AG 2016. A new model (MIDAS) for forecasting economic data has been proposed recently to take into account of more relevant information than the ARIMAX model. However, in order to convince econometricians to use MIDAS instead of ARIMAX, at least some evidence from empirical studies is needed, to indicate that the forecast performance of MIDAS is superior than that of ARIMAX. Our present work precisely aims at filling this need. In doing so, we also investigate a practical problem: Forecasting export growth in Thailand. Our empirical findings confirm that the MIDAS regression model significantly improves the forecast accuracy when compared with the ARIMAX model. 2018-09-05T02:58:01Z 2018-09-05T02:58:01Z 2016-01-01 Book Series 16113349 03029743 2-s2.0-85005976075 10.1007/978-3-319-49046-5_51 https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85005976075&origin=inward http://cmuir.cmu.ac.th/jspui/handle/6653943832/55575
institution Chiang Mai University
building Chiang Mai University Library
country Thailand
collection CMU Intellectual Repository
topic Computer Science
Mathematics
spellingShingle Computer Science
Mathematics
Tanaporn Tungtrakul
Natthaphat Kingnetr
Songsak Sriboonchitta
An empirical confirmation of the superior performance of MIDAS over ARIMAX
description © Springer International Publishing AG 2016. A new model (MIDAS) for forecasting economic data has been proposed recently to take into account of more relevant information than the ARIMAX model. However, in order to convince econometricians to use MIDAS instead of ARIMAX, at least some evidence from empirical studies is needed, to indicate that the forecast performance of MIDAS is superior than that of ARIMAX. Our present work precisely aims at filling this need. In doing so, we also investigate a practical problem: Forecasting export growth in Thailand. Our empirical findings confirm that the MIDAS regression model significantly improves the forecast accuracy when compared with the ARIMAX model.
format Book Series
author Tanaporn Tungtrakul
Natthaphat Kingnetr
Songsak Sriboonchitta
author_facet Tanaporn Tungtrakul
Natthaphat Kingnetr
Songsak Sriboonchitta
author_sort Tanaporn Tungtrakul
title An empirical confirmation of the superior performance of MIDAS over ARIMAX
title_short An empirical confirmation of the superior performance of MIDAS over ARIMAX
title_full An empirical confirmation of the superior performance of MIDAS over ARIMAX
title_fullStr An empirical confirmation of the superior performance of MIDAS over ARIMAX
title_full_unstemmed An empirical confirmation of the superior performance of MIDAS over ARIMAX
title_sort empirical confirmation of the superior performance of midas over arimax
publishDate 2018
url https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85005976075&origin=inward
http://cmuir.cmu.ac.th/jspui/handle/6653943832/55575
_version_ 1681424531402522624

Similar Items