The Predictive Power of Transition Matrices
When working with Markov chains, especially if they are of order greater than one, it is often necessary to evaluate the respective contribution of each lag of the variable under study on the present. This is particularly true when using the Mixture Transition Distribution model to approximate the t...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-11-01
|
Series: | Symmetry |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-8994/13/11/2096 |
_version_ | 1797508367367798784 |
---|---|
author | André Berchtold |
author_facet | André Berchtold |
author_sort | André Berchtold |
collection | DOAJ |
description | When working with Markov chains, especially if they are of order greater than one, it is often necessary to evaluate the respective contribution of each lag of the variable under study on the present. This is particularly true when using the Mixture Transition Distribution model to approximate the true fully parameterized Markov chain. Even if it is possible to evaluate each transition matrix using a standard association measure, these measures do not allow taking into account all the available information. Therefore, in this paper, we introduce a new class of so-called "predictive power" measures for transition matrices. These measures address the shortcomings of traditional association measures, so as to allow better estimation of high-order models. |
first_indexed | 2024-03-10T05:01:08Z |
format | Article |
id | doaj.art-61a092af93754d3fa9c45828bf8f5a71 |
institution | Directory Open Access Journal |
issn | 2073-8994 |
language | English |
last_indexed | 2024-03-10T05:01:08Z |
publishDate | 2021-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Symmetry |
spelling | doaj.art-61a092af93754d3fa9c45828bf8f5a712023-11-23T01:44:53ZengMDPI AGSymmetry2073-89942021-11-011311209610.3390/sym13112096The Predictive Power of Transition MatricesAndré Berchtold0Institute of Social Sciences & NCCR LIVES, University of Lausanne, CH-1015 Lausanne, SwitzerlandWhen working with Markov chains, especially if they are of order greater than one, it is often necessary to evaluate the respective contribution of each lag of the variable under study on the present. This is particularly true when using the Mixture Transition Distribution model to approximate the true fully parameterized Markov chain. Even if it is possible to evaluate each transition matrix using a standard association measure, these measures do not allow taking into account all the available information. Therefore, in this paper, we introduce a new class of so-called "predictive power" measures for transition matrices. These measures address the shortcomings of traditional association measures, so as to allow better estimation of high-order models.https://www.mdpi.com/2073-8994/13/11/2096predictive powermeasure of associationtransition matrixMarkov chainMTD model |
spellingShingle | André Berchtold The Predictive Power of Transition Matrices Symmetry predictive power measure of association transition matrix Markov chain MTD model |
title | The Predictive Power of Transition Matrices |
title_full | The Predictive Power of Transition Matrices |
title_fullStr | The Predictive Power of Transition Matrices |
title_full_unstemmed | The Predictive Power of Transition Matrices |
title_short | The Predictive Power of Transition Matrices |
title_sort | predictive power of transition matrices |
topic | predictive power measure of association transition matrix Markov chain MTD model |
url | https://www.mdpi.com/2073-8994/13/11/2096 |
work_keys_str_mv | AT andreberchtold thepredictivepoweroftransitionmatrices AT andreberchtold predictivepoweroftransitionmatrices |