Some statistical tests based on divergence measures
Закрыть

Error message

  • Notice: Trying to get property of non-object in publication_view_data() (line 909 of /var/www/sites/idsi/ibn2014/trunk/sites/all/modules/publication_view/publication_view.module).
  • Notice: Trying to get property of non-object in publication_view_data() (line 927 of /var/www/sites/idsi/ibn2014/trunk/sites/all/modules/publication_view/publication_view.module).
Articolul precedent
Articolul urmator
127 1
Ultima descărcare din IBN:
2024-05-10 04:47
SM ISO690:2012
BARBU, Vlad Stefan. Some statistical tests based on divergence measures. In: Conference on Applied and Industrial Mathematics: CAIM 2022, Ed. 30, 14-17 septembrie 2023, Chişinău. Iași, România: 2023, Ediţia 30, p. 54.
EXPORT metadate:
Google Scholar
Crossref
CERIF

DataCite
Dublin Core
Conference on Applied and Industrial Mathematics
Ediţia 30, 2023
Conferința "Conference on Applied and Industrial Mathematics"
30, Chişinău, Moldova, 14-17 septembrie 2023

Some statistical tests based on divergence measures


Pag. 54-54

Barbu Vlad Stefan
 
University of Rouen-Normandy
 
 
Disponibil în IBN: 21 martie 2024


Rezumat

Divergence measures are of great importance in statistical inference; equally important are their limiting versions, known as divergence rates. In the first part of our presentation, we focus on generalized divergence measures for Markov chains. We consider generalizations of Alpha divergence measure (Amari and Nagaoka, 2000) and Beta divergence measures (Basu et. al, 1998) and investigate their limiting behaviour. We also study the corresponding weighted generalized divergence measures and the associated rates (Belis and Guiasu, 1968; Guiasu, 1971; Kapur, 1994). In the second part of our presentation, we focus on hypothesis testing based on weighted divergences. More precisely, we present a goodness of fit test and a homogeneity test and we study their performance. This type of tests based on weighted divergences allow us to focus on specific subsets of the support without, at the same time, losing the information of the others. With this method we achieve a significantly more sensitive test than the classical ones but with comparable error rates.

Cuvinte-cheie
Divergence measures, weighted divergence measures, entropy, Markov Processes, hypotheses testing

Crossref XML Export

<?xml version='1.0' encoding='utf-8'?>
<doi_batch version='4.3.7' xmlns='http://www.crossref.org/schema/4.3.7' xmlns:xsi='http://www.w3.org/2001/XMLSchema-instance' xsi:schemaLocation='http://www.crossref.org/schema/4.3.7 http://www.crossref.org/schema/deposit/crossref4.3.7.xsd'>
<head>
<doi_batch_id>ibn-200065</doi_batch_id>
<timestamp>1719572347</timestamp>
<depositor>
<depositor_name>Information Society Development Instiute, Republic of Moldova</depositor_name>
<email_address>[email protected]</email_address>
</depositor>
</head>
<body>
<collection>
<collection_metadata>
<full_title>Conference on Applied and Industrial Mathematics</full_title>
</collection_metadata>
<collection_issue>
<publication_date media_type='print'>
<year>2023</year>
</publication_date>
</collection_issue>
<collection_article publication_type='full_text'><titles>
<title>Some statistical tests based on divergence measures</title>
</titles>
<contributors>
<person_name sequence='first' contributor_role='author'>
<given_name>Vlad Stefan</given_name>
<surname>Barbu</surname>
</person_name>
</contributors>
<publication_date media_type='print'>
<year>2023</year>
</publication_date>
<pages>
<first_page>54</first_page>
<last_page>54</last_page>
</pages>
</collection_article>
</collection>
</body>
</doi_batch>