Structure learning: some testing problems
The work is based on data about the prevalence of congenital anomalies among newborns in Lithuania. The log-linear model is used to assess dependence structure of a subset of categorical variables. It is shown that fitting the log-linear model with just three categorical variables can be a rather c...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Vilnius University Press
2005-12-01
|
| Series: | Lietuvos Matematikos Rinkinys |
| Subjects: | |
| Online Access: | https://www.journals.vu.lt/LMR/article/view/27388 |
| _version_ | 1797194441182674944 |
|---|---|
| author | Marijus Radavičius Jurgita Židanavičiūtė |
| author_facet | Marijus Radavičius Jurgita Židanavičiūtė |
| author_sort | Marijus Radavičius |
| collection | DOAJ |
| description |
The work is based on data about the prevalence of congenital anomalies among newborns in Lithuania. The log-linear model is used to assess dependence structure of a subset of categorical variables. It is shown that fitting the log-linear model with just three categorical variables can be a rather complicated task due to large number of unknown parameters and cells in the contingency table. The classical chi-squre test and the bootstrap technique are compared for testing goodness-of-fit. The results demonstrate that the number of cells of even nonsparse contingency tables has significant impact on the tail distribution of the likelihood ratio statistics.
|
| first_indexed | 2024-03-07T15:40:16Z |
| format | Article |
| id | doaj.art-155d772c4ad041859641e47f26b1e5c8 |
| institution | Directory Open Access Journal |
| issn | 0132-2818 2335-898X |
| language | English |
| last_indexed | 2024-04-24T05:56:20Z |
| publishDate | 2005-12-01 |
| publisher | Vilnius University Press |
| record_format | Article |
| series | Lietuvos Matematikos Rinkinys |
| spelling | doaj.art-155d772c4ad041859641e47f26b1e5c82024-04-23T09:01:30ZengVilnius University PressLietuvos Matematikos Rinkinys0132-28182335-898X2005-12-0145spec.10.15388/LMR.2005.27388Structure learning: some testing problemsMarijus Radavičius0Jurgita Židanavičiūtė1Institute of Mathematics and InformaticsVilnius Gediminas Technical University The work is based on data about the prevalence of congenital anomalies among newborns in Lithuania. The log-linear model is used to assess dependence structure of a subset of categorical variables. It is shown that fitting the log-linear model with just three categorical variables can be a rather complicated task due to large number of unknown parameters and cells in the contingency table. The classical chi-squre test and the bootstrap technique are compared for testing goodness-of-fit. The results demonstrate that the number of cells of even nonsparse contingency tables has significant impact on the tail distribution of the likelihood ratio statistics. https://www.journals.vu.lt/LMR/article/view/27388contingency tableslog-linear modelscategorical databootstrap |
| spellingShingle | Marijus Radavičius Jurgita Židanavičiūtė Structure learning: some testing problems Lietuvos Matematikos Rinkinys contingency tables log-linear models categorical data bootstrap |
| title | Structure learning: some testing problems |
| title_full | Structure learning: some testing problems |
| title_fullStr | Structure learning: some testing problems |
| title_full_unstemmed | Structure learning: some testing problems |
| title_short | Structure learning: some testing problems |
| title_sort | structure learning some testing problems |
| topic | contingency tables log-linear models categorical data bootstrap |
| url | https://www.journals.vu.lt/LMR/article/view/27388 |
| work_keys_str_mv | AT marijusradavicius structurelearningsometestingproblems AT jurgitazidanaviciute structurelearningsometestingproblems |