L'analyse log-linéaire de tableaux de contingence et le modèle logit I : principe, usage, intérêt et limites

This paper introduces the theoretical basis of the loglinear methods, as a substitute to analysis of variance when variables are categorical, and logit, as a substitute to regression analysis in the same context. Their specific advantage is to allow the modelling of categorical, thus qualitative dat...

Full description

Bibliographic Details
Main Authors: Estelle Kah, Michel Pruvot
Format: Article
Language:deu
Published: Unité Mixte de Recherche 8504 Géographie-cités 2003-01-01
Series:Cybergeo
Subjects:
Online Access:https://journals.openedition.org/cybergeo/3481
_version_ 1797223023076442112
author Estelle Kah
Michel Pruvot
author_facet Estelle Kah
Michel Pruvot
author_sort Estelle Kah
collection DOAJ
description This paper introduces the theoretical basis of the loglinear methods, as a substitute to analysis of variance when variables are categorical, and logit, as a substitute to regression analysis in the same context. Their specific advantage is to allow the modelling of categorical, thus qualitative data, often collected from surveys, while keeping their probabilistic nature. The stress is put on the concepts of interaction and odds ratio which allow to unveil complex phenomena with nonlinear relations.
first_indexed 2024-03-08T03:01:33Z
format Article
id doaj.art-f2ed7143edf646eab8c21e9824c39e89
institution Directory Open Access Journal
issn 1278-3366
language deu
last_indexed 2024-04-24T13:30:37Z
publishDate 2003-01-01
publisher Unité Mixte de Recherche 8504 Géographie-cités
record_format Article
series Cybergeo
spelling doaj.art-f2ed7143edf646eab8c21e9824c39e892024-04-04T09:32:39ZdeuUnité Mixte de Recherche 8504 Géographie-citésCybergeo1278-33662003-01-0110.4000/cybergeo.3481L'analyse log-linéaire de tableaux de contingence et le modèle logit I : principe, usage, intérêt et limitesEstelle KahMichel PruvotThis paper introduces the theoretical basis of the loglinear methods, as a substitute to analysis of variance when variables are categorical, and logit, as a substitute to regression analysis in the same context. Their specific advantage is to allow the modelling of categorical, thus qualitative data, often collected from surveys, while keeping their probabilistic nature. The stress is put on the concepts of interaction and odds ratio which allow to unveil complex phenomena with nonlinear relations.https://journals.openedition.org/cybergeo/3481interactionlogistic modelloglinearodds ratioqualitative data
spellingShingle Estelle Kah
Michel Pruvot
L'analyse log-linéaire de tableaux de contingence et le modèle logit I : principe, usage, intérêt et limites
Cybergeo
interaction
logistic model
loglinear
odds ratio
qualitative data
title L'analyse log-linéaire de tableaux de contingence et le modèle logit I : principe, usage, intérêt et limites
title_full L'analyse log-linéaire de tableaux de contingence et le modèle logit I : principe, usage, intérêt et limites
title_fullStr L'analyse log-linéaire de tableaux de contingence et le modèle logit I : principe, usage, intérêt et limites
title_full_unstemmed L'analyse log-linéaire de tableaux de contingence et le modèle logit I : principe, usage, intérêt et limites
title_short L'analyse log-linéaire de tableaux de contingence et le modèle logit I : principe, usage, intérêt et limites
title_sort l analyse log lineaire de tableaux de contingence et le modele logit i principe usage interet et limites
topic interaction
logistic model
loglinear
odds ratio
qualitative data
url https://journals.openedition.org/cybergeo/3481
work_keys_str_mv AT estellekah lanalyseloglineairedetableauxdecontingenceetlemodelelogitiprincipeusageinteretetlimites
AT michelpruvot lanalyseloglineairedetableauxdecontingenceetlemodelelogitiprincipeusageinteretetlimites