Volume 24, Issue 4, November 2018, Pages 1481–1488
Abdellatif ELLOUMI1, Olfa Ben Amor Zegnani2, and Abeljelil FARHAT3
1 Faculty of Economic and Management Sciences, Mahdia, Tunisia
2 Faculty of Economic and Management Sciences, Mahdia, Tunisia
3 Faculty of Economic and Management Sciences, Mahdia, Tunisia
Original language: English
Copyright © 2018 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
This study attempts to model a qualitative endogenous variable whose number exceeds two terms. We address the proper technique, which is the multinomial logit techniquemodel, to measure the impairment in sleep disorder in terms of the IAH. Then, a succinct description of the available data is provided. The main results achieved, applying the multinomial logistic regression, are expected and explained. The two variables (sex of the patient and Clinical snoring), exhibit very high coefficients in exponentials, which demonstrate their importance in distinguishing between the different categories (L, M and S). We propose a procedure for calculating rates of good rankings. In applying this procedure, we get a moderate rate of high good ranking. This positive output can be explained by the construction of the estimated values using the multi-class method in which these values were constructed using the conditional probabilities.
Author Keywords: Biostatistics, help to the medical decision, sleep disorder, modelling of the qualitative variables, Multinomial Logistic Regression.
Abdellatif ELLOUMI1, Olfa Ben Amor Zegnani2, and Abeljelil FARHAT3
1 Faculty of Economic and Management Sciences, Mahdia, Tunisia
2 Faculty of Economic and Management Sciences, Mahdia, Tunisia
3 Faculty of Economic and Management Sciences, Mahdia, Tunisia
Original language: English
Copyright © 2018 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
This study attempts to model a qualitative endogenous variable whose number exceeds two terms. We address the proper technique, which is the multinomial logit techniquemodel, to measure the impairment in sleep disorder in terms of the IAH. Then, a succinct description of the available data is provided. The main results achieved, applying the multinomial logistic regression, are expected and explained. The two variables (sex of the patient and Clinical snoring), exhibit very high coefficients in exponentials, which demonstrate their importance in distinguishing between the different categories (L, M and S). We propose a procedure for calculating rates of good rankings. In applying this procedure, we get a moderate rate of high good ranking. This positive output can be explained by the construction of the estimated values using the multi-class method in which these values were constructed using the conditional probabilities.
Author Keywords: Biostatistics, help to the medical decision, sleep disorder, modelling of the qualitative variables, Multinomial Logistic Regression.
How to Cite this Article
Abdellatif ELLOUMI, Olfa Ben Amor Zegnani, and Abeljelil FARHAT, “Sleep Disorder Modelling Test: Theories and applications based on the multinomial logit model,” International Journal of Innovation and Applied Studies, vol. 24, no. 4, pp. 1481–1488, November 2018.
