RJMDE - Official publication of Romanian Association of Dental Education

Romanian Association for Dental Education

St.Mihail Kocalniceanu No2. Iasi

Official Website

ADRE.RO

Telephone

+40735.523.366

Romanian Journal of Medical and Dental Education 2012,Volum 1 - Pilot METHODS FOR MULTIVARIATE DATA ANALYSIS IN THE STUDY OF ORAL DISEASES: THE MULTIPLE LINEAR REGRESSION

METHODS FOR MULTIVARIATE DATA ANALYSIS IN THE STUDY OF ORAL DISEASES: THE MULTIPLE LINEAR REGRESSION

Cristina DASCALU

METHODS FOR MULTIVARIATE DATA ANALYSIS IN THE STUDY OF ORAL DISEASES: THE MULTIPLE LINEAR REGRESSION (Abstract): During the statistical analysis of medical data, in many situations it is necessary to identify the multiple correlations
established between the studied parameters. In this purpose, one of the most useful methods is to build a model of multiple regression, which allows the modeling of a dependant variable values having at least the ordinal type, based on its linear relation with more than one independent variables satisfying the same restriction, called predictors. The multiple linear regression model is
a generalization of the simple linear regression model, which identifies the parameters of an equation with n variables y = b0+b1x1+b2x2+…+ bnxn+e, based on which we can find the predictors that have a statistically significant influence over the dependant variable. We used this model to identify, on a set of 202 patients having different types of oral lesions, the biochemical
analysis which can be eventually correlated with the oral diagnosis. We found that the values of leucocytes, hemoglobin and hematocrit are significant for the general oral diagnosis, the cholesterol and glucose values for the oral lesion type, and the hemoglobin for the periodontal disease. The identified predictors are useful for further data processing.

Read the entire article

Tags: , ,

By continuing to use the site, you agree to the use of cookies || Prin continuarea navigarii pe acest site esti de acord cu utilizarea cookie-urilor more information

The cookie settings on this website are set to "allow cookies" to give you the best browsing experience possible. If you continue to use this website without changing your cookie settings or you click "Accept" below then you are consenting to this. || journal.adre.ro utilizeaza fisiere de tip cookie pentru a personaliza si imbunatati experienta ta pe Website-ul nostru. Te informam ca ne-am actualizat politicile pentru a integra in acestea si in activitatea curenta a adre.ro cele mai recente modificari propuse de Regulamentul (UE) 2016/679 privind protectia persoanelor fizice in ceea ce priveste prelucrarea datelor cu caracter personal si privind libera circulatie a acestor date. inainte de a continua navigarea pe Website-ul nostru te rugam sa aloci timpul necesar pentru a citi si intelege continutul Politicii de Cookie. Prin continuarea navigarii pe Website-ul nostru confirmi acceptarea utilizarii fisierelor de tip cookie conform Politicii de Cookie. Nu uita totusi ca poti modifica in orice moment setarile acestor fisiere cookie urmand instructiunile din Politica de Cookie

Close