ES EN
Head of The European Journal of Psychology Applied to Legal Context
Vol. 2. Num. 1. - 2010. Pages

Prediction of cannabis and cocaine use in adolescence using decision trees and logistic regression

[Prediction of cannabis and cocaine use in adolescence using decision trees and logistic regression]

Elena Gervilla and Alfonso Palmer



Abstract

Alcohol is currently the most consumed substance among the Spanish adolescent population. Some of the variables that bear an influence on this consumption include ease of access, use of alcohol by friends and some personality factors. The aim of this study was to analyze and quantify the predictive value of these variables specifically on alcohol consumption in the adolescent population. The useful sample was made up of 6,145 adolescents (49.8% boys and 50.2% girls) with a mean age of 15.4 years (SE= 1.2). The data were analyzed using the statistical model for a count variable and Data Mining techniques. The results show the influence of ease of access, alcohol consumption by the group of friends, and certain personality factors on alcohol intake, allowing us to quantify the intensity of this influence according to age and gender. Knowing these factors is the starting point in elaborating specific preventive actions against alcohol consumption.

Resumen

Copyright © 2019. Colegio Oficial de Psicólogos de Madrid

© Copyright 2019. Colegio Oficial de Psicólogos de Madrid Privacy PolicyCookies Policy

We use our own and third­party cookies. The data we compile is analysed to improve the website and to offer more personalized services. By continuing to browse, you are agreeing to our use of cookies. For more information, see our cookies policy

Aceptar