In applications involving ordinal predictors, common approaches to reduce dimensionality are either extensions of unsupervised techniques such as principal component analysis, or variable selection procedures that rely on modeling the regression function. In this paper, a supervised dimension reduction method tailored to ordered categorical predictors is introduced. It uses a model-based dimension reduction approach, inspired by extending sufficient dimension reductions to the context of latent Gaussian variables. The reduction is chosen without modeling the response as a function of the predictors and does not impose any distributional assumption on the response or on the response given the predictors. A likelihood-based estimator of the reduction is derived and an iterative expectation-maximization type algorithm is proposed to alleviate the computational load and thus make the method more practical. A regularized estimator, which simultaneously achieves variable selection and dimension reduction, is also presented. Performance of the proposed method is evaluated through simulations and a real data example for socioeconomic index construction, comparing favorably to widespread use techniques.

Consumo de alimentos fuera del hogar en Argentina. Relevancia de la composición demográfica y tipología de los hogares Food consumption outside the home in Argentina. Relevance of demographic composition and typology of households

Tomando al género como categoría de análisis, en el presente trabajo se estudia la asociación entre los estilos de vida para el caso de Argentina, cuantificando las diferencias reveladas entre varones y mujeres respecto al consumo de alcohol y tabaco, a los hábitos alimenticios y al nivel de actividad física que realizan. Para ello se realiza un análisis multivariado de correspondencia múltiple y se estima un modelo log-lineal de asociación empírica. Los resultados muestran diferencias de género significativas, apoyando la hipótesis de que los hombres afirman su masculinidad y se legitiman como el sexo fuerte por medio de comportamientos poco saludables.Palabras clave: ALCohoL; TAbACo; CoNSuMo dE FRuTAS y VERduRAS; ACTIVIdAd FíSICA; ModELo LoG-LINEAL AbSTRACT Taking gender as a category of analysis, in this paper the association between lifestyles is analyzed for the Argentinean case, quantifying the revealed differences between men and women. Specifically the alcohol and tobacco consumption, dietary habits and level of physical activity are considered in the lifestyle category. A multiple correspondence analysis is performed and a log-linear model of empirical association is estimated. The results show significant gender differences supporting the hypothesis that men affirm their masculinity and are legitimized as the stronger sex through unhealthy behaviors.

No abstract