Elena Abascal Fernández

A methodology for measuring latent variables based on multiple factor analysis

Abstract The quantification of latent variables, such as social welfare, economic development or infrastructure usually involves a multivariate method. A methodology for comparing the various synthetic category indicators that emerge when different measurement methods are applied to a given latent variable is considered. When the different methods of synthesis share a common pattern, a “harmonised” indicator which is the global synthesis of them all is proposed. The methodology is based on the exploratory method known as multiple factor analysis. An empirical study of infrastructure assets in the Spanish Autonomous Communities is used for illustration.

Face to face and telephone surveys in terms of sampling representativeness: a multidimensional analysis

This paper analyzes sample structure in a survey-based research project using both face-to-face and telephone survey techniques, at a time when the telephone survey has completely ousted the face-to-face survey; particularly in electoral studies. Multiple Correspondence Analysis is applied to the data from a political poll conducted prior to regional elections held in Spain’s Autonomous Community of Galicia in which half of the questionnaires were administered by telephone and the other half via face-to-face interview. Unlike other studies—that use a partial approach based on bivariate analysis—this one examines all the sociodemographic variables simultaneously.

Relación del gasto en ocio y vacaciones con variables del ciclo de vida del hogar, demográficas, geográficas y económicas

El gasto en ocio y vacaciones de los hogares puede depender de variables demograficas, geograficas y economicas asociadas al hogar o al sustentador principal. Tambien afecta el tipo de hogar, cuya clasificacion puede realizarse segun los modelos considerados en la teoria del ciclo de vida del hogar (CVH). En este trabajo, se utiliza el programa estadistico SPAD para aplicar la metodologia de la caracterizacion de la variable y analizar el poder explicativo de un total de doce variables sobre el gasto en “vacaciones todo incluido”, “servicios culturales” y otras cinco partidas destacadas del grupo “Ocio, espectaculos y cultura” de la Encuesta de Presupuestos Familiares (EPF) de Espana. El estudio confirma el interes de considerar variables como el numero de dependientes para segmentar consumidores de ocio y vacaciones, pero no de variables mas complejas basadas en modelos del CVH.