Estadística aplicada a las Ciencias Sociales. Las variables

Las variables son la base, los ladrillos, sobre la que se construye el edificio de la estadística.En este e-prints se explica qué son las variables y cómo se diferencian y clasifican según diferentes criterios.

One-sided asymptotic inferences for a proportion.

Two-sided asymptotic confidence intervals for an unknown proportion p have been the subject of a great deal of literature. Surprisingly, there are very few papers devoted, like this article, to the case of one tail, despite its great importance in practice and the fact that its behavior is usually different from that of the case with two tails. This paper evaluates 47 methods and concludes that (1) the optimal method is the classic Wilson method with a correction for continuity and (2) a simpler option, almost as good as the first, is the new adjusted Wald method (Wald's classic method applied to the data increased in the values proposed by Borkowf: adding a single imaginary failure or success).

Analysis of residuals in contingency tables: another nail in the coffin of conditional approaches to significance testing.

Omnibus tests of significance in contingency tables use statistics of the chi-square type. When the null is rejected, residual analyses are conducted to identify cells in which observed frequencies differ significantly from expected frequencies. Residual analyses are thus conditioned on a significant omnibus test. Conditional approaches have been shown to substantially alter type I error rates in cases involving t tests conditional on the results of a test of equality of variances, or tests of regression coefficients conditional on the results of tests of heteroscedasticity. We show that residual analyses conditional on a significant omnibus test are also affected by this problem, yielding type I error rates that can be up to 6 times larger than nominal rates, depending on the size of the table and the form of the marginal distributions. We explored several unconditional approaches in search for a method that maintains the nominal type I error rate and found out that a bootstrap correction for multiple testing achieved this goal. The validity of this approach is documented for two-way contingency tables in the contexts of tests of independence, tests of homogeneity, and fitting psychometric functions. Computer code in MATLAB and R to conduct these analyses is provided as Supplementary Material.

Design of maintenance structures for rural electrification with solar home systems. The case of the Moroccan program.

n decentralised rural electrification through solar home systems, private companies and promoting institutions are faced with the problem of deploying maintenance structures to operate and guarantee the service of the solar systems for long periods (ten years or more). The problems linked to decentralisation, such as the dispersion of dwellings, difficult access and maintenance needs, makes it an arduous task. This paper proposes an innovative design tool created ad hoc for photovoltaic rural electrification based on a real photovoltaic rural electrification program in Morocco as a special case study. The tool is developed from a mathematical model comprising a set of decision variables (location, transport, etc.) that must meet certain constraints and whose optimisation criterion is the minimum cost of the operation and maintenance activity assuming an established quality of service. The main output of the model is the overall cost of the maintenance structure. The best location for the local maintenance headquarters and warehouses in a given region is established, as are the number of maintenance technicians and vehicles required.

Metodología de minería de datos aplicada a la competencia hotelera

El presente estudio comprende una síntesis general de los conocimientos adquiridos en el desarrollo del Máster en Minería de Datos e Inteligencia de Negocios. Se ha intentado pasar por la mayoría de las áreas que en el mismo se tratan, prestando especial atención a la parte de análisis de datos propiamente dicha. La temática se ha centrado en el sector hotelero de la ciudad de Madrid. Se pretende hacer un ejercicio en profundidad de análisis de datos, seguido de un análisis de predicción del precio de los hoteles situados en esta ciudad, tomando como referencias distintas características de estos establecimientos, además de momentos temporales y otros matices. Otro punto a tratar en este estudio está basado en un análisis de la competencia hotelera, que tomará como base los resultados obtenidos en los primeros pasos de este proyecto. Así, se llega a la selección de un modelo óptimo de predicción, obtenido tras un proceso de ensayo-error de distintas técnicas predictivas, seguido de un proceso de elección. Así mismo, se consigue entender cómo se agrupan los distintos hoteles y cómo se sitúan en su mercado, atendiendo al comportamiento de los centros que forman su competencia.