Ver PDF

Ver PDF

Ver PDF

Ver PDF

The purpose of this research is to study technical aspects involved in the implementation of a Principal Component Analysis (PCA) neural network in terms of predictive capacity, generalization and accuracy in order to establish optimal criteria for the validation and implementation thereof. Our hypothesis is that the statistical structure of the data affects the optimal performance of a PCA neural network in the unsupervised context. It was demonstrated that the Hebbian algorithm at the learning phase ensures enhanced quality of network representation as it makes efficient use of information where generalized variance is large. 

The purpose of this research is to study technical aspects involved in the implementation of a Principal Component Analysis (PCA) neural network in terms of predictive capacity, generalization and accuracy in order to establish optimal criteria for the validation and implementation thereof. Our hypothesis is that the statistical structure of the data affects the optimal performance of a PCA neural network in the unsupervised context. It was demonstrated that the Hebbian algorithm at the learning phase ensures enhanced quality of network representation as it makes efficient use of information where generalized variance is large. 

This paper presents a theoretical exercise to obtain the maximum number of candidates to be submitted to presidential elections to avoid a second round. The method used to achieve this goal is to obtain the probability density function of the number of candidates from the average of the ratios of the political preference share, establishing the likelihood that someone to be elected president in the first round on 1%.

Understanding the structure of the formation of attitudes towards research will allow the design of teaching and application strategies aimed at reversing the tendency to minimize the relevance of research. The empirical evidence confirms that the formation of the scale of attitudes towards research in the students of the professional engineering and science careers of the National University of Engineering has a multidimensional character, which is structured by the following factors that explain 42.9% of total inertia, namely: (1) Importance of research for society and personal life, (2) Institutional environment and (3) Modeling and analysis of statistical data. We worked with a sample of 382 students for which it was necessary to develop suitable data collection instruments for latent structures.

In this work, we try to find factors that determine the export continuity of Peruvian apparel exporters. Logistic regression has been used because it gives several advantages over other methods where the outcome variable is dichotomous or continuous with few values. Logit model exhibits significant interactions which have been deeply analyzed. Likewise, it was possible an exhaustive residual and goodness-of-fit analysis. Finally, we could validate the model for forecast of export continuity in 2006.