The allocation appropriate weights problem to academic performance in high school for the National Engineering University’s postulant is considered. The constant mean linear model with two restriction and ten admission exam data between 1995 to 1999 are used to perform the objective. The statistics analysis suggests that adequate choices are 0.94 to admission exam and 0.06 to high school averages.

Ver PDF

Ver PDF

En el proceso de selección de postulantes a la UNI se consideran dos notas: la del examen de admisión y la nota promedio obtenida en el Colegio. En este trabajo se considera el problema de asignarles ponderaciones apropiadas a esas notas. Para el efecto, usamos un modelo lineal de media constante con dos restricciones y los datos de los diez exámenes de admisión realizados entre 1995-1999. El análisis estadístico sugiere que las ponderaciones apropiadas deben ser 0.94 y 0.06 respectivamente. Esas ponderaciones conducen a que n0 exista significación estadística cuando se realiza comparaciones entre los notas finales de ingreso y las del examen de admisión.

En este trabajo se investiga la posibilidad de asignar pesos óptimos a los puntajes obtenidos por los postulantes a la FAUA-UNI en los exámenes de admisión y vocación profesional. Se usó un modelo lineal con restricciones y los resultados de los procesos de admisión entre 1997 y 1998. El análisis estadístico indica que las ponderaciones deben ser de 0.6 para el examen de admisión y de 0.4 para el de vocación profesional. También se detectó que el procedimiento que se usa actualmente no tiene las condiciones estadísticas para su aplicación y conduce a una mala clasificación de alrededor del 28% de los ingresantes a la FAUA.

En este trabajo se investiga las variables explicativas más relevantes que describen, al comportamiento del puntaje en el examen de admisión a la Universidad Nacional de Ingeniería. Para ello se usaron dos técnicas estadísticas; la "Regresión Stepwise", y la "Regresión Ridge". En el análisis se utilizó los datos correspondientes al examen de admisión para el año de 1994. La recolección de los datos se obtuvo mediante un muestreo estratificado sistemático con asignación proporcional al tamaño poblacional. Dicho análisis revela que la variable más importante recae en el "PROMEDIO GENERAL" (XG), obtenido durante la educación secundaria; entre otras de las variables más relevantes se encuentran: EL "Canal de Ingreso" (X4). el "Tipo de preparación Pre-Universitaria" (X1), y el "Tiempo de preparación Pre-Universitaria" (X7).

The allocation appropriate weights problem to academic performance in high school for the National Engineering University’s postulant is considered. The constant mean linear model with two restriction and ten admission exam data between 1995 to 1999 are used to perform the objective. The statistics analysis suggests that adequate choices are 0.94 to admission exam and 0.06 to high school averages.

In this paper the most important explicative variables in the behaviour of admission exam grades to National Engineering University  is investigated. The tecniques STEPWISE REGRESSION and RIDGE REGRESSION are considerated ans in the analysis is used the results of 1994 admission exam. These data were obtained through sistematic stratificated sampling with proporcional asignation to size population. The results reveals that the most important variable is the general average in high school (XC); others important variables are Admission canal (X1), Pre-University Preparation type (X4), and Pre-University Preparation Time (x7). 

The vertiginous growth in the number of universities in our country has raised certain doubts about the quality of the university teaching process. Government agencies have set the standards for the accreditation of university studies, which cannot be improved if we do not know what students perceive. This study proposes the 6 Qs model to know the dimensions of student satisfaction and finds that there is a relationship of approximately 10% with academic performance, clearly establishing its multidimensional character, and that Research and basic infrastructure are the most dissatisfied indicators and need to be improved as a priority.

An exploratory analysis of the spatial distribution of social indicators in developing countries is essential to understand how these indicators are distributed geographically. Particularly in this study we intend to describe the spatial distribution of the multidimensional poverty index across the districts of Metropolitan Lima by crossing its borders and establishing a certain degree of competitiveness among local governments, so that their authorities take corrective action policies and strengthen the level of key indicators on which the corresponding social index depends. The new ingredient in this type of studies is the consideration of the geographical coordinate of each of the districts in the analysis, so that the methodological design takes into account not only the occurrence of the phenomenon of interest, but also its geographical location and its possible interaction in space...

Hybrid ANN-ARIMA models have been built by remodeling, to make the forecasts of the new cases of infections by Covid-19 in Peru, for this the confirmed cases of Covid-19 were extracted and used between the period 06/03/20 until 02/28/21, from the open data platform of the Ministry of Health. The results found indicate that the 02 best models correspond to the multiplicative hybrid model NNAR (27, 1, 6) * ARIMA (3, 0, 2) (1, 0, 1), and to the additive hybrid model NNAR (27, 1, 6) + ARIMA (1, 0, 1), whose values of the mean absolute percentage error (MAPE) differ by only 0.575%, thus providing almost the same forecasts. Considering the average of the MAPE values for the 03 best models of each modeling category, it has been determined that the NNAR-ARIMA hybrid models are better than the MLP-ARIMA hybrid models, that the NNAR + ARIMA additive hybrid models have a superiority of 1.20 % on th...

The selection of the best students in the admission process is a complex and delicate task. In this paper, a new weighting is proposed to obtain the general admission score, using the multivariate technique of "Factor Analysis". The results found reveal three important components: Scientific Support, with 56%, General Culture, with 29% and Skills and Skills with 15%. This weighting preserves a high concordance with the traditional form, since there is a modification in the orders of merit of only 12% of the cases.

The proportion of courses failed by FIECS students is studied with the purpose of facilitating decision-making in future teaching programs or reorienting educational policy in the institution. The results indicate that 77% of students fail in one or more courses and that, in addition, the variables Laboratory Service, Student age, Study material, and Parental satisfaction affect this proportion.

In this work, the impact of academic risk on academic performance is determined by constructing a scale to calculate the multidimensional index of academic risk, using the statistical technique of factor analysis, which explains 83.274% of the total variation and is made up of six dimensions and 42 items. The most important dimension is the student's personal attitudes (X1), followed by family support (X2) and the teaching domain (X3). The impact of academic risk on performance is inverse and significant, reaching a linear correlation of r = - 0.214, which translates into a decrease of 0.191 points in academic performance for each point in academic risk. It was also determined that the dimension of the teaching domain (X3) has a highly significant and inverse impact on the student's academic performance, quantified as a decrease of 0.255 for each point in the teaching domain.

In this work the possibility to optimal weights allocation of scores in admission and profesional vocation exams for FAUA-UNI is investigated. The linear models with restriction and results of admission process between 1997 and 1998 are used. The statistics analysis reveals that the optimal weights are 0.6 to admission exam and 0.4 to profesional vocation exam. Also the non-existence of statistics conditions for application to current procedure is detected and it conduce to misclassification about 28% of aspirants admitted.