Search results for "Anàlisi de regressió"
showing 3 items of 3 documents
Aplicación de la topología molecular para la predicción de biodegradación anaerobia de clorofenoles
2013
Se ha aplicado la topología molecular y el análisis de regresión multilineal en la búsqueda de un modelo de relación cuantitativa estructura-actividad (QSAR) capaz de predecir la capacidad de biodegradación anaerobia de un grupo de clorofenoles. Tomando el valor de la constante de velocidad de desaparición del derivado clorofenolico, log k, como variable dependiente y los descriptores topológicos como variables independientes, se obtuvo una ecuación con tres variables y coeficientes de correlación y de predicción , R2=0.9291 y Q2=0.870. El modelo fue validado a través de una validación interna y un test de aleatoriedad. Los resultados obtenidos muestran una alta capacidad de predicción para…
External imbalances from a GVAR perspective
2021
In this paper we study the drivers governing external disequilibria through a Global VAR (GVAR) analysis applied to a group of 24 countries during the period 1972-2017. The GVAR methodology is particularly well suited for our research question. First, it permits to measure the effects of both, domestic and foreign country-specific shocks. Second, it allows to analyze not only the long-run relationships, but also the dynamics through generalized impulse-response functions. Third, it enables to test many hypotheses from a macroeconomic perspective and the existence of spillovers. Our results show evidence of international financial integration in terms of the fulfillment of the real interest …
Análisis de métodos de validación cruzada para la obtención robusta de parámetros biofísicos
2015
[EN] Non-parametric regression methods are powerful statistical methods to retrieve biophysical parameters from remote sensing measurements. However, their performance can be affected by what has been presented during the training phase. To ensure robust retrievals, various cross-validation sub-sampling methods are often used, which allow to evaluate the model with subsets of the field dataset. Here, two types of cross-validation techniques were analyzed in the development of non-parametric regression models: hold-out and k-fold. Selected non-parametric linear regression methods were least squares Linear Regression (LR) and Partial Least Squares Regression (PLSR), and nonlinear methods were…