Flexible regression modeling with adaptive logistic basis functions
نویسنده
چکیده
The author proposes a new method for flexible regression modeling of multi-dimensional data, where the regression function is approximated by a linear combination of logistic basis functions. The method is adaptive, selecting simple or more complex models as appropriate. The number, location, and (to some extent) shape of the basis functions are automatically determined from the data. The method is also affine invariant, so accuracy of the fit is not affected by rotation or scaling of the covariates. Squared error and absolute error criteria are both available for estimation. The latter provides a robust estimator of the conditional median function. Computation is relatively fast, particularly for large data sets, so the method is well suited for data mining applications. Un modèle de régression flexible défini à partir d’une base de fonctions logistiques adaptatives Résumé : L’auteur propose une nouvelle méthode de régression flexible pour la modélisation de données multivariées dans laquelle la fonction de régression est approchée par une combinaison linéaire de fonctions logistiques. Cette méthode adaptative permet de choisir des modèles plus ou moins complexes selon les besoins. Le nombre, la localisation et (jusqu’à un certain point) la forme des fonctions logistiques de base sont automatiquement déterminés à partir des données. La méthode étant équivariante par transformations affines, la précision de l’ajustement n’est pas affectée par une rotation ou un changement d’échelle des variables exogènes. L’estimation peut s’appuyer sur le critère de l’erreur quadratique ou absolue. Dans le second cas, on obtient un estimateur robuste de la médiane conditionnelle. La méthode se prête bien au forage de données, car les calculs nécessaires se font rapidement, même pour de grands ensembles de données.
منابع مشابه
Determining Effective Factors on Forest Fire Using the Compound of Multivariate Adaptive Regression Spline and Genetic Algorithm, a Case Study: Golestan, Iran
Determining Effective Factors on Forest Fire Using the Compound of Multivariate Adaptive Regression Spline and Genetic Algorithm, a Case Study: Golestan, Iran Pahlavani, P., Assistant professor at School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran Raei, A., PhD Candidate of GIS at School of Surveying and Geospatial Engineering, College of Engineeri...
متن کاملDetermining Effective Factors on Forest Fire Using the Compound of Multivariate Adaptive Regression Spline and Genetic Algorithm, a Case Study: Golestan, Iran
Determining Effective Factors on Forest Fire Using the Compound of Multivariate Adaptive Regression Spline and Genetic Algorithm, a Case Study: Golestan, Iran Pahlavani, P., Assistant professor at School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran Raei, A., PhD Candidate of GIS at School of Surveying and Geospatial Engineering, College of Engineeri...
متن کاملRobust adaptive control of voltage saturated flexible joint robots with experimental evaluations
This paper is concerned with the problem of design and implementation a robust adaptive control strategy for flexible joint electrically driven robots (FJEDR), while considering to the constraints on the actuator voltage input. The control design procedure is based on function approximation technique, to avoid saturation besides being robust against both structured and unstructured uncertaintie...
متن کاملA convex version of multivariate adaptive regression splines
Multivariate adpative regression splines (MARS) provide a flexible statistical modeling method that employs forward and backward search algorithms to identify the combination of basis functions that best fits the data and simultaneously conduct variable selection. In optimization, MARS has been used successfully to estimate the unknown functions in stochastic dynamic programming (SDP), stochast...
متن کاملComparison of artificial neural network with logistic regression in prediction of tendency to surgical intervention in nurses
Introduction: Logistic regression is one of the modeling methods for bipartite dependent variables. On the other hand, artificial neural network is a flexible method with the least limitation. The importance of growing unnecessary beauty surgeries and the importance of prediction and classification made us consider the present study, with the aim of comparing logistic regression and artificial ...
متن کامل