Search results for "model selection"

Compressed Particle Methods for Expensive Models With Application in Astronomy and Remote Sensing

2021

In many inference problems, the evaluation of complex and costly models is often required. In this context, Bayesian methods have become very popular in several fields over the last years, in order to obtain parameter inversion, model selection or uncertainty quantification. Bayesian inference requires the approximation of complicated integrals involving (often costly) posterior distributions. Generally, this approximation is obtained by means of Monte Carlo (MC) methods. In order to reduce the computational cost of the corresponding technique, surrogate models (also called emulators) are often employed. Another alternative approach is the so-called Approximate Bayesian Computation (ABC) sc…

Semiparametric stochastic frontier models: A generalized additive model approach

2017

Abstract The choice of the functional form of the frontier into a stochastic frontier model is typically neglected in applications and canonical functions are usually considered. This paper introduces a semiparametric approach for stochastic frontier estimation that extends previous works based on pseudo-likelihood estimators allowing flexibility in model selection and capability of imposing monotonicity and concavity constraints. For these purposes the present work introduces a generalized additive framework that moreover permits to model the influence of contextual/environmental factors to the hypothesized production process by the relative extension given by generalized additive models f…

A computational method to estimate sparse multiple Gaussian graphical models

2012

In recent years several researchers have proposed the use of the Gaussian graphical model defined on a high dimensional setting to explore the dependence relationships between random variables. Standard methods, usually proposed in literature, are based on the use of a specific penalty function, such as the L1-penalty function. In this paper our aim is to estimate and compare two or more Gaussian graphical models defined in a high dimensional setting. In order to accomplish our aim, we propose a new computational method, based on glasso method, which lets us to extend the notion of p-value.

2014

Introduction: Many studies examine gene expression data that has been obtained under the influence of multiple factors, such as genetic background, environmental conditions, or exposure to diseases. The interplay of multiple factors may lead to effect modification and confounding. Higher order linear regression models can account for these effects. We present a new methodology for linear model selection and apply it to microarray data of bone marrow-derived macrophages. This experiment investigates the influence of three variable factors: the genetic background of the mice from which the macrophages were obtained, Yersinia enterocolitica infection (two strains, and a mock control),and treat…

Spatial autocorrelation and the selection of simultaneous autoregressive models

2007

Aim Spatial autocorrelation is a frequent phenomenon in ecological data and can affect estimates of model coefficients and inference from statistical models. Here, we test the performance of three different simultaneous autoregressive (SAR) model types (spatial error = SAR err , lagged = SAR lag and mixed = SAR mix ) and common ordinary least squares (OLS) regression when accounting for spatial autocorrelation in species distribution data using four artificial data sets with known (but different) spatial autocorrelation structures. Methods We evaluate the performance of SAR models by examining spatial patterns in model residuals (with correlograms and residual maps), by comparing model para…

Variable selection in mixed models: a graphical approach

2014

Model selection can be defined as the task of estimating the performance of dif- ferent models in order to choose the (approximate) best one. The purpose of this article is to introduce an extension of the graphical representation of deviance proposed in the framework of classical and generalized linear models to the wider class of mixed models. The proposed plot is useful in determining which are the important explanatory variables conditioning on the random effects part. The applicability and the easy interpretation of the graph are illus- trated with a real data examples.

Learning the relevant image features with multiple kernels

2009

This paper proposes to learn the relevant features of remote sensing images for automatic spatio-spectral classification with the automatic optimization of multiple kernels. The method consists of building dedicated kernels for different sets of bands, contextual or textural features. The optimal linear combination of kernels is optimized through gradient descent on the support vector machine (SVM) objective function. Since a na¨ive implementation is computationally demanding, we propose an efficient model selection procedure based on kernel alignment. The result is a weight — learned from the data — for each kernel where both relevant and meaningless image features emerge after training. E…

A new tuning parameter selector in lasso regression

2019

Penalized regression models are popularly used in high-dimensional data analysis to carry out variable selction and model fitting simultaneously. Whereas success has been widely reported in literature, their performance largely depend on the tuning parameter that balances the trade-off between model fitting and sparsity. In this work we introduce a new tuning parameter selction criterion based on the maximization of the signal-to-noise ratio. To prove its effectiveness we applied it to a real data on prostate cancer disease.

Five Ways in Which Computational Modeling Can Help Advance Cognitive Science

2019

Abstract There is a rich tradition of building computational models in cognitive science, but modeling, theoretical, and experimental research are not as tightly integrated as they could be. In this paper, we show that computational techniques—even simple ones that are straightforward to use—can greatly facilitate designing, implementing, and analyzing experiments, and generally help lift research to a new level. We focus on the domain of artificial grammar learning, and we give five concrete examples in this domain for (a) formalizing and clarifying theories, (b) generating stimuli, (c) visualization, (d) model selection, and (e) exploring the hypothesis space.

Empirical study of the dependence of the results of multivariable flexible survival analyses on model selection strategy

2008

Flexible survival models, which avoid assumptions about hazards proportionality (PH) or linearity of continuous covariates effects, bring the issues of model selection to a new level of complexity. Each ‘candidate covariate’ requires inter-dependent decisions regarding (i) its inclusion in the model, and representation of its effects on the log hazard as (ii) either constant over time or time-dependent (TD) and, for continuous covariates, (iii) either loglinear or non-loglinear (NL). Moreover, ‘optimal’ decisions for one covariate depend on the decisions regarding others. Thus, some efficient model-building strategy is necessary. We carried out an empirical study of the impact of the model …