Search results for "selection"

showing 10 items of 1940 documents

Bayesian regularization for flexible baseline hazard functions in Cox survival models.

2019

Fully Bayesian methods for Cox models specify a model for the baseline hazard function. Parametric approaches generally provide monotone estimations. Semi-parametric choices allow for more flexible patterns but they can suffer from overfitting and instability. Regularization methods through prior distributions with correlated structures usually give reasonable answers to these types of situations. We discuss Bayesian regularization for Cox survival models defined via flexible baseline hazards specified by a mixture of piecewise constant functions and by a cubic B-spline function. For those "semi-parametric" proposals, different prior scenarios ranging from prior independence to particular c…

Statistics and ProbabilityComputer scienceProportional hazards modelModel selectionBayesian probabilityPosterior probabilityMarkov chain Monte CarloBayes TheoremGeneral MedicineOverfittingSurvival AnalysisMarkov Chainssymbols.namesakeStatisticsCovariatesymbolsPiecewiseStatistics Probability and UncertaintyMonte Carlo MethodProportional Hazards ModelsBiometrical journal. Biometrische ZeitschriftREFERENCES
researchProduct

Graphical representation of some duality relations in stochastic population models

2007

We derive a unified stochastic picture for the duality of a resampling-selection model with a branching-coalescing particle process (cf. http://www.ams.org/mathscinet-getitem?mr=MR2123250) and for the self-duality of Feller's branching diffusion with logistic growth (cf. math/0509612). The two dual processes are approximated by particle processes which are forward and backward processes in a graphical representation. We identify duality relations between the basic building blocks of the particle processes which lead to the two dualities mentioned above.

Statistics and ProbabilityDiscrete mathematicsDualityProcess (engineering)Feller's branching diffusionProbability (math.PR)Duality (optimization)Dual (category theory)Algebragraphical representationbranching-coalescing particle processstochastic population dynamicsPopulation model60K35resampling-selection modelMathematikFOS: MathematicsStatistics Probability and UncertaintyLogistic functionDiffusion (business)Representation (mathematics)Mathematics - ProbabilityMathematics
researchProduct

Comments on “Unobservable Selection and Coefficient Stability

2019

Abstract–: We establish a link between the approaches proposed by Oster (2019) and Pei, Pischke, and Schwandt (2019) which contribute to the development of inferential procedures for causal effects in the challenging and empirically relevant situation where the unknown data-generation process is not included in the set of models considered by the investigator. We use the general misspecification framework recently proposed by De Luca, Magnus, and Peracchi (2018) to analyze and understand the implications of the restrictions imposed by the two approaches.

Statistics and ProbabilityEconomics and EconometricEconomics and EconometricsTestingSettore SECS-P/05 - EconometriaOLSInconsistency01 natural sciencesUnobservable010104 statistics & probabilityBiaStability theory0502 economics and businessInconsistent Statistics and ProbabilityEconometrics0101 mathematicsSelection (genetic algorithm)050205 econometrics 05 social sciencesCausal effectConfoundingMean squared error (MSE)MisspecificationStatistics Probability and UncertaintyPsychologySocial Sciences (miscellaneous)Journal of Business and Economic Statistics
researchProduct

Is the productivity premium of internationalized firms technology-driven?

2020

AbstractWe ask whether the productivity advantage of internationalized firms documented by the international trade literature can be interpreted most accurately in terms of proximity to the “technological frontier”. We answer in the affirmative using a methodology (based on mixture models) of unbundling technology and total factor productivity (TFP) by estimating “technology-specific” production function parameters. Exploiting detailed data provided by the EFIGE database (a sample of firms distributed across Austria, France, Germany, Hungary, Italy, Spain, and the UK), we find technology gaps (with respect to the frontier) more than three times larger than the TFP gaps on average. We also f…

Statistics and ProbabilityEconomics and EconometricsHeterogenous firm Productivity premium Selection effect Technology TFP Trade modelTechnologyCompetitor analysisForeign direct investmentHeterogenous firm · Productivity premium · Selection effect · Technology · TFP · Trade modelSelection effectCompetition (economics)TFPMathematics (miscellaneous)Heterogenous firmProductivity premiumProduction (economics)media_common.cataloged_instanceTrade modelBusinessUnbundlingEuropean unionSettore SECS-P/01 - Economia PoliticaProductivityTotal factor productivitySocial Sciences (miscellaneous)Industrial organizationmedia_common
researchProduct

A heuristic method for estimating attribute importance by measuring choice time in a ranking task

2012

The evaluation of a product or service in terms of its attributes has been broadly studied in marketing, management and decision sciences. However, methods for finding important attributes have theoretical and practical limitations. The former are related to the selection of the most appropriate model; the latter are due to large number of variables that affect the specific experimental context. This study aims to present a new methodology that captures attribute preferences from a respondent and in particular, by using the choice time in a ranking task, it allows to indirectly obtain the importance weights for several tested attributes through a simple, fast and inexpensive procedure. More…

Statistics and ProbabilityEconomics and EconometricsService (systems architecture)HeuristicComputer scienceSettore SECS-S/02 - Statistica Per La Ricerca Sperimentale E TecnologicaVariable and attributeContext (language use)computer.software_genreTask (project management)RankingRespondentData miningStatistics Probability and UncertaintySettore SECS-S/01 - StatisticacomputerFinanceSelection (genetic algorithm)CHOICE TIME response time response latency attribute rating choice models
researchProduct

Tailoring sparse multivariable regression techniques for prognostic single-nucleotide polymorphism signatures.

2011

When seeking prognostic information for patients, modern technologies provide a huge amount of genomic measurements as a starting point. For single-nucleotide polymorphisms (SNPs), there may be more than one million covariates that need to be simultaneously considered with respect to a clinical endpoint. Although the underlying biological problem cannot be solved on the basis of clinical cohorts of only modest size, some important SNPs might still be identified. Sparse multivariable regression techniques have recently become available for automatically identifying prognostic molecular signatures that comprise relatively few covariates and provide reasonable prediction performance. For illus…

Statistics and ProbabilityEpidemiologyComputer scienceFeature selectionBiostatisticscomputer.software_genrePolymorphism Single NucleotideLasso (statistics)Gene FrequencyResamplingCovariateHumansLikelihood FunctionsModels StatisticalMultivariable calculusRegression analysisGenomicsPrognosisRegressionMinor allele frequencyLeukemia Myeloid AcuteMultivariate AnalysisRegression AnalysisData miningcomputerAlgorithmsStatistics in medicine
researchProduct

Methods and Tools for Bayesian Variable Selection and Model Averaging in Normal Linear Regression

2018

In this paper, we briefly review the main methodological aspects concerned with the application of the Bayesian approach to model choice and model averaging in the context of variable selection in regression models. This includes prior elicitation, summaries of the posterior distribution and computational strategies. We then examine and compare various publicly available R-packages, summarizing and explaining the differences between packages and giving recommendations for applied users. We find that all packages reviewed (can) lead to very similar results, but there are potentially important differences in flexibility and efficiency of the packages.

Statistics and ProbabilityGeneral linear modelProper linear modelbusiness.industryComputer science05 social sciencesPosterior probabilityRegression analysisFeature selectionMachine learningcomputer.software_genre01 natural sciences010104 statistics & probabilityBayesian multivariate linear regression0502 economics and businessLinear regressionEconometricsArtificial intelligence050207 economics0101 mathematicsStatistics Probability and UncertaintyBayesian linear regressionbusinesscomputerInternational Statistical Review
researchProduct

Extending conventional priors for testing general hypotheses in linear models

2007

We consider that observations come from a general normal linear model and that it is desirable to test a simplifying null hypothesis about the parameters. We approach this problem from an objective Bayesian, model-selection perspective. Crucial ingredients for this approach are 'proper objective priors' to be used for deriving the Bayes factors. Jeffreys-Zellner-Siow priors have good properties for testing null hypotheses defined by specific values of the parameters in full-rank linear models. We extend these priors to deal with general hypotheses in general linear models, not necessarily of full rank. The resulting priors, which we call 'conventional priors', are expressed as a generalizat…

Statistics and ProbabilityGeneralizationApplied MathematicsGeneral MathematicsModel selectionBayesian probabilityLinear modelBayes factorAgricultural and Biological Sciences (miscellaneous)Prior probabilityEconometricsStatistics Probability and UncertaintyGeneral Agricultural and Biological SciencesNull hypothesisStatistical hypothesis testingMathematicsBiometrika
researchProduct

dglars: An R Package to Estimate Sparse Generalized Linear Models

2014

dglars is a publicly available R package that implements the method proposed in Augugliaro, Mineo, and Wit (2013), developed to study the sparse structure of a generalized linear model. This method, called dgLARS, is based on a differential geometrical extension of the least angle regression method proposed in Efron, Hastie, Johnstone, and Tibshirani (2004). The core of the dglars package consists of two algorithms implemented in Fortran 90 to efficiently compute the solution curve: a predictor-corrector algorithm, proposed in Augugliaro et al. (2013), and a cyclic coordinate descent algorithm, proposed in Augugliaro, Mineo, and Wit (2012). The latter algorithm, as shown here, is significan…

Statistics and ProbabilityGeneralized linear modelEXPRESSIONMathematical optimizationTISSUESFortrancyclic coordinate descent algorithmdgLARSFeature selectionDANTZIG SELECTORpredictor-corrector algorithmLIKELIHOODLEAST ANGLE REGRESSIONsparse modelsDifferential (infinitesimal)differential geometrylcsh:Statisticslcsh:HA1-4737computer.programming_languageMathematicsLeast-angle regressionExtension (predicate logic)Expression (computer science)generalized linear modelsBREAST-CANCER RISKVARIABLE SELECTIONDifferential geometrydifferential geometry generalized linear models dgLARS predictor-corrector algorithm cyclic coordinate descent algorithm sparse models variable selection.MARKERSHRINKAGEStatistics Probability and UncertaintyHAPLOTYPESSettore SECS-S/01 - StatisticacomputerAlgorithmSoftware
researchProduct

Extended differential geometric LARS for high-dimensional GLMs with general dispersion parameter

2018

A large class of modeling and prediction problems involves outcomes that belong to an exponential family distribution. Generalized linear models (GLMs) are a standard way of dealing with such situations. Even in high-dimensional feature spaces GLMs can be extended to deal with such situations. Penalized inference approaches, such as the $$\ell _1$$ or SCAD, or extensions of least angle regression, such as dgLARS, have been proposed to deal with GLMs with high-dimensional feature spaces. Although the theory underlying these methods is in principle generic, the implementation has remained restricted to dispersion-free models, such as the Poisson and logistic regression models. The aim of this…

Statistics and ProbabilityGeneralized linear modelMathematical optimizationGeneralized linear modelsPredictor-€“corrector algorithmGeneralized linear model02 engineering and technologyPoisson distributionDANTZIG SELECTOR01 natural sciencesCross-validationHigh-dimensional inferenceTheoretical Computer Science010104 statistics & probabilitysymbols.namesakeExponential familyLEAST ANGLE REGRESSION0202 electrical engineering electronic engineering information engineeringApplied mathematicsStatistics::Methodology0101 mathematicsCROSS-VALIDATIONMathematicsLeast-angle regressionLinear model020206 networking & telecommunicationsProbability and statisticsVARIABLE SELECTIONEfficient estimatorPredictor-corrector algorithmComputational Theory and MathematicsDispersion paremeterLINEAR-MODELSsymbolsSHRINKAGEStatistics Probability and UncertaintySettore SECS-S/01 - StatisticaStatistics and Computing
researchProduct