Model selection via Bayesian information capacity designs for generalised linear models
From MaRDI portal
Abstract: The first investigation is made of designs for screening experiments where the response variable is approximated by a generalised linear model. A Bayesian information capacity criterion is defined for the selection of designs that are robust to the form of the linear predictor. For binomial data and logistic regression, the effectiveness of these designs for screening is assessed through simulation studies using all-subsets regression and model selection via maximum penalised likelihood and a generalised information criterion. For Poisson data and log-linear regression, similar assessments are made using maximum likelihood and the Akaike information criterion for minimally-supported designs that are constructed analytically. The results show that effective screening, that is, high power with moderate type I error rate and false discovery rate, can be achieved through suitable choices for the number of design support points and experiment size. Logistic regression is shown to present a more challenging problem than log-linear regression. Some areas for future work are also indicated.
Recommendations
- Bayesian \(D\)-optimal design issues for binomial generalized linear model screening designs
- Sequential Experimental Designs for Generalized Linear Models
- A robust design of a screen for a binary response
- Screening designs for model discrimination
- Optimal Bayesian design applied to logistic regression experiments
Cites work
- L 1-Regularization Path Algorithm for Generalized Linear Models
- A new look at the statistical model identification
- An Analysis for Unreplicated Fractional Factorials
- An Optimal Experimental Design Criterion for Discriminating Between Non-Normal Models
- Bayesian variable selection and computation for generalized linear models with conjugate priors
- Bias reduction in exponential family nonlinear models
- Bias reduction of maximum likelihood estimates
- Construction of supersaturated designs through partially aliased interactions
- Continuous optimal designs for generalized linear models under model uncertainty
- D-optimal designs for Poisson regression models
- Design selection criteria for discrimination/estimation for nested models and a binomial re\-sponse
- Designs for generalized linear models
- DT-optimum designs for model discrimination and parameter estimation
- Generalised information criteria in model selection
- scientific article; zbMATH DE number 3746271 (Why is no real title available?)
- scientific article; zbMATH DE number 47310 (Why is no real title available?)
- Model Selection and Multimodel Inference
- Monte Carlo and quasi-Monte Carlo sampling
- Optimal Bayesian design applied to logistic regression experiments
- Optimum experimental designs, with SAS
- Regularization parameter selections via generalized information criterion
- Robust designs for binary data: applications of simulated annealing
- The Application of the Annealing Algorithm to the Construction of Exact Optimal Designs for Linear-Regression Models
- The design of experiments for discriminating between two rival models
- Understanding predictive information criteria for Bayesian models
Cited in
(5)- Special issue on design of experiments
- Optimal Bayesian design for discriminating between models with intractable likelihoods in epidemiology
- Model choice in generalised linear models: a Bayesian approach via Kullback-Leibler projections
- Assessing some aspects of factor screening with nonnormal responses
- d-QPSO: A Quantum-Behaved Particle Swarm Technique for FindingD-Optimal Designs With Discrete and Continuous Factors and a Binary Response
This page was built for publication: Model selection via Bayesian information capacity designs for generalised linear models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1658158)
