Design issues for generalized linear models: a review

DOI10.1214/088342306000000105zbMATH Open1246.62168arXivmath/0701088OpenAlexW3100822788MaRDI QIDQ449737FDOQ449737

Bhramar Mukherjee, Bikas K. Sinha, André I. Khuri, Malay Ghosh

Publication date: 1 September 2012

Published in: Statistical Science (Search for Journal in Brave)

Abstract: Generalized linear models (GLMs) have been used quite effectively in the modeling of a mean response under nonstandard conditions, where discrete as well as continuous data distributions can be accommodated. The choice of design for a GLM is a very important task in the development and building of an adequate model. However, one major problem that handicaps the construction of a GLM design is its dependence on the unknown parameters of the fitted model. Several approaches have been proposed in the past 25 years to solve this problem. These approaches, however, have provided only partial solutions that apply in only some special cases, and the problem, in general, remains largely unresolved. The purpose of this article is to focus attention on the aforementioned dependence problem. We provide a survey of various existing techniques dealing with the dependence problem. This survey includes discussions concerning locally optimal designs, sequential designs, Bayesian designs and the quantile dispersion graph approach for comparing designs for GLMs.

Full work available at URL: https://arxiv.org/abs/math/0701088

Recommendations

• Designs for generalized linear models
• Robust designs in generalized linear models: a quantile dispersion graphs approach
• scientific article; zbMATH DE number 1209393
• A comparison of design alternatives for generalized linear models
• Design of experiments for generalized linear models

zbMATH Keywords

logistic regressionresponse surface methodologysequential designsBayesian designsdependence on unknown parameterslocally optimal designsquantal dispersion graphs

Mathematics Subject Classification ID

Bayesian inference (62F15) Generalized linear models (logistic models) (62J12) Optimal statistical designs (62K05) Sequential statistical design (62L05)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Two‐Stage Design of Quanta1 Response Studies
• Optimum Experimental Designs for Multinomial Logistic Models
• The sequential generation of multiresponse d-optimal designs when the variance-covariance matrix is not known
• On the choice of an experiment for prediction in linear regression
• Title not available (Why is that?)
• Optimum Dose Levels when Males and Females Differ in Response
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Generalized linear models to study spatial distribution of tree species in Argentinean arid Chaco
• The use of prior distributions in the design of experiments for parameter estimation in non-linear situations
• The Optimum Design of a Two-Factor Experiment Using Prior Information
• Title not available (Why is that?)
• Stopping times for stochastic approximation procedures
• A decision theory approach to optimal regression designs
• An extension of the General Equivalence Theorem to nonlinear models
• Spacing of Information in Polynomial Regression
• Quantile dispersion graphs for evaluating and comparing designs for logistic regression models
• Title not available (Why is that?)
• Optimal designs for criteria involving log(potency) in comparative binary bioassays
• Coherent dispersion criteria for optimal experimental design
• Bayesian experimental design: A review
• Title not available (Why is that?)
• Title not available (Why is that?)
• A Simplex Method for Function Minimization
• Optimum Experimental Designs for Properties of a Compartmental Model
• Title not available (Why is that?)
• Title not available (Why is that?)
• Übersichtsarbeiten
• A Stochastic Approximation Method
• Statistical decision theory and Bayesian analysis. 2nd ed
• A Bayesian Sequential Procedure for Quantal Response in the Context of Adaptive Mental Testing
• Title not available (Why is that?)
• Optimal Bayesian design applied to logistic regression experiments
• Expected information as ecpected utility
• Generalized, linear, and mixed models
• Title not available (Why is that?)
• Experimental Design for Binary Data
• Title not available (Why is that?)
• Locally Optimal Designs for Estimating Parameters
• Adaptive design and stochastic approximation
• Design and Analysis of Phase I Clinical Trials
• Efficient Sequential Designs With Binary Data
• Title not available (Why is that?)
• Optimal Experimental Design for Another's Analysis
• Title not available (Why is that?)
• Design of Experiment for Bioassay
• On a Measure of the Information Provided by an Experiment
• Title not available (Why is that?)
• On Asymptotic Normality in Stochastic Approximation
• Stochastic Estimation of the Maximum of a Regression Function
• Experimental design in a class of models
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• A Method for Obtaining and Analyzing Sensitivity Data
• Optimal Bayesian experimental design for linear models
• Response surface methodology. Process and product optimization using designed experiments
• Title not available (Why is that?)
• Optimal multipurpose designs for regression models
• D-optimal designs for generalised linear models with variance proportional to the square of the mean
• On Optimal Screening Ages
• On D-optimal designs for binary data
• Optimal designs for binary data under logistic regression
• Title not available (Why is that?)
• Title not available (Why is that?)
• A Simple Bayesian Modification of D-Optimal Designs to Reduce Dependence on an Assumed Model
• DESIGN OF EXPERIMENTS IN NON-LINEAR SITUATIONS
• Title not available (Why is that?)
• Topics in optimal design
• An Extension of the Robbins-Monro Procedure
• Title not available (Why is that?)
• Robust Bayesian experimental designs in normal linear models
• A note on D-optimal designs for a logistic regression model
• Selection of Dose Levels for Estimating a Percentage Point of a Logistic Quantal Response Curve
• Title not available (Why is that?)
• Title not available (Why is that?)
• Implementable Bayesian Designs for Limiting Dilution Assays
• Three-Stage Designs for Seed Testing Experiments
• Bayesian bioassay design
• Asymptotic properties of least-squares estimates in stochastic regression models
• Construction of optimal designs to increase the power of the multiresponse lack of fit test
• Compromise designs in heteroscedastic linear models
• Transformation of observations in stochastic approximation
• Optimal regression designs for prediction when prior knowledge is available
• MODA 5 - Advances in model-oriented data analysis and experimental design. Proceedings of the 5th international workshop in Marseilles, France, June 22--26, 1998. Dedicated to Andrej Pázman for his 60th birthday
• First-order optimal designs for non-linear models
• A note on optimal Bayesian design for nonlinear problems
• Bayesian D-optimal designs for the exponential growth model
• On optimal estimation methods using stochastic approximation procedures
• Constrained design strategies for improving normal approximations in nonlinear regression problems
• Algorithms for finding locally and Bayesian optimal designs for binary dose--response models with control mortality
• Optimal sequential designs of case-control studies.
• Bayesian optimal one point designs for one parameter nonlinear models
• Bayesian design of experiment for quantal responses: What is promised versus what is delivered
• Robust Bayesian experimental design and estimation for analysis of variance models using a class of normal mixtures
• Bayesian statistics in medicine: Where are we and where should we be going?
• Generalized linear models. With applications in engineering and the sciences
• Optimal Design via Curve Fitting of Monte Carlo Experiments
• Title not available (Why is that?)
• Response Surface Methodology: 1966-1988
• Title not available (Why is that?)
• Optimal designs for generalized linear models
• Model robust response surface designs: Scaling two-level factorials
• Title not available (Why is that?)
• Multiple-objective optimal designs for the logit model
• Title not available (Why is that?)
• On a new stopping rule for stochastic approximation
• Estimation Following a Sequentially Designed Experiment
• On the Evidence Needed to Reach Agreed Action Between Adversaries, with Application to Acceptance Sampling
• Optimal regression design for control in linear regression
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Optimal Designs for Bivariate Logistic Regression
• Applying Generalized Linear Models
• The Effect of Incomplete Knowledge of Parameter Values on Single- and Multiple-Stage Designs for Logistic Regression
• The Equivalence of Constrained and Weighted Designs in Multiple Objective Design Problems

Cited In (43)

• An algorithmic approach to construct D-optimal saturated designs for logistic model
• Comparison of designs for multivariate generalized linear models
• Robust designs for dose-response studies: model and labelling robustness
• Robustness of Bayesian D-optimal design for the logistic mixed model against misspecification of autocorrelation
• Sequential Experimental Designs for Generalized Linear Models
• Pseudo-Bayesian D-optimal designs for longitudinal Poisson mixed models with correlated errors
• Online calibration via variable length computerized adaptive testing
• Analytic solutions for D-optimal factorial designs under generalized linear models
• Assessing some aspects of factor screening with nonnormal responses
• On Computationally Tractable Selection of Experiments in Measurement-Constrained Regression Models
• Bayesian \(D\)-optimal designs for the two parameter logistic mixed effects model
• Excess of locally D-optimal designs for Cobb-Douglas model
• Optimal designs for nonlinear regression models with respect to non-informative priors
• Optimal crossover designs for generalized linear models
• On the de la Garza phenomenon
• Design of experiments for generalized linear models
• A note on the de la Garza phenomenon for locally optimal designs
• Fraction of design space plots for generalized linear models
• Excess of locally D-optimal designs and homothetic transformations
• Maximind-optimal designs for binary longitudinal responses
• D-optimal Factorial Designs under Generalized Linear Models
• D-optimal designs for linear mixed model with random effects of Dirichlet process
• Mixed-integer linear programming for computing optimal experimental designs
• Optimal designs for multivariate logistic mixed models with longitudinal data
• BayesianD-Optimal Designs for Poisson Regression Models
• The augmentation of existing data for improving the path of steepest ascent
• Constructing Efficient Experimental Designs for Generalized Linear Models
• A Maximin Φp-Efficient Design for Multivariate Generalized Linear Models
• Optimal Sampling for Generalized Linear Models Under Measurement Constraints
• Title not available (Why is that?)
• Optimal design of multifactor experiments via grid exploration
• D-optimal designs for multinomial logistic models
• Sequential designs for repeated-measures experiments
• Bayesian sequential experimental design for binary response data with application to electromyographic experiments
• On the construction of optimal designs
• Bayesian D-Optimal Design Issues for Binomial Generalized Linear Model Screening Designs
• Complete classes of designs for nonlinear regression models and principal representations of moment spaces
• Nonparametric Bayesian optimal designs for exponential regression model
• Factorial experimental designs and generalized linear models
• On the Choice of a Prior for Bayesian D-Optimal Designs for the Logistic Regression Model with a Single Predictor
• Identifying locally optimal designs for nonlinear models: A simple extension with profound consequences
• Support points of locally optimal designs for nonlinear models with two parameters
• An empirical comparison of some experimental designs for the valuation of large variable annuity portfolios

Uses Software

• LISP-STAT
• NPSOL
• designv2

This page was built for publication: Design issues for generalized linear models: a review

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q449737)