Model-robust designs for quantile regression

DOI10.1080/01621459.2014.969427MaRDI QIDQ5367360zbMATH OpenOpenAlexFDO

Authors Linglong Kong, Douglas P. Wiens

Publication date 13 October 2017

Published in Journal of the American Statistical Association (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1403.1638

zbMATH Keywords

asymptotic mean squared errorB-splinescompound designexchange algorithmgenetic algorithmgrowth chartsheteroscedasticityminimax biasminimax mean squared errormodel-robust designsnonlinear modelsregression quantilesuniformity

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Robust parameter designs (62K25)

Abstract: We give methods for the construction of designs for linear models, when the purpose of the investigation is the estimation of the conditional quantile function and the estimation method is quantile regression. The designs are robust against misspecified response functions, and against unanticipated heteroscedasticity. The methods are illustrated by example, and in a case study in which they are applied to growth charts.

Recommendations

• Some model robust designs in regression
• Optimal designs for quantile regression models
• A comparative study of robust designs for M-estimated regression models
• Some robust design strategies for percentile estimation in binary response models
• Techniques for the construction of robust regression designs

Cited in

(8)

• A new robust inference for predictive quantile regression
• Bayesian optimum accelerated life test plans based on quantile regression
• Risk-adapted optimal experimental design
• Assessment and validation in quantile composite-based path modeling
• Some robust design strategies for percentile estimation in binary response models
• Construction of optimal designs for quantile regression model via particle swarm optimization
• Efficient and robust optimal design for quantile regression based on linear programming
• Robust design for mixture experiments: an efficient class of exchangeable designs for Scheffé polynomials

This page was built for publication: Model-robust designs for quantile regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5367360)