Robust Experimental Designs for Generalized Linear Models
Optimal experimental designs for generalized linear models (GLM) depend on the unknown coefficients, and two experiments having the same model but different coefficient values will typically have different optimal designs. Therefore, unlike experimental design for linear models, the prior knowledge and estimates of the outcome of an experiment must be taken into account.
The function DOPT.m is an implementation of a fast and simple method for finding Local D-optimal designs for high-order multivariate models. With this capability in hand the rest of the files demonstrate a simple heuristic capable of finding designs that are robust to most parameters an experimenter might consider, including uncertainty in the coefficient values, in the linear predictor equation and in the link function.
The theory behind the algorithms is detailed at:
Technical Report RP-SOR-0601, Robust Experimental Design for Multivariate Generalized Linear Models, Hovav A. Dror and David M. Steinberg, January 2006.
The report is available at: http://www.math.tau.ac.il/~dms/GLM_Design
Cite As
Hovav Dror (2024). Robust Experimental Designs for Generalized Linear Models (https://www.mathworks.com/matlabcentral/fileexchange/9927-robust-experimental-designs-for-generalized-linear-models), MATLAB Central File Exchange. Retrieved .
MATLAB Release Compatibility
Platform Compatibility
Windows macOS LinuxCategories
- AI, Data Science, and Statistics > Statistics and Machine Learning Toolbox > Industrial Statistics >
Tags
Acknowledgements
Inspired: Sequential Experimental Designs for GLM
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!Discover Live Editor
Create scripts with code, output, and formatted text in a single executable document.