Title: R package OptimalDesign
Authors: Lenka Filova - Comenius University in Bratislava (Slovakia) [presenting]
Radoslav Harman - Comenius University in Bratislava (Slovakia)
Abstract: The purpose is to present computational and graphical capabilities of our R package OptimalDesign which provides a toolbox for the computation of D-, A-, I-, and c-efficient exact and approximate designs of experiments on finite domains, for regression models with real-valued, uncorrelated observations. The package fills a gap in presently available functions for experimental design optimization by implementing several competing algorithms based on significantly different principles, including mathematical programming methods and search heuristics. This allows the user to cross-check the quality of the results, and, in many cases, provides efficient design alternatives to choose for the experiment. An important feature of the package is that several implemented procedures allow for multiple linear constraints on the vector of design weights.