Optimal designs for discrete choice models via graph Laplacians

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Röttger, Frank, Kahle, Thomas, Schwabe, Rainer
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916846700068864
author Röttger, Frank
Kahle, Thomas
Schwabe, Rainer
author_facet Röttger, Frank
Kahle, Thomas
Schwabe, Rainer
contents In discrete choice experiments, the information matrix depends on the model parameters. Therefore designing optimally informative experiments for arbitrary initial parameters often yields highly nonlinear optimization problems and makes optimal design infeasible. To overcome such challenges, we connect design theory for discrete choice experiments with Laplacian matrices of undirected graphs, resulting in complexity reduction and feasibility of optimal design. We rewrite the $D$-optimality criterion in terms of Laplacians via Kirchhoff's matrix tree theorem, and show that its dual has a simple description via the Cayley-Menger determinant of the Farris transform of the Laplacian matrix. This results in a drastic reduction of complexity and allows us to implement a gradient descent algorithm to find locally $D$-optimal designs. For the subclass of Bradley-Terry paired comparison models, we find a direct link to maximum likelihood estimation for Laplacian-constrained Gaussian graphical models. Finally, we study the performance of our algorithm and demonstrate its application to real and simulated data.
format Preprint
id arxiv_https___arxiv_org_abs_2208_08926
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Optimal designs for discrete choice models via graph Laplacians
Röttger, Frank
Kahle, Thomas
Schwabe, Rainer
Statistics Theory
Methodology
Primary: 62K05, Secondary: 62H22, 62R01, 90C25
In discrete choice experiments, the information matrix depends on the model parameters. Therefore designing optimally informative experiments for arbitrary initial parameters often yields highly nonlinear optimization problems and makes optimal design infeasible. To overcome such challenges, we connect design theory for discrete choice experiments with Laplacian matrices of undirected graphs, resulting in complexity reduction and feasibility of optimal design. We rewrite the $D$-optimality criterion in terms of Laplacians via Kirchhoff's matrix tree theorem, and show that its dual has a simple description via the Cayley-Menger determinant of the Farris transform of the Laplacian matrix. This results in a drastic reduction of complexity and allows us to implement a gradient descent algorithm to find locally $D$-optimal designs. For the subclass of Bradley-Terry paired comparison models, we find a direct link to maximum likelihood estimation for Laplacian-constrained Gaussian graphical models. Finally, we study the performance of our algorithm and demonstrate its application to real and simulated data.
title Optimal designs for discrete choice models via graph Laplacians
topic Statistics Theory
Methodology
Primary: 62K05, Secondary: 62H22, 62R01, 90C25
url https://arxiv.org/abs/2208.08926