Score: 0

Linear Regression Using Hilbert-Space-Valued Covariates with Unknown Reproducing Kernel

Published: April 23, 2025 | arXiv ID: 2504.16780v1

By: Xinyi Li, Margaret Hoch, Michael R. Kosorok

Potential Business Impact:

Finds patterns in complex brain images.

Business Areas:
A/B Testing Data and Analytics

We present a new method of linear regression based on principal components using Hilbert-space-valued covariates with unknown reproducing kernels. We develop a computationally efficient approach to estimation and derive asymptotic theory for the regression parameter estimates under mild assumptions. We demonstrate the approach in simulation studies as well as in data analysis using two-dimensional brain images as predictors.

Country of Origin
🇺🇸 United States

Page Count
40 pages

Category
Mathematics:
Statistics Theory