New Algorithms for Nonlinear Least Squares and Bayesian Parameter Estimation.
Abstract
Some new algorithms are presented for fitting mathematical models to multiple-response experiments. These algorithms give estimates of the parameters in a user-defined predictor model, and also estimate the parameters of a Gaussian model of the observational error distribution. The development is based on Bayes' theorem, and provides a natural extension of known least-squares estimation methods. Allowance is made for missing values of responses, which occur frequently in practical work.
Document Details
- Document Type
- Technical Report
- Publication Date
- Feb 01, 1980
- Accession Number
- ADA083819
Entities
People
- Jan P. Sorensen
- Warren E. Stewart
Organizations
- University of Wisconsin–Madison