- Bayesian Anal.
- Volume 6, Number 4 (2011), 727-754.
Estimating a bivariate linear relationship
Solutions of the bivariate, linear errors-in-variables estimation problem with unspecified errors are expected to be invariant under interchange and scaling of the coordinates. The appealing model of normally distributed true values and errors is unidentified without additional information. I propose a prior density that incorporates the fact that the slope and variance parameters together determine the covariance matrix of the unobserved true values but is otherwise diffuse. The marginal posterior density of the slope is invariant to interchange and scaling of the coordinates and depends on the data only through the sample correlation coefficient and ratio of standard deviations. It covers the interval between the two ordinary least squares estimates but diminishes rapidly outside of it. I introduce the R package leivfor computing the posterior density, and I apply it to examples in astronomy and method comparison.
Bayesian Anal., Volume 6, Number 4 (2011), 727-754.
First available in Project Euclid: 13 June 2012
Permanent link to this document
Digital Object Identifier
Mathematical Reviews number (MathSciNet)
Zentralblatt MATH identifier
Leonard, David. Estimating a bivariate linear relationship. Bayesian Anal. 6 (2011), no. 4, 727--754. doi:10.1214/11-BA627. https://projecteuclid.org/euclid.ba/1339616542