Estimating the Standard Errors of Individual-Specific Parameters in Random Parameters Models
AuthorsWilliam Greene, Mark Harris, Christopher Spencer
PublishedDecember 2013
PublisherCurtin University
Abstract
We consider the estimation of the standard errors of individual‐specific parameters calculated ex post from a non‐linear random parameters model. Our key contribution lies in introducing a simple method of appropriately calculating these standard errors, which explicitly takes into account the sampling variability of the estimation of the model’s parameters. To demonstrate the applicability of the technique, we use it in a model of the voting behaviour of Bank of England MPC members. Our results have clear implications for drawing statistical inference on the estimated random parameters.
The Bankwest Curtin Economics Centre team acknowledges the Wadjuk Nyungar people as the traditional owners of the land on which the Centre is situated.