Bootstrapping a Regression Equation: Some Empirical Results

Abstract

The bootstrap, like the jackknife, is a technique for estimating standard errors. The idea is to use Monte Carlo simulation based on a nonparametric estimate of the underlying error distribution. The main object of this article is to present the bootstrap in the context of an econometric equation describing the demand for energy by industry. As it turns out, the conventional asymptotic formulas for estimating standard errors are too optimistic by factors of nearly three, when applied to a particular finite-sample problem. In a simpler context, this finding can be given a mathematical proof.

Key Words:

• Regression
• Generalized least squares
• Seemingly unrelated equations
• Econometric models
• Forecasting
• Standard errors