On approximation of linear regression disturbance distribution

Abstract

Inference on the parameters of a linear regression usually requires the assumption that the disturbances are normally distributed. But sometimes this assumption does not correspond to the residual distribution. Thus, there is a need to infer the disturbances of the regression model from its residuals. In this article, the analysis is mainly focused on estimation of moments of the disturbances based on residuals. The main goal of this article is derivation of the unbiased estimators of the third and forth central moments of the linear regression disturbances. They are applied to estimation parameters of the random component distribution based on empirical data. In addition to the normal distribution of the random component, the gamma distribution and the class of Pearson curves are considered. An example of skewness and kurtosis coefficient estimation is shown. An example of estimating the dominant of the gamma distribution is shown. Finally, different types of point and interval forecasts of the examined variable are presented.