Testing significance of variables in regression analysis when there is non-normality or heteroskedasticity. : The wild bootstrap and the generalised lambda distribution

Pavlidis, E. and Paya, I. and Peel, D. A. (2008) Testing significance of variables in regression analysis when there is non-normality or heteroskedasticity. : The wild bootstrap and the generalised lambda distribution. In: Advances In Doctoral Research In Management (Volume 2) :. World Scientific Publishing Co., pp. 151-174. ISBN 9789812778666

Abstract

Statistical inference on the parameters of regression models requires special precautions when the error term is heteroskedastic and/or non-normal. In this case, although conventional test statistics do not follow t and F distributions, simulation methods can be used to draw inferences. We discuss two methods: the wild bootstrap and the generalised lambda distribution. By employing both artificial and real-world data from the National Footbal League, we show that these methods may prove particularly useful in hypothesis testing.