Introduction to Fat Tails

Abstract

This chapter initiates discussion on the kurtosis and skewness measures and its implications. The unit covers in detail what are fat tails and tail risk in financial data. Why are fat tails important and its implication for investment decisions? How to handle such fat tails using quantile regressions? The OLS loses its effectiveness particularly in the extreme of the distributions or tailed analysis, whereas quantile regression estimates the conditional median or the conditional quartile of the dependable variables for the given independent variables. OLS is mainly based on the mean values of the covariates unlike quantile estimates. Theoretical discussion on quantile regression along with stepwise execution with appropriate examples is discussed using EViews. The OLS and quantile regression estimates are compared for detailed analysis. Additionally quantile-wise analysis estimates are shown to check each variable coefficient slope and its implications using suitable examples. The regression residual graphs are also discussed in detail with appropriate examples using EViews.