Comparison of Entropy Measures in Panel Quantile Regression and Applications to Economic Growth Analysis

Abstract

The three entropy measures (Shannon, Tsallis, and Renyi entropy) are used as the objective of the entropy functions in Generalized Maximum Entropy(GME) to estimate the unknown parameters in the panel quantile regression model. This study applies these estimators to the macroeconomic dataset. The results show that Tsallis entropy is the most appropriate measure to describe the effect of macroeconomic variables on economic growth in G20 countries as it provides the lowest mean squared error (MSE) and root mean squared error (RMSE). The results also show that the Shannon entropy GME estimates a bit different from Tsallis and Renyi in terms of the magnitudes of the estimates, particularly in the extreme quantiles(10th and 90th).