Macroeconomic development and stock market performance : a non-parametric approach

This paper applies a local-linear non-parametric kernel regression technique to examine the effect of macroeconomic factors on stock market performance in Ghana. We show that the popular parametric specification in the existing literature suffers from functional misspecification. The evidence suggests that the relationship is non-linear and hence the implied elasticities are non-constant, contrary to findings in the literature. The main finding of the study suggests that stock prices are significantly affected by macroeconomic fundamentals and oil price shocks albeit weakly. This reinforces the need to closely monitor behaviour of macroeconomic indicators while sustaining prudent macroeconomic policy management.