Short and Long-Term Dynamic Dependencies of Main Latin American Stock Indexes and Commodity Prices: A Wavelet Approach

Abstract

Modern portfolio theory seeks to maximize returns and minimize risk through the selection of non-correlated investment instruments. Investment instruments in the portfolio are, often, nonlinear and non-stationary making forecasting of returns difficult. The use of decomposition models has been found to improve the accuracy of predictive models. This paper extends modern portfolio theory by applying wavelet analysis to the Latin American stock markets in various time horizons as investment vehicles in a portfolio along with major commodity markets. The main findings reveal that different commodities are needed in the portfolio depending on the time horizon and market.