Estimating Risk Premia in the Bolivian Financial Market: Garch Models

Abstract

In an uncertain economic environment, risk averse investors demand risk premiums, to hold in their portfolio, assets subject to this uncertainty. This paper investigates if a conditional variance, a measure of total risk, is a significant determinant of the risk premium of the Bolivian financial assets, using ARCH (Autoregressive Conditional Heterocedastic) models. The ARCH models explicitly model time varying conditional variances by relating them to variables known from previous periods. The paper also tests the CAPM (Capital Asset Pricing Model), which provides a theory for the pricing of assets with uncertain returns using GARCH (Generalized Autoregressive Conditional Heterocedastic) models. This essentially assumes that agents update their estimates of the means, variances and/or covariances of returns each period, using the newly revealed surprises in the last period's asset returns. In this context, a GARCH process is estimated to the Bolivian financial market, where the expected return of each asset is proportional to the conditional covariance of each return with that of a market portfolio.