Systematic risk assesment using OLS method : the case of the capital market of Bosnia and Herzegovina

The Sharpe-Lintner Capital Asset Pricing Model (CAPM) implies a simple linear equation for pricing risky financial assets, individually and in portfolios. CAPM finds that the relevant risk measure of individual financial assets held as a portion of a well-diversified portfolio is not a variance (or a standard deviation) of financial assets, as proposed by the Modern Portfolio Theory, but a contribution of financial assets to the portfolio variance, measured by the financial asset beta. Beta coefficient is the measure of the systematic risk of risky assets. This paper explores beta coefficients of stocks of the Bosnia and Herzegovina capital market. This capital market is new and underdeveloped, with a modest supply of securities and with a small number of marketable securities. It is interesting to explore whether the beta coefficients of domestic stocks are efficient and whether they could be used in portfolio management. The paper employs the OLS method to estimate the standard Sharpe-Linter CAPM model. As in most other new markets, this market has a non-synchronous trading problem, which determined the selection of the sample used in the econometric analysis. A representative sample of stocks with satisfactory marketability is analyzed over a five-year period, i.e. 2005- 2009. The basic hypothesis of the research is: beta coefficient as a measure of systematic risk is a relevant risk measure for the capital market of Bosnia and Herzegovina. A special aim of the paper is to explore whether estimated models satisfy the presumptions of the linear regression model, which is being examined using a series of diagnostic tests. The results of this paper can be widely used and have significant implications for business purposes. Special attention is dedicated to estimating efficient beta coefficients that may be considered as reliable in a wide use of the CAPM model in financial practice.