Testing the non-parametric conditional CAPM in the Brazilian stock market/Avaliacao do CAPM condicional nao parametrico no mercado de acoes do Brasil

This paper seeks to analyze if the variations of returns and systematic risks from Brazilian portfolios could be explained by the nonparametric conditional Capital Asset Pricing Model (CAPM) by Wang (2002). There are four informational variables available to the investors: (i) the Brazilian industrial production level; (ii) the broad money supply M4; (iii) the inflation represented by the Indice de Precos ao Consumidor Amplo (IPCA); and (iv) the real-dollar exchange rate, obtained by PTAX dollar quotation. This study comprised the shares listed in the BOVESPA throughout January 2002 to December 2009. The test methodology developed by Wang (2002) and retorted to the Mexican context by Castillo-Spindola (2006) was used. The observed results indicate that the nonparametric conditional model is relevant in explaining the portfolios' returns of the sample considered for two among the four tested variables, M4 and PTAX dollar at 5% level of significance.