ABSTRACT: This paper analyzed the effects that variations in the exchange rate and international prices of the soybean have on the price of the soybean oil, in retail level, in the city of São Paulo. This article tested methods of time series, like unit root test, Granger causality test, Johansen cointegration test, Vectorial Autoregressive model (VAR), Variance Decomposition of Prediction Error and Impulse Response function. The period includes January from 1999 to December of 2002. The causality tests showed that the exchange rate 2 and international price of the soy affect the behavior of the price of the soy oil, however, the variables are not co- integrated, in other words, there is no long run relationship among them.
            The results of the variance decomposition of the prediction error and of the impulse response function showed that the exchange rate and price of the soybean have effect just in the short  run on the price of the soy oil. Empirical results point out that variables don’t cointegrate, possibly, reflects the fact that the market of soy oil presents characteristics different from the
other segments of the soy complex. Not only external variables, but also, internal variable are very important in the formation of the price of the soy oil.
 

Key-Words: soybean oil, price, VAR model, causality test.
 

[Margarido, Mario Antonio; Bueno, Carlos Roberto; Martins, Vagner; Carnevalli, Luciana; Análise dos Efeitos
Preço e Câmbio sobre o Preço do Óleo de Soja na Cidade de São Paulo: uma aplicação do modelo VAR.].
Recife. V Encontro de Economistas da Língua Portuguesa, 5 - 7 de novembro de 2003.