Volatility of Stock Market and Exchange Rate Returns in Peru: Long Memory or Short Memory with Level Shifts?

Though the econometrics literature on this area is extensive, in Peru few studies have been dedicated to the analysis of financial returns in general and volatility in particular. As part of an empirical research agenda suggested by Humala and Rodríguez (2013), this paper represents one of the first attempts to distinguish between long- and short-memory (with level shifts) in volatility of Peru’s stock market and exchange rate returns. We utilize the statistical approach put forward by Perron and Qu (2010). The data is end-of-day and span the period January 3, 1990 to June 13, 2013 (5,831 observations) for the stock market returns, and January, 3 1997 until June 24, 2013 (4,110 observations) for exchange rate returns. The analysis of the ACF, the periodogram and the fractional parameter estimation for the two volatilities suggest that the theoretical predictions of Perron and Qu’s simple mixture model (2010) are correct. The results are more conclusive for stock market volatility in comparison with those of the exchange rate. The application of one of the statistics employed by Perron and Qu (2010) suggest the rejection of a long-memory hypothesis for both volatilities. Nonetheless, the other statistics provide weak evidence against the null hypothesis, above all for the exchange rate market. To reinforce the findings, some results associated with other investigations are presented.

Keywords

Structural Change, Jumps, Long Memory Processes, Fractional Integration, Frequency Domain Estimates, Random Level Shifts, Stock Market and Forex Rate Volatilities in Peru

JEL Classification

C22