ANALYZING INFLATION BY THE FRACTIONALLY INTEGRATED ARFIMA-GARCH MODEL

This paper considers the application of long-memory processes to descr ibing inflation for ten countries. We implement a new procedure to obt ain approximate maximum likelihood estimates of an ARFIMA-GARCH proces s; which is fractionally integrated I(d) with a superimposed stationar y ARMA component in its conditional mean. Additionally, this long memo ry process is allowed to have GARCH type conditional heteroscedasticit y. On analysing monthly post-World War II CPI inflation for ten differ ent countries, we find strong evidence of long memory with mean revert ing behaviour for all countries except Japan, which appears stationary . For three high inflation economies there is evidence that the mean a nd volatility of inflation interact in a way that is consistent with t he Friedman hypothesis.