Nonfractional Long-Range Dependence: Long Memory, Antipersistence, and Aggregation

This paper used cross-sectional aggregation as the inspiration for a model with long-range dependence that arises in actual data. One of advantages our is it less brittle than fractionally integrated processes. In particular, we showed antipersistent phenomenon not present cross-sectionally aggregated process. We proved this has implications estimators frequency domain, which will be misspecified nonfractional long-range-dependent processes negative degrees persistence. As an application, how can approximate differenced process using theoretically-motivated An example temperature data framework provides better fit to fractional difference operator.