Asymmetric time series and temporal aggregation

被引：18

作者：

Brännäs, K ^{[1
]}

Ohlsson, H

机构：

[1] Umea Univ, Dept Econ, SE-90187 Umea, Sweden

[2] Uppsala Univ, Dept Econ, SE-75120 Uppsala, Sweden

来源：

REVIEW OF ECONOMICS AND STATISTICS | 1999年 / 81卷 / 02期

关键词：

D O I：

10.1162/003465399558120

中图分类号：

F [经济];

学科分类号：

02 ;

摘要：

The detection of nonlinearities could depend on the sampling frequency. Asymmetric monthly series may become symmetric when aggregated to quarterly or annual frequencies. We test against nonlinearity using the nonlinear autoregressive asymmetric moving average (ARasMA) model, which nests the linear ARMA model as a special case. Using monthly, quarterly, and annual Swedish unemployment series, we find support for symmetry/linearity in the annual series but not in the monthly and quarterly series.

引用

页码：341 / 344

页数：4