Asymmetric time aggregation and its potential benefits for forecasting annual data
For many economic time-series variables that are observed regularly and frequently, for example weekly, the underlying activity is not distributed uniformly across the year. For the aim of predicting annual data, one may consider temporal aggregation into larger subannual units based on an activity timescale instead of cal- endar time. Such a scheme may strike a balance between annual modeling (which processes little information) and modeling at the finest available frequency (which may lead to an excessive parameter dimension), and it may also outperform model- ing calendar time units (with some months or quarters containing more information than others). We suggest an algorithm that performs an approximate inversion of the inherent seasonal time deformation. We illustrate the procedure using two exemplary weekly time series.
|Keywords||seasonality, forecasting, time deformation, time series|
|Persistent URL||dx.doi.org/10.1007/s00181-014-0864-0, hdl.handle.net/1765/78816|
|Series||Econometric Institute Reprint Series , ERIM Top-Core Articles|
|Journal||Empirical Economics: a quarterly journal of the Institute for Advanced Studies, Vienna|
Kunst, R.M, & Franses, Ph.H.B.F. (2014). Asymmetric time aggregation and its potential benefits for forecasting annual data. Empirical Economics: a quarterly journal of the Institute for Advanced Studies, Vienna, 49, 363–387. doi:10.1007/s00181-014-0864-0