Numerical distribution functions for seasonal unit root tests

Abstract

When working with time series data observed at intervals smaller than a year, it is often necessary to test for the presence of seasonal unit roots.One of the most widely used methods for testing seasonal unit roots is that of HEGY, which provides test statistics with non-standard distributions. This paper describes a generalisation of this method for any periodicity and uses a response surface regressions approach to calculate the critical values and P values of the HEGY statistics whatever the periodicity and sample size of the data. The algorithms are prepared with the Gretl open source econometrics package and some new tables of critical values for daily, hourly and halfhourly data are presented.

Bayesian deep learning based method for probabilistic forecast of day-ahead electricity prices

“…In order to investigate the presence of seasonal unit root in the Italian PUN Time Series we employed the method reported in [103], representing a generalization of the Hylleberg, Engle, Granger and Yoo (HEGY) test for any periodicity. We employed the gretl open source software package [106] for such purpose.…”

Numerical distribution functions for seasonal stability tests

“…After the surface regression is estimated for the 221 quantiles for every statistic, an interpolation between these values may be made using the method by MacKinnon (1996), which is also used for example in Harvey & van Dijk (2006) and Diaz-Emparanza (2013). Consider the regression…”