Seasonal unit roots and forecasts of two-digit European industrial production

Osborn, Denise R.; Heravi, Saeed; Birchenhall, Chris

doi:10.1016/s0169-2070(98)00055-7

Cited by 60 publications

(51 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results of these experiments are contained in Table 4 comparison. This is a somewhat surprising finding, given the evidence of the HEGY tests that there is little seasonal integration; but is completely consistent with the finding of Osborn et al (1999) that seasonal difference models perform well when used to predict 2-digit industrial production series at short horizons, even though they find very little test-based evidence of seasonal integration.…”

Section: Prediction Experimentssupporting

confidence: 74%

“…This result suggests that seasonal integration tests that reject the null of SUROOT need to be interpreted with caution. Their poor finite sample properties may mislead investigators into believing that seasonal unit root models are not useful (see Osborn et al (1999) for a related discussion). However, for horizons of greater than one-step ahead, the SUROOT model performs poorly when used for prediction, suggesting that parameter estimation error is crucial to understanding the empirical performance of such models.…”

Section: Discussionmentioning

confidence: 99%

“…From a theoretical perspective, many papers have developed new testing methods and suggested various nonlinear seasonal models. A very few important contributions in this area include: Hylleberg (1992Hylleberg ( ,1994, Beaulieu and Miron (1993), Franses (1996a,b), Miron (1996), Miron and Beaulieu (1996), Franses, Hoek and Paap (1997), Franses and Vogelsang (1998), Osborn, Heravi and Birchenhall (1999), Ghysels and Osborn (2001), Franses and Paap (2002), Osborn (2002), Osborn and Rodrigues (2002), Franses and van Dijk (2005), and the references cited therein.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Prediction and simulation using simple models characterized by nonstationarity and seasonality

Swanson

Urbach²

2015

International Review of Economics & Finance

View full text Add to dashboard Cite

In this paper, we provide new evidence on the empirical usefulness of various simple seasonal models, and underscore the importance of carefully designing criteria by which one judges alternative models. In particular, we underscore the importance of both choice of forecast or simulation horizon and choice between minimizing point or distribution based loss measures. Our empirical analysis centers around the implementation of a series of simulation and prediction experiments, as well as a discussion of the stochastic properties of seasonal unit root models. Our prediction experiments are based on analysis of a group of 14 variables have been chosen to closely mimic the set of indicators used by the Federal Reserve to help in setting U.S. monetary policy, and our simulation experiments are based on a comparison of simulated and historical distributions of said variables using the testing approach of Corradi and Swanson (2007a). A key impetus for this paper stems from the fact that various financial service companies routinely create "economic scenarios", whereby seasonal and nonstationary financial and economic variables such as those examined here are simulated (and predicted) using relatively simple time series models. These "economic scenarios" are subsequently used in risk management and asset allocation, as is often mandated by various world financial regulatory authorities. Our findings suggest that a simple version of the seasonal unit root (SUROOT) model performs very well for predicting 8 of 14 variables, when the forecast horizon is 1-step ahead. However, for horizons of greater than one-step ahead, our SUROOT model perform poorly when used for prediction, suggesting that parameter estimation error is crucial to understanding the empirical performance of such models. This "parameter estimation error" result is confirmed via a series of Monte Carlo experiments. Simulation experiments yield similar conclusions, although SUROOT models in this case are useful for constructing "forward" conditional distributions at 1-and 3-step ahead horizons. Interestingly, simple periodic autoregressions do not have this property, and are found to perform very well in both prediction and simulation experiments, at all horizons up to 60 months ahead.JEL classification: C13, C22, C52, C53.

show abstract

Section: Prediction Experimentssupporting

confidence: 74%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction and simulation using simple models characterized by nonstationarity and seasonality

Swanson

Urbach²

2015

International Review of Economics & Finance

View full text Add to dashboard Cite

show abstract

“…The application of the proper filter to achieve stationarity is however a question of improving the forecast accuracy, cf. Franses (1991) or Osborn et al (1999). We apply several tests for both unit roots at the zero frequency and seasonal unit roots in the region-specific series.…”

Section: Regional Patterns Of Unemployment In Germanymentioning

confidence: 99%

Regional unemployment forecasts with spatial interdependencies

Schanne

Wapler

Weyh

2010

International Journal of Forecasting

View full text Add to dashboard Cite

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte.

show abstract

“…This confirms the results from our simulations. Thus, for this series, the HEGY test does not detect all the seasonal and non-seasonal unit roots and, as shown by Clements and Hendry (1997) and Osborn et al (1999), the forecasts from this incomplete filter are less accurate than those from imposing annual differencing.…”

Section: Us Seriesmentioning

confidence: 85%

Forecasts of the seasonal fractional integrated series

Darné

Guiraud

Terraza

2004

Journal of Forecasting

View full text Add to dashboard Cite

We study the probability of rejecting the seasonal unit root tests developed by Hylleberg et al. when they are applied to fractionally integrated seasonal time series. We find that these tests have quite low power and that they lead to a risk of over-differencing. The forecasting performance of fractionally integrated seasonal models is also examined. This approach is compared with the traditional approaches from Box-Jenkins methodology, and the HEGY-type test procedure. Forecasting results obtained from simulated series and quarterly economic time series show that the fractional approach improves the forecasting accuracy with regard to the other approaches. Copyright © 2004 John Wiley & Sons, Ltd.

show abstract

Seasonal unit roots and forecasts of two-digit European industrial production

Cited by 60 publications

References 22 publications

Prediction and simulation using simple models characterized by nonstationarity and seasonality

Prediction and simulation using simple models characterized by nonstationarity and seasonality

Regional unemployment forecasts with spatial interdependencies

Forecasts of the seasonal fractional integrated series

Contact Info

Product

Resources

About