Comparing price forecast accuracy of natural gas models and futures markets [An article from: Energy Policy]
Book Details
Author(s)G. Wong-Parodi, L. Dale, A. Lekov
PublisherElsevier
ISBN / ASINB000PAUZ64
ISBN-13978B000PAUZ64
AvailabilityAvailable for download now
MarketplaceUnited States 🇺🇸
Description
This digital document is a journal article from Energy Policy, published by Elsevier in 2006. The article is delivered in HTML format and is available in your Amazon.com Media Library immediately after purchase. You can view it with any web browser.
Description:
The purpose of this article is to compare the accuracy of forecasts for natural gas prices as reported by the Energy Information Administration's short-term energy outlook (STEO) and the futures market for the period from 1998 to 2004. The analysis tabulates the existing data and develops a statistical comparison of the error between STEO and US wellhead natural gas prices and between Henry Hub and US wellhead spot prices. The results indicate that, on average, Henry Hub is a slightly better predictor of natural gas prices with an average error of -0.52 and a standard deviation of 1.25 than STEO with an average error of -0.83 and a standard deviation of 1.34. In addition, the results reveal that during the 13-24 months of the 2-year ahead forecast, STEO is a biased predictor of natural gas prices. This analysis suggests that as the futures market continues to report longer forward prices (currently out to 5 years), it may be of interest to economic modelers to compare the accuracy of their models to the futures market. The authors would especially like to thank Doug Hale of the Energy Information Administration for supporting and reviewing this work.
Description:
The purpose of this article is to compare the accuracy of forecasts for natural gas prices as reported by the Energy Information Administration's short-term energy outlook (STEO) and the futures market for the period from 1998 to 2004. The analysis tabulates the existing data and develops a statistical comparison of the error between STEO and US wellhead natural gas prices and between Henry Hub and US wellhead spot prices. The results indicate that, on average, Henry Hub is a slightly better predictor of natural gas prices with an average error of -0.52 and a standard deviation of 1.25 than STEO with an average error of -0.83 and a standard deviation of 1.34. In addition, the results reveal that during the 13-24 months of the 2-year ahead forecast, STEO is a biased predictor of natural gas prices. This analysis suggests that as the futures market continues to report longer forward prices (currently out to 5 years), it may be of interest to economic modelers to compare the accuracy of their models to the futures market. The authors would especially like to thank Doug Hale of the Energy Information Administration for supporting and reviewing this work.
