Natural gas volatility prediction: Fresh evidence from extreme weather and extended GARCH-MIDAS-ES model

Liang, Chao; Xia, Zhenglan; Liu, Xiaodong; Wang, Lu

doi:10.1016/j.eneco.2022.106437

Cited by 29 publications

(6 citation statements)

References 100 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to Table 3, the p values of the STL‐GARCH‐W model with the inclusion of weather indicators and the STL‐GJR‐GARCH‐W model are almost bigger than 0.1 for both statistics, indicating that both models exhibit strong forecasting power for NYMEX volatility. This finding is similar to the work of Liang, Xia, et al (2022). Second, the MCS tests for the STL‐GARCH‐W model that includes temperature, precipitation, and solar radiation both have a p value of 1, while the STL‐GJR‐GARCH‐W model that includes wind speed, humidity, and barometric pressure both have a p value of 1, indicating that the STL‐GARCH‐W model has the strongest predictive power when weather indicators have an effect on volatility, while when weather indicators have no significant effect on volatility, the STL‐GJR‐GARCH‐W model has the strongest forecasting power.…”

Section: Resultssupporting

confidence: 93%

“…Nick and Thoenes (2014) examined the main influences on the German natural gas market using a structural VAR approach, finding that temperature and supply shocks affect NGPV. Liang, Xia, et al (2022) Although the close link between weather and natural gas markets has been confirmed in existing literatures, there is a dearth of literature that includes weather indicators directly in NGPV forecasting models. More importantly, the future weather data that we need to use when attempting to forecast NGPV in future periods are unknown and need to be obtained by relying on forecasting techniques.…”

Section: Introductionmentioning

confidence: 93%

“…Nick and Thoenes (2014) examined the main influences on the German natural gas market using a structural VAR approach, finding that temperature and supply shocks affect NGPV. Liang, Xia, et al (2022) based on an extended GARCH‐MIDAS model to consider the predictability of extreme weather information on NGPV, and the empirical results show that the forecasting model with the addition of weather indicators does outperform the forecasting model without the addition of weather indicators. Importantly, based on various out‐of‐sample tests, some extreme weather indicators can provide more valuable information to forecast NGPV.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Role of weather in the natural gas market: Insights from the STL‐GARCH‐W method

Peng,

Xia,

Huang

et al. 2023

International Finance

Self Cite

View full text Add to dashboard Cite

Weather has been shown to affect natural gas markets, but there is limited research on the strength and manner in which weather affects predictions of natural gas volatility. In this study, six weather indicators are used as exogenous variables, and seasonal‐trend decomposition‐generalized autoregressive conditional heteroskedasticity‐Weather (STL‐GARCH‐W) and STL‐GJR‐GARCH‐W models are constructed to explore the effect of weather on global natural gas market. The empirical findings indicate that temperature and precipitation have a notable positive effect on natural gas, while solar radiation has a prominent negative effect. Furthermore, the STL‐GARCH‐W model outperform the STL‐GJR‐GARCH‐W model and the benchmark STL‐GARCH model when temperature, precipitation, and solar radiation are considered. In addition, the January effect has been shown to significantly influence natural gas price volatility. Finally, most parameters in both models are of statistical significance, demonstrating that both models accurately forecast natural gas volatility and emphasizing the importance of weather indicators for modelling natural gas price volatility. Our study provides new insights for energy market investors and policy makers.

show abstract

Section: Resultssupporting

confidence: 93%

Section: Introductionmentioning

confidence: 93%

“…Nick and Thoenes (2014) examined the main influences on the German natural gas market using a structural VAR approach, finding that temperature and supply shocks affect NGPV. Liang, Xia, et al (2022) based on an extended GARCH‐MIDAS model to consider the predictability of extreme weather information on NGPV, and the empirical results show that the forecasting model with the addition of weather indicators does outperform the forecasting model without the addition of weather indicators. Importantly, based on various out‐of‐sample tests, some extreme weather indicators can provide more valuable information to forecast NGPV.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Role of weather in the natural gas market: Insights from the STL‐GARCH‐W method

Peng,

Xia,

Huang

et al. 2023

International Finance

Self Cite

View full text Add to dashboard Cite

show abstract

“…Additionally, the study explored whether the impact of influencing factors differed among various oil types, including WTI and Brent crude oil. Also (Liang et al, 2022;Raza et al, 2023;Salisu, Gupta, et al, 2022) used the GARCH-MIDAS model to forecast volatility in the commodities space.…”

Section: Literature Reviewmentioning

confidence: 99%

The Role of Macroeconomic Variables in Forecasting Equity Market Volatility in the East African Community Using Garch-Midas Model

Sheng,

Jade

2024

ESJ

View full text Add to dashboard Cite

This study delves into the dynamic relationship between macroeconomic variables and equity market volatility in the East African Community. The research employs the Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model coupled with the Mixed Data Sampling (MIDAS) approach. Through a comparative process, it is found that the different macroeconomic variables exhibit heterogeneous effects on the different countries in the East African community that is macroeconomic factors significantly explain the variation in stock market volatility in Uganda and including these factors in the GARCH-MIDAS model improved its forecasting ability, however, in Kenya it was found that majority of the macroeconomic variables had insignificant effects on stock market volatility and didn’t improve the forecasting ability of the GARCH-MIDAS model.

show abstract

“…So far, the existing literature has mostly focused on the relations between NG and other commodities or securities (see, for instance, [38][39][40][41][42][43][44][45][46][47]), as well as on modeling price volatility (e.g., [48][49][50][51][52][53][54][55]), demand and supply (e.g., [56][57][58][59][60][61][62][63][64]), spot prices (e.g., [65][66][67][68][69][70][71][72][73][74][75][76]) or futures prices of individual contracts (e.g., [77][78][79]). Relatively less attention has been paid to NG futures prices term structure modeling and forecasting and only a few studies have partly tackled the issues we are dealing with.…”

Section: Introductionmentioning

confidence: 99%

A Machine-Learning-Based Approach for Natural Gas Futures Curve Modeling

Castello

Resta

2023

Energies

View full text Add to dashboard Cite

This work studies the term structure dynamics in the natural gas futures market, focusing on the Dutch Title Transfer Facility (TTF) daily futures prices. At first, using the whole dataset, we compared the in-sample fitting performance of three models: the four-factor dynamic Nelson–Siegel–Svensson (4F-DNSS) model, the five-factor dynamic De Rezende–Ferreira (5F-DRF) model, and the B-spline model. Our findings suggest that B-spline is the method that achieves the best in-line fitting results. Then, we turned our attention to forecasting, using data from 20 January 2011 to 13 May 2022 as the training set and the remaining data, from 16 May to 13 June 2022, for day-ahead predictions. In this second part of the work we combined the above mentioned models (4F-DNSS, 5F-DRF and B-spline) with a Nonlinear Autoregressive Neural Network (NAR-NN), asking the NAR-NN to provide parameter tuning. All the models provided accurate out-of-sample prediction; nevertheless, based on extensive statistical tests, we conclude that, as in the previous case, B-spline (combined with an NAR-NN) ensured the best out-of-sample prediction.

show abstract

Natural gas volatility prediction: Fresh evidence from extreme weather and extended GARCH-MIDAS-ES model

Cited by 29 publications

References 100 publications

Role of weather in the natural gas market: Insights from the STL‐GARCH‐W method

Role of weather in the natural gas market: Insights from the STL‐GARCH‐W method

The Role of Macroeconomic Variables in Forecasting Equity Market Volatility in the East African Community Using Garch-Midas Model

A Machine-Learning-Based Approach for Natural Gas Futures Curve Modeling

Contact Info

Product

Resources

About