Examining 81 countries over a period of up to 145 years and using various predictor variables and forecasting specifications, we provide a detailed analysis of equity premium predictability. We find that excess returns are more predictable in emerging and frontier markets than in developed markets. For all groups, forecast combinations perform very well out of sample. Analyzing the cross-section of countries, we find that market inefficiency is an important driver of return predictability. We also document significant cross-market return predictability. Finally, domestic inflation-adjusted returns are significantly more predictable than USD returns.
{"title":"Predicting the equity premium around the globe: Comprehensive evidence from a large sample","authors":"Fabian Hollstein , Marcel Prokopczuk , Björn Tharann , Chardin Wese Simen","doi":"10.1016/j.ijforecast.2024.05.002","DOIUrl":"10.1016/j.ijforecast.2024.05.002","url":null,"abstract":"<div><div>Examining 81 countries over a period of up to 145 years and using various predictor variables and forecasting specifications, we provide a detailed analysis of equity premium predictability. We find that excess returns are more predictable in emerging and frontier markets than in developed markets. For all groups, forecast combinations perform very well out of sample. Analyzing the cross-section of countries, we find that market inefficiency is an important driver of return predictability. We also document significant cross-market return predictability. Finally, domestic inflation-adjusted returns are significantly more predictable than USD returns.</div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 1","pages":"Pages 208-228"},"PeriodicalIF":6.9,"publicationDate":"2024-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141401101","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-08DOI: 10.1016/j.ijforecast.2024.05.006
Hui Cheng, Cuiqing Jiang, Zhao Wang, Xiaoya Ni
Accurately forecasting loss given default (LGD) poses challenges, due to its highly skewed distributions and complex nonlinear dependencies with predictors. To this end, we propose a multi-view locally weighted regression (MVLWR) method for LGD forecasting. To address the complexity of LGD distributions, we build a specific ensemble LGD forecasting model tailored for each new sample, providing flexibility and relaxing reliance on distribution assumptions. To address complex relationships, we combine multi-view learning and ensemble learning for LGD modeling. Specifically, we divide original features into multiple complementary groups, build a view-specific locally weighted model for each group, and aggregate the outputs from all view-specific models. An empirical evaluation using a real-world dataset shows that the proposed method outperforms all the benchmarked methods in terms of both out-of-sample and out-of-time performance in LGD forecasting. We also provide valuable insights and practical implications for stakeholders, particularly financial institutions, to enhance their LGD forecasting capabilities.
{"title":"Multi-view locally weighted regression for loss given default forecasting","authors":"Hui Cheng, Cuiqing Jiang, Zhao Wang, Xiaoya Ni","doi":"10.1016/j.ijforecast.2024.05.006","DOIUrl":"10.1016/j.ijforecast.2024.05.006","url":null,"abstract":"<div><div>Accurately forecasting loss given default (LGD) poses challenges, due to its highly skewed distributions and complex nonlinear dependencies with predictors. To this end, we propose a multi-view locally weighted regression (MVLWR) method for LGD forecasting. To address the complexity of LGD distributions, we build a specific ensemble LGD forecasting model tailored for each new sample, providing flexibility and relaxing reliance on distribution assumptions. To address complex relationships, we combine multi-view learning and ensemble learning<span> for LGD modeling. Specifically, we divide original features into multiple complementary groups, build a view-specific locally weighted model for each group, and aggregate the outputs from all view-specific models. An empirical evaluation using a real-world dataset shows that the proposed method outperforms all the benchmarked methods in terms of both out-of-sample and out-of-time performance in LGD forecasting. We also provide valuable insights and practical implications for stakeholders, particularly financial institutions, to enhance their LGD forecasting capabilities.</span></div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 1","pages":"Pages 290-306"},"PeriodicalIF":6.9,"publicationDate":"2024-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141413761","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-06DOI: 10.1016/j.ijforecast.2024.05.007
Philipp Adämmer , Jan Prüser , Rainer A. Schüssler
We examine the incremental value of news-based data relative to the FRED-MD economic indicators for quantile predictions of employment, output, inflation, and consumer sentiment in a high-dimensional setting. Our results suggest that news data contain valuable information not captured by a large set of economic indicators. We provide empirical evidence that this information can be exploited to improve tail risk predictions. The added value is largest when media coverage and sentiment are combined to compute text-based predictors. Methods that capture quantile-specific non-linearities produce superior forecasts to those with linear predictive relationships. The results are robust along different modeling choices.
{"title":"Forecasting macroeconomic tail risk in real time: Do textual data add value?","authors":"Philipp Adämmer , Jan Prüser , Rainer A. Schüssler","doi":"10.1016/j.ijforecast.2024.05.007","DOIUrl":"10.1016/j.ijforecast.2024.05.007","url":null,"abstract":"<div><div>We examine the incremental value of news-based data relative to the FRED-MD economic indicators for quantile predictions of employment, output, inflation, and consumer sentiment in a high-dimensional setting. Our results suggest that news data contain valuable information not captured by a large set of economic indicators. We provide empirical evidence that this information can be exploited to improve tail risk predictions. The added value is largest when media coverage and sentiment are combined to compute text-based predictors. Methods that capture quantile-specific non-linearities produce superior forecasts to those with linear predictive relationships. The results are robust along different modeling choices.</div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 1","pages":"Pages 307-320"},"PeriodicalIF":6.9,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-02DOI: 10.1016/j.ijforecast.2024.05.008
Jeroen Rombouts , Marie Ternes , Ines Wilms
Platform businesses operate on a digital core, and their decision-making requires high-dimensional accurate forecast streams at different levels of cross-sectional (e.g., geographical regions) and temporal aggregation (e.g., minutes to days). It also necessitates coherent forecasts across all hierarchy levels to ensure aligned decision-making across different planning units such as pricing, product, controlling, and strategy. Given that platform data streams feature complex characteristics and interdependencies, we introduce a non-linear hierarchical forecast reconciliation method that produces cross-temporal reconciled forecasts in a direct and automated way through popular machine learning methods. The method is sufficiently fast to allow forecast-based high-frequency decision-making that platforms require. We empirically test our framework on unique, large-scale streaming datasets from a leading on-demand delivery platform in Europe and a bicycle-sharing system in New York City.
{"title":"Cross-temporal forecast reconciliation at digital platforms with machine learning","authors":"Jeroen Rombouts , Marie Ternes , Ines Wilms","doi":"10.1016/j.ijforecast.2024.05.008","DOIUrl":"10.1016/j.ijforecast.2024.05.008","url":null,"abstract":"<div><div>Platform businesses operate on a digital core, and their decision-making requires high-dimensional accurate forecast streams at different levels of cross-sectional (e.g., geographical regions) and temporal aggregation (e.g., minutes to days). It also necessitates coherent forecasts across all hierarchy levels to ensure aligned decision-making across different planning units such as pricing, product, controlling, and strategy. Given that platform data streams feature complex characteristics and interdependencies, we introduce a non-linear hierarchical forecast reconciliation method that produces cross-temporal reconciled forecasts in a direct and automated way through popular machine learning methods. The method is sufficiently fast to allow forecast-based high-frequency decision-making that platforms require. We empirically test our framework on unique, large-scale streaming datasets from a leading on-demand delivery platform in Europe and a bicycle-sharing system in New York City.</div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 1","pages":"Pages 321-344"},"PeriodicalIF":6.9,"publicationDate":"2024-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-29DOI: 10.1016/j.ijforecast.2024.05.003
Paul Labonne
This paper presents a new way to account for downside and upside risks when producing density nowcasts of GDP growth. The approach relies on modelling location, scale, and shape common factors in real-time macroeconomic data. While movements in the location generate shifts in the central part of the predictive density, the scale controls its dispersion (akin to general uncertainty) and the shape its asymmetry, or skewness (akin to downside and upside risks). The empirical application is centred on US GDP growth, and the real-time data come from FRED-MD. The results show that there is more to real-time data than their levels or means: their dispersion and asymmetry provide valuable information for nowcasting economic activity. Scale and shape common factors (i) yield more reliable measures of uncertainty and (ii) improve precision when macroeconomic uncertainty is at its peak.
{"title":"Asymmetric uncertainty: Nowcasting using skewness in real-time data","authors":"Paul Labonne","doi":"10.1016/j.ijforecast.2024.05.003","DOIUrl":"10.1016/j.ijforecast.2024.05.003","url":null,"abstract":"<div><div>This paper presents a new way to account for downside and upside risks when producing density nowcasts of GDP growth. The approach relies on modelling location, scale, and shape common factors in real-time macroeconomic data. While movements in the location generate shifts in the central part of the predictive density, the scale controls its dispersion (akin to general uncertainty) and the shape its asymmetry, or skewness (akin to downside and upside risks). The empirical application is centred on US GDP growth, and the real-time data come from FRED-MD. The results show that there is more to real-time data than their levels or means: their dispersion and asymmetry provide valuable information for nowcasting economic activity. Scale and shape common factors (i) yield more reliable measures of uncertainty and (ii) improve precision when macroeconomic uncertainty is at its peak.</div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 1","pages":"Pages 229-250"},"PeriodicalIF":6.9,"publicationDate":"2024-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-25DOI: 10.1016/j.ijforecast.2024.05.004
Gunnar Bårdsen , Ragnar Nymoen
A framework for forecasting new COVID-19 cases jointly with hospital admissions and hospital beds with COVID-19 cases is presented. This project, dubbed CovidMod, produced 21 days ahead forecasts each working day from March 2021 to April 2022. Comparison of RMSFEs from that period, with the RMSFEs of the Norwegian Institute of Public Health (NIPH), favours the CovidMod forecasts, both for new cases and for hospital beds. Another comparison, with the short term forecasts produced by the Cardt method, shows little difference. Next, we present a new model where smooth transition regression is used as a feasible method to include forecasted effects of non-linear policy responses to the deviation between hospital beds and hospital bed capacity, on the forecasts of the original three variables. The forecasting performance of the model with endogenous policy effects is demonstrated retrospectively. It is suggested as a complementary approach to follow when the forecasted variables are generated from processes that include policy responses as realistic features.
{"title":"Dynamic time series modelling and forecasting of COVID-19 in Norway","authors":"Gunnar Bårdsen , Ragnar Nymoen","doi":"10.1016/j.ijforecast.2024.05.004","DOIUrl":"10.1016/j.ijforecast.2024.05.004","url":null,"abstract":"<div><div>A framework for forecasting new COVID-19 cases jointly with hospital admissions and hospital beds with COVID-19 cases is presented. This project, dubbed CovidMod, produced 21 days ahead forecasts each working day from March 2021 to April 2022. Comparison of RMSFEs from that period, with the RMSFEs of the Norwegian Institute of Public Health (NIPH), favours the CovidMod forecasts, both for new cases and for hospital beds. Another comparison, with the short term forecasts produced by the Cardt method, shows little difference. Next, we present a new model where smooth transition regression is used as a feasible method to include forecasted effects of non-linear policy responses to the deviation between hospital beds and hospital bed capacity, on the forecasts of the original three variables. The forecasting performance of the model with endogenous policy effects is demonstrated retrospectively. It is suggested as a complementary approach to follow when the forecasted variables are generated from processes that include policy responses as realistic features.</div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 1","pages":"Pages 251-269"},"PeriodicalIF":6.9,"publicationDate":"2024-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705212","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-20DOI: 10.1016/j.ijforecast.2024.05.001
Li Li , Han Li , Anastasios Panagiotelis
This paper extends the technique of gradient boosting with a focus on using domain-specific models instead of trees. The domain of mortality forecasting is considered as an application. The two novel contributions are to use well-known stochastic mortality models as weak learners in gradient boosting rather than trees, and to include a penalty that shrinks mortality forecasts in adjacent age groups and nearby geographical regions closer together. The proposed method demonstrates superior forecasting performance based on US male mortality data from 1969 to 2019. The proposed approach also enables us to interpret and visualize the results. The boosted model with age-based shrinkage yields the most accurate national-level mortality forecast. For state-level forecasts, spatial shrinkage provides further improvement in accuracy in addition to the benefits of age-based shrinkage. This improvement can be attributed to data sharing across states with large and small populations in adjacent regions and states with common risk factors.
{"title":"Boosting domain-specific models with shrinkage: An application in mortality forecasting","authors":"Li Li , Han Li , Anastasios Panagiotelis","doi":"10.1016/j.ijforecast.2024.05.001","DOIUrl":"10.1016/j.ijforecast.2024.05.001","url":null,"abstract":"<div><div><span>This paper extends the technique of gradient boosting with a focus on using domain-specific models instead of trees. The domain of mortality forecasting is considered as an application. The two novel contributions are to use well-known stochastic mortality models as weak learners in gradient boosting rather than trees, and to include a penalty that shrinks mortality forecasts in adjacent age groups and nearby </span>geographical regions<span> closer together. The proposed method demonstrates superior forecasting performance based on US male mortality data from 1969 to 2019. The proposed approach also enables us to interpret and visualize the results. The boosted model with age-based shrinkage yields the most accurate national-level mortality forecast. For state-level forecasts, spatial shrinkage provides further improvement in accuracy in addition to the benefits of age-based shrinkage. This improvement can be attributed to data sharing across states with large and small populations in adjacent regions and states with common risk factors.</span></div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 1","pages":"Pages 191-207"},"PeriodicalIF":6.9,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141138769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-15DOI: 10.1016/j.ijforecast.2024.04.007
Gianluca Cubadda , Stefano Grassi , Barbara Guardabascio
Many economic variables are characterized by changes in their conditional mean and volatility, and time-varying Vector Autoregressive Models are often used to handle such complexity. Unfortunately, as the number of series grows, they present increasing estimation and interpretation issues. This paper tries to address this problem by proposing a Multivariate Autoregressive Index model that features time-varying mean and volatility. Technically, we develop a new estimation methodology that mixes switching algorithms with the forgetting factors strategy of Koop and Korobilis (2012). This substantially reduces the computational burden and allows one to select or weigh the number of common components, and other data features, in real-time without additional computational costs. Using US macroeconomic data, we provide a forecast exercise that shows the feasibility and usefulness of this model.
{"title":"The time-varying Multivariate Autoregressive Index model","authors":"Gianluca Cubadda , Stefano Grassi , Barbara Guardabascio","doi":"10.1016/j.ijforecast.2024.04.007","DOIUrl":"10.1016/j.ijforecast.2024.04.007","url":null,"abstract":"<div><div>Many economic variables are characterized by changes in their conditional mean and volatility, and time-varying Vector Autoregressive Models are often used to handle such complexity. Unfortunately, as the number of series grows, they present increasing estimation and interpretation issues. This paper tries to address this problem by proposing a Multivariate Autoregressive Index model that features time-varying mean and volatility. Technically, we develop a new estimation methodology that mixes switching algorithms with the forgetting factors strategy of Koop and Korobilis (2012). This substantially reduces the computational burden and allows one to select or weigh the number of common components, and other data features, in real-time without additional computational costs. Using US macroeconomic data, we provide a forecast exercise that shows the feasibility and usefulness of this model.</div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 1","pages":"Pages 175-190"},"PeriodicalIF":6.9,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-07DOI: 10.1016/j.ijforecast.2024.04.006
Jiazi Chen , Zhiwu Hong , Linlin Niu
An extended dynamic Nelson–Siegel (DNS) model is developed with an additional functional demographic (FD) factor that considers the overall demographic age distribution as a persistent end-shifting driving force. The FD factor in the extended DNS model improves the accuracy of the yield curve forecast by reducing both bias and variance compared with the random walk model, the DNS model, the DNS model with a simple demographic factor of a middle-to-young age ratio, and a benchmark end-shifting model. The model with an unspanned FD factor performs substantially better than the alternative models for most maturities at forecast horizons between one and five years.
我们开发了一个扩展的动态内尔松-西格尔（DNS）模型，该模型增加了一个人口功能（FD）因子，将整体人口年龄分布视为一种持续的末端转移驱动力。与随机漫步模型、DNS 模型、带有中青年年龄比这一简单人口因素的 DNS 模型和基准末端移动模型相比，扩展 DNS 模型中的 FD 因子通过减少偏差和方差提高了收益率曲线预测的准确性。在 1 至 5 年的预测期限内，对于大多数期限的收益率曲线，采用无跨度 FD 因子的模型要比其他模型好得多。
{"title":"Forecasting interest rates with shifting endpoints: The role of the functional demographic age distribution","authors":"Jiazi Chen , Zhiwu Hong , Linlin Niu","doi":"10.1016/j.ijforecast.2024.04.006","DOIUrl":"10.1016/j.ijforecast.2024.04.006","url":null,"abstract":"<div><div>An extended dynamic Nelson–Siegel (DNS) model is developed with an additional functional demographic (FD) factor that considers the overall demographic age distribution as a persistent end-shifting driving force. The FD factor in the extended DNS model improves the accuracy of the yield curve forecast by reducing both bias and variance compared with the random walk model, the DNS model, the DNS model with a simple demographic factor of a middle-to-young age ratio, and a benchmark end-shifting model. The model with an unspanned FD factor performs substantially better than the alternative models for most maturities at forecast horizons between one and five years.</div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 1","pages":"Pages 153-174"},"PeriodicalIF":6.9,"publicationDate":"2024-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141031213","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-04DOI: 10.1016/j.ijforecast.2024.04.005
Anton Hasselgren , Ai Jun Hou , Sandy Suardi , Caihong Xu , Xiaoxia Ye
This paper explores whether the dispersion in forecasted crude oil prices from the European Central Bank Survey of Professional Forecasters can provide insights for predicting crude oil return volatility. It is well-documented that higher disagreement among forecasters of asset price implies greater uncertainty and higher return volatility. Using several Generalized Autoregressive Conditional Heteroskedasticity with Mixed Data Sampling (GARCH-MIDAS) models, we find, based on the in-sample estimation results, the oil market experiences greater volatility when the forecasters’ disagreements increase. The model that integrates both historical realized variance and forward-looking forecaster disagreement into the conditional variance, along with the model focusing solely on pure forward-looking forecaster disagreement, exhibits a much superior fit to the data compared to the model relying solely on realized variance and the models considering forward-looking forecasted mean return. The out-of-sample forecasting results unequivocally illustrate that incorporating forecaster disagreement offers valuable insights, markedly enhancing the predictive accuracy of crude oil return volatility within the GARCH-MIDAS model. Moreover, we illustrate the economic benefit of considering forecasters’ disagreement when forecasting volatility, demonstrating its significance for VaR risk management.
本文探讨了欧洲中央银行专业预测者调查所得出的原油价格预测离散度是否能为预测原油收益波动性提供启示。有大量文献表明，资产价格预测者之间的分歧越大，意味着不确定性越大，回报波动性越高。我们使用几个具有混合数据抽样的广义自回归条件异方差（GARCH-MIDAS）模型，根据样本内估计结果发现，当预测者之间的分歧增大时，石油市场的波动性也会增大。将历史已实现方差和前瞻性预测者分歧整合到条件方差中的模型，以及只关注纯粹前瞻性预测者分歧的模型，与只依赖已实现方差的模型和考虑前瞻性预测平均收益率的模型相比，与数据的拟合效果要好得多。样本外预测结果清楚地表明，将预测者分歧纳入 GARCH-MIDAS 模型可提供有价值的见解，显著提高原油收益波动的预测准确性。此外，我们还说明了在预测波动性时考虑预测者分歧的经济效益，证明了其对 VaR 风险管理的重要意义。
{"title":"Do oil price forecast disagreement of survey of professional forecasters predict crude oil return volatility?","authors":"Anton Hasselgren , Ai Jun Hou , Sandy Suardi , Caihong Xu , Xiaoxia Ye","doi":"10.1016/j.ijforecast.2024.04.005","DOIUrl":"10.1016/j.ijforecast.2024.04.005","url":null,"abstract":"<div><div>This paper explores whether the dispersion in forecasted crude oil prices from the European Central Bank Survey of Professional Forecasters can provide insights for predicting crude oil return volatility. It is well-documented that higher disagreement among forecasters of asset price implies greater uncertainty and higher return volatility. Using several Generalized Autoregressive Conditional Heteroskedasticity with Mixed Data Sampling (GARCH-MIDAS) models, we find, based on the in-sample estimation results, the oil market experiences greater volatility when the forecasters’ disagreements increase. The model that integrates both historical realized variance and forward-looking forecaster disagreement into the conditional variance, along with the model focusing solely on pure forward-looking forecaster disagreement, exhibits a much superior fit to the data compared to the model relying solely on realized variance and the models considering forward-looking forecasted mean return. The out-of-sample forecasting results unequivocally illustrate that incorporating forecaster disagreement offers valuable insights, markedly enhancing the predictive accuracy of crude oil return volatility within the GARCH-MIDAS model. Moreover, we illustrate the economic benefit of considering forecasters’ disagreement when forecasting volatility, demonstrating its significance for VaR risk management.</div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 1","pages":"Pages 141-152"},"PeriodicalIF":6.9,"publicationDate":"2024-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号