Pub Date : 2024-10-10DOI: 10.1016/j.ijforecast.2024.09.003
Raffaele Mattera , Philip Hans Franses
This paper proposes to use factor models with cluster structure to forecast growth rates of house prices in the US. We assume the presence of global and cluster-specific factors and that the clustering structure is unknown. We adopt a computational procedure that automatically estimates the number of global factors, the clustering structure and the number of clustered factors. The procedure enhances spatial clustering so that the nature of clustered factors reflects the similarity of the time series in the time domain and their spatial proximity. Considering house prices in 1975–2023, we highlight the existence of four main clusters in the US. Moreover, we show that forecasting approaches incorporating global and cluster-specific factors provide more accurate forecasts than models using only global factors and models without factors.
{"title":"Forecasting house price growth rates with factor models and spatio-temporal clustering","authors":"Raffaele Mattera , Philip Hans Franses","doi":"10.1016/j.ijforecast.2024.09.003","DOIUrl":"10.1016/j.ijforecast.2024.09.003","url":null,"abstract":"<div><div>This paper proposes to use factor models with cluster structure to forecast growth rates of house prices in the US. We assume the presence of global and cluster-specific factors and that the clustering structure is unknown. We adopt a computational procedure that automatically estimates the number of global factors, the clustering structure and the number of clustered factors. The procedure enhances spatial clustering so that the nature of clustered factors reflects the similarity of the time series in the time domain and their spatial proximity. Considering house prices in 1975–2023, we highlight the existence of four main clusters in the US. Moreover, we show that forecasting approaches incorporating global and cluster-specific factors provide more accurate forecasts than models using only global factors and models without factors.</div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 1","pages":"Pages 398-417"},"PeriodicalIF":6.9,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705207","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 : 2024-10-07DOI: 10.1016/j.ijforecast.2024.09.002
Chao Zhang , Xingyue Pu , Mihai Cucuringu , Xiaowen Dong
We present a novel nonparametric methodology for modeling and forecasting multivariate realized volatilities using customized graph neural networks to incorporate spillover effects across stocks. The proposed model offers the benefits of incorporating spillover effects from multi-hop neighbors, capturing nonlinear relationships, and flexible training with different loss functions. The empirical findings suggest that incorporating spillover effects from multi-hop neighbors alone does not yield a clear advantage in terms of predictive accuracy. Furthermore, modeling nonlinear spillover effects enhances the forecasting accuracy of realized volatilities, particularly for short-term horizons of up to one week. More importantly, our results consistently indicate that training with the quasi-likelihood loss leads to substantial improvements in model performance compared to the commonly used mean squared error, primarily due to its superior handling of heteroskedasticity. A comprehensive series of empirical evaluations in alternative settings confirm the robustness of our results.
{"title":"Forecasting realized volatility with spillover effects: Perspectives from graph neural networks","authors":"Chao Zhang , Xingyue Pu , Mihai Cucuringu , Xiaowen Dong","doi":"10.1016/j.ijforecast.2024.09.002","DOIUrl":"10.1016/j.ijforecast.2024.09.002","url":null,"abstract":"<div><div>We present a novel nonparametric methodology for modeling and forecasting multivariate realized volatilities using customized graph neural networks to incorporate spillover effects across stocks. The proposed model offers the benefits of incorporating spillover effects from multi-hop neighbors, capturing nonlinear relationships, and flexible training with different loss functions. The empirical findings suggest that incorporating spillover effects from multi-hop neighbors alone does not yield a clear advantage in terms of predictive accuracy. Furthermore, modeling nonlinear spillover effects enhances the forecasting accuracy of realized volatilities, particularly for short-term horizons of up to one week. More importantly, our results consistently indicate that training with the quasi-likelihood loss leads to substantial improvements in model performance compared to the commonly used mean squared error, primarily due to its superior handling of heteroskedasticity. A comprehensive series of empirical evaluations in alternative settings confirm the robustness of our results.</div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 1","pages":"Pages 377-397"},"PeriodicalIF":6.9,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705206","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 : 2024-09-26DOI: 10.1016/j.ijforecast.2024.09.001
Niko Hauzenberger , Michael Pfarrhofer , Luca Rossini
In this paper we propose a time-varying parameter (TVP) vector error correction model (VECM) with heteroskedastic disturbances. We propose tools to carry out dynamic model specification in an automatic fashion. This involves using global–local priors and postprocessing the parameters to achieve truly sparse solutions. Depending on the respective set of coefficients, we achieve this by minimizing auxiliary loss functions. Our two-step approach limits overfitting and reduces parameter estimation uncertainty. We apply this framework to modeling European electricity prices. When considering daily electricity prices for different markets jointly, our model highlights the importance of explicitly addressing cointegration and nonlinearities. In a forecasting exercise focusing on hourly prices for Germany, our approach yields competitive metrics of predictive accuracy.
{"title":"Sparse time-varying parameter VECMs with an application to modeling electricity prices","authors":"Niko Hauzenberger , Michael Pfarrhofer , Luca Rossini","doi":"10.1016/j.ijforecast.2024.09.001","DOIUrl":"10.1016/j.ijforecast.2024.09.001","url":null,"abstract":"<div><div>In this paper we propose a time-varying parameter (TVP) vector error correction model (VECM) with heteroskedastic disturbances. We propose tools to carry out dynamic model specification in an automatic fashion. This involves using global–local priors and postprocessing the parameters to achieve truly sparse solutions. Depending on the respective set of coefficients, we achieve this by minimizing auxiliary loss functions. Our two-step approach limits overfitting and reduces parameter estimation uncertainty. We apply this framework to modeling European electricity prices. When considering daily electricity prices for different markets jointly, our model highlights the importance of explicitly addressing cointegration and nonlinearities. In a forecasting exercise focusing on hourly prices for Germany, our approach yields competitive metrics of predictive accuracy.</div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 1","pages":"Pages 361-376"},"PeriodicalIF":6.9,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705205","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 : 2024-09-20DOI: 10.1016/j.ijforecast.2024.08.007
Bahman Rostami-Tabar, Pierre Pinson, Michael D. Porter
{"title":"Guest editorial: Forecasting for social good","authors":"Bahman Rostami-Tabar, Pierre Pinson, Michael D. Porter","doi":"10.1016/j.ijforecast.2024.08.007","DOIUrl":"10.1016/j.ijforecast.2024.08.007","url":null,"abstract":"","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 1","pages":"Pages 1-2"},"PeriodicalIF":6.9,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142704580","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 : 2024-08-31DOI: 10.1016/j.ijforecast.2024.07.008
Maolin Yang, Muyi Li, Guodong Li
This paper addresses the challenge of forecasting multivariate long-memory time series. While statistical models such as the autoregressive fractionally integrated moving average (ARFIMA) and hyperbolic generalized autoregressive conditional heteroscedasticity (HYGARCH) can capture long-memory effects in time series data, they are often limited by dimensionality and parametric specification. Alternatively, recurrent neural networks (RNNs) are popular tools for approximating complex structures in sequential data. However, the lack of long-memory effect of these networks has been justified from a statistical perspective. In this paper, we propose a new network process called the memory-augmented gated recurrent unit (MGRU), which incorporates a fractionally integrated filter into the original GRU structure. We investigate the long-memory effect of the MGRU process, and demonstrate its effectiveness at capturing long-range dependence in real applications. Our findings illustrate that the proposed MGRU network outperforms existing models, indicating its potential as a promising tool for long-memory time series forecasting.
{"title":"On memory-augmented gated recurrent unit network","authors":"Maolin Yang, Muyi Li, Guodong Li","doi":"10.1016/j.ijforecast.2024.07.008","DOIUrl":"https://doi.org/10.1016/j.ijforecast.2024.07.008","url":null,"abstract":"This paper addresses the challenge of forecasting multivariate long-memory time series. While statistical models such as the autoregressive fractionally integrated moving average (ARFIMA) and hyperbolic generalized autoregressive conditional heteroscedasticity (HYGARCH) can capture long-memory effects in time series data, they are often limited by dimensionality and parametric specification. Alternatively, recurrent neural networks (RNNs) are popular tools for approximating complex structures in sequential data. However, the lack of long-memory effect of these networks has been justified from a statistical perspective. In this paper, we propose a new network process called the memory-augmented gated recurrent unit (MGRU), which incorporates a fractionally integrated filter into the original GRU structure. We investigate the long-memory effect of the MGRU process, and demonstrate its effectiveness at capturing long-range dependence in real applications. Our findings illustrate that the proposed MGRU network outperforms existing models, indicating its potential as a promising tool for long-memory time series forecasting.","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"74 1","pages":""},"PeriodicalIF":7.9,"publicationDate":"2024-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142190563","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 : 2024-08-24DOI: 10.1016/j.ijforecast.2024.07.009
Yilun Dong, Youzhi Hao, Detang Lu
Shale gas production forecasting is an important research topic in the gas industry. A common shale gas block includes dozens or even thousands of wells and therefore has a great number of historical production series. However, most existing methods apply single-well modelling. This cannot exploit data from other wells and requires a long production history from the target well, so the forecasting timeliness is compromised. Moreover, the parameters required by many of the existing methods are difficult to collect in practice, so the forecasting accessibility is compromised. Therefore, this study presents a shale gas production forecasting framework with improved timeliness and accessibility. To ensure timeliness, the proposed approach utilises historical data from existing wells and only requires a short production history from the target well. To ensure accessibility, the proposed approach only requires past daily production time and gas yield. The performance of the proposed method is demonstrated through a comparison with baseline methods. The results regarding cumulative gas production forecasting indicate that the proposed method has an average overall mean absolute percentage error (OMAPE) of 0.210, outperforming an artificial neural network with an average OMAPE of 0.241 and ARIMA with an average OMAPE of more than 2.
{"title":"A framework for timely and accessible long-term forecasting of shale gas production based on time series pattern matching","authors":"Yilun Dong, Youzhi Hao, Detang Lu","doi":"10.1016/j.ijforecast.2024.07.009","DOIUrl":"https://doi.org/10.1016/j.ijforecast.2024.07.009","url":null,"abstract":"Shale gas production forecasting is an important research topic in the gas industry. A common shale gas block includes dozens or even thousands of wells and therefore has a great number of historical production series. However, most existing methods apply single-well modelling. This cannot exploit data from other wells and requires a long production history from the target well, so the forecasting timeliness is compromised. Moreover, the parameters required by many of the existing methods are difficult to collect in practice, so the forecasting accessibility is compromised. Therefore, this study presents a shale gas production forecasting framework with improved timeliness and accessibility. To ensure timeliness, the proposed approach utilises historical data from existing wells and only requires a short production history from the target well. To ensure accessibility, the proposed approach only requires past daily production time and gas yield. The performance of the proposed method is demonstrated through a comparison with baseline methods. The results regarding cumulative gas production forecasting indicate that the proposed method has an average overall mean absolute percentage error (OMAPE) of 0.210, outperforming an artificial neural network with an average OMAPE of 0.241 and ARIMA with an average OMAPE of more than 2.","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"3 1","pages":""},"PeriodicalIF":7.9,"publicationDate":"2024-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142190564","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 : 2024-07-29DOI: 10.1016/j.ijforecast.2024.07.001
Nadine Kafa, M. Zied Babai, Walid Klibi
Forecasting for Social Good has gained considerable attention for its impact on individuals, businesses, and society. This research introduces an integrated hierarchical forecasting-based decision-making approach for mail flow in a major postal organisation, presenting new social performance indicators. These indicators, including the discharge level, discharge rate, and overload rate, guide decision makers toward consistent workload planning, bridging a literature gap concerning forecast utility measures. The study evaluates three forecasting methods—exponential smoothing with error, trend, and seasonality (ETS), the autoregressive integrated moving average (ARIMA), and the light gradient boosting machine (LightGBM)—in terms of forecast accuracy and social measures, comparing them to the organisation’s current method. The empirical results confirm that the proposed approach is more accurate than the current method. Moreover, while ETS shows the highest forecast accuracy, LightGBM outperforms all methods in social measures. This indicates that a highly accurate forecasting method does not always enhance social performance, challenging traditional views on forecasting evaluation.
{"title":"Forecasting mail flow: A hierarchical approach for enhanced societal wellbeing","authors":"Nadine Kafa, M. Zied Babai, Walid Klibi","doi":"10.1016/j.ijforecast.2024.07.001","DOIUrl":"10.1016/j.ijforecast.2024.07.001","url":null,"abstract":"<div><div>Forecasting for Social Good has gained considerable attention for its impact on individuals, businesses, and society. This research introduces an integrated hierarchical forecasting-based decision-making approach for mail flow in a major postal organisation, presenting new social performance indicators. These indicators, including the discharge level, discharge rate, and overload rate, guide decision makers toward consistent workload planning, bridging a literature gap concerning forecast utility measures. The study evaluates three forecasting methods—exponential smoothing with error, trend, and seasonality (ETS), the autoregressive integrated moving average (ARIMA), and the light gradient boosting machine (LightGBM)—in terms of forecast accuracy and social measures, comparing them to the organisation’s current method. The empirical results confirm that the proposed approach is more accurate than the current method. Moreover, while ETS shows the highest forecast accuracy, LightGBM outperforms all methods in social measures. This indicates that a highly accurate forecasting method does not always enhance social performance, challenging traditional views on forecasting evaluation.</div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 1","pages":"Pages 51-65"},"PeriodicalIF":6.9,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142704583","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 : 2024-07-10DOI: 10.1016/j.ijforecast.2024.06.004
Nowshin Sharmile , Isaac A. Nuamah , Lauren Davis , Funda Samanlioglu , Steven Jiang , Carter Crain
Non-profit hunger relief organizations primarily depend on donors’ benevolence to help alleviate hunger in their communities. However, the quantity and frequency of donations they receive may vary over time, thus making fair distribution of donated supplies challenging. This paper presents a hierarchical forecasting methodology to determine the quantity of food donations received per month in a multi-warehouse food aid network. We further link the forecasts to an optimization model to identify the fair allocation of donations, considering the network distribution capacity in terms of supply chain coordination and flexibility. The results indicate which locations within the network are under-served and how donated supplies can be allocated to minimize the deviation between overserved and underserved counties.
{"title":"Predicting and optimizing the fair allocation of donations in hunger relief supply chains","authors":"Nowshin Sharmile , Isaac A. Nuamah , Lauren Davis , Funda Samanlioglu , Steven Jiang , Carter Crain","doi":"10.1016/j.ijforecast.2024.06.004","DOIUrl":"10.1016/j.ijforecast.2024.06.004","url":null,"abstract":"<div><div><span>Non-profit hunger relief organizations primarily depend on donors’ benevolence to help alleviate hunger in their communities. However, the quantity and frequency of donations they receive may vary over time, thus making fair distribution of donated supplies challenging. This paper presents a hierarchical forecasting methodology to determine the quantity of food donations received per month in a multi-warehouse food aid network. We further link the forecasts to an optimization model to identify the fair allocation of donations, considering the network distribution capacity in terms of </span>supply chain coordination and flexibility. The results indicate which locations within the network are under-served and how donated supplies can be allocated to minimize the deviation between overserved and underserved counties.</div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 1","pages":"Pages 31-50"},"PeriodicalIF":6.9,"publicationDate":"2024-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141707869","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 : 2024-06-21DOI: 10.1016/j.ijforecast.2024.06.002
Wei-Ting Lai , Ray-Bing Chen , Shih-Feng Huang
This study proposes a modified VAR-deGARCH model, denoted by M-VAR-deGARCH, for modeling asynchronous multivariate financial time series with GARCH effects and simultaneously accommodating the latest market information. A variational Bayesian (VB) procedure is developed for the M-VAR-deGARCH model to infer structure selection and parameter estimation. We conduct extensive simulations and empirical studies to evaluate the fitting and forecasting performance of the M-VAR-deGARCH model. The simulation results reveal that the proposed VB procedure produces satisfactory selection performance. In addition, our empirical studies find that the latest market information in Asia can provide helpful information to predict market trends in Europe and South Africa, especially when momentous events occur.
{"title":"A modified VAR-deGARCH model for asynchronous multivariate financial time series via variational Bayesian inference","authors":"Wei-Ting Lai , Ray-Bing Chen , Shih-Feng Huang","doi":"10.1016/j.ijforecast.2024.06.002","DOIUrl":"10.1016/j.ijforecast.2024.06.002","url":null,"abstract":"<div><div><span>This study proposes a modified VAR-deGARCH model, denoted by M-VAR-deGARCH, for modeling asynchronous multivariate financial time series<span><span> with GARCH effects and simultaneously accommodating the latest market information. A variational Bayesian (VB) procedure is developed for the M-VAR-deGARCH model to infer structure selection and parameter estimation. We conduct extensive simulations and empirical studies to evaluate the fitting and forecasting performance of the M-VAR-deGARCH model. The simulation results reveal that the proposed VB procedure produces satisfactory selection performance. In addition, our empirical studies find that the latest market information in </span>Asia can provide helpful information to predict market trends in Europe and </span></span>South Africa, especially when momentous events occur.</div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 1","pages":"Pages 345-360"},"PeriodicalIF":6.9,"publicationDate":"2024-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705208","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 : 2024-06-19DOI: 10.1016/j.ijforecast.2024.05.005
Chaya Weerasinghe, Rubén Loaiza-Maya, Gael M. Martin, David T. Frazier
Approximate Bayesian Computation (ABC) has gained popularity as a method for conducting inference and forecasting in complex models, most notably those which are intractable in some sense. In this paper, we use ABC to produce probabilistic forecasts in state space models (SSMs). Whilst ABC-based forecasting in correctly-specified SSMs has been studied, the misspecified case has not been investigated. It is this case that we emphasize. We invoke recent principles of ‘focused’ Bayesian prediction, whereby Bayesian updates are driven by a scoring rule that rewards predictive accuracy; the aim being to produce predictives that perform well in that rule, despite misspecification. Two methods are investigated for producing the focused predictions. In a simulation setting, ‘coherent’ predictions are in evidence for both methods. That is, the predictive constructed using a particular scoring rule often predicts best according to that rule. Importantly, both focused methods typically produce more accurate forecasts than an exact but misspecified predictive, in particular when the degree of misspecification is marked. An empirical application to a truly intractable SSM completes the paper.
{"title":"ABC-based forecasting in misspecified state space models","authors":"Chaya Weerasinghe, Rubén Loaiza-Maya, Gael M. Martin, David T. Frazier","doi":"10.1016/j.ijforecast.2024.05.005","DOIUrl":"10.1016/j.ijforecast.2024.05.005","url":null,"abstract":"<div><div>Approximate Bayesian Computation (ABC) has gained popularity as a method for conducting inference and forecasting in complex models, most notably those which are intractable in some sense. In this paper, we use ABC to produce probabilistic forecasts in state space models (SSMs). Whilst ABC-based forecasting in correctly-specified SSMs has been studied, the misspecified case has not been investigated. It is this case that we emphasize. We invoke recent principles of ‘focused’ Bayesian prediction, whereby Bayesian updates are driven by a scoring rule that rewards predictive accuracy; the aim being to produce predictives that perform well in that rule, despite misspecification. Two methods are investigated for producing the focused predictions. In a simulation setting, ‘coherent’ predictions are in evidence for both methods. That is, the predictive constructed using a particular scoring rule often predicts best according to that rule. Importantly, both focused methods typically produce more accurate forecasts than an exact but misspecified predictive, in particular when the degree of misspecification is marked. An empirical application to a truly intractable SSM completes the paper.</div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 1","pages":"Pages 270-289"},"PeriodicalIF":6.9,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705211","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