Forecasting Tourism Demand With a New Time-Varying Forecast Averaging Approach

2021 ◽  
pp. 004728752110612
Author(s):  
Yuying Sun ◽  
Jian Zhang ◽  
Xin Li ◽  
Shouyang Wang
Keyword(s):  
Structural Changes ◽  
Model Averaging ◽  
Structural Instability ◽  
Time Varying ◽  
Forecast Combination ◽  
Tourism Demand ◽  
Single Model ◽  
Forecasting Accuracy ◽  
Combination Methods ◽  
Out Of Sample

Existing research has shown that combination can effectively improve tourism forecasting accuracy compared with single model. However, the model uncertainty and structural instability in combination for out-of-sample tourism forecasting may influence the forecasting performance. This paper proposes a novel forecast combination approach based on time-varying jackknife model averaging (TVJMA), which can more efficiently handle structural changes and nonstationary trends in tourism data. Using Hong Kong tourism demand from five major tourism source regions as an empirical study, we investigate whether our proposed nonparametric TVJMA-based approach can improve tourism forecasting accuracy further. Empirical results show that the proposed TVJMA-based approach outperforms other competitors including single model and three combination methods in most cases. Findings indicate the outstanding performance of our method is robust to various forecasting horizons and different estimation periods.

scholarly journals Optimal forecasting accuracy using Lp-norm combination

METRON ◽  
2021 ◽  
Author(s):  
Massimiliano Giacalone
Keyword(s):  
Real Data ◽  
Optimization Techniques ◽  
Combination Method ◽  
Forecast Combination ◽  
Forecasting Accuracy ◽  
Lp Norm ◽  
Combination Methods ◽  
Historical Series ◽  
Non Gaussian ◽  
Standard Regression

AbstractA well-known result in statistics is that a linear combination of two-point forecasts has a smaller Mean Square Error (MSE) than the two competing forecasts themselves (Bates and Granger in J Oper Res Soc 20(4):451–468, 1969). The only case in which no improvements are possible is when one of the single forecasts is already the optimal one in terms of MSE. The kinds of combination methods are various, ranging from the simple average (SA) to more robust methods such as the one based on median or Trimmed Average (TA) or Least Absolute Deviations or optimization techniques (Stock and Watson in J Forecast 23(6):405–430, 2004). Standard regression-based combination approaches may fail to get a realistic result if the forecasts show high collinearity in several situations or the data distribution is not Gaussian. Therefore, we propose a forecast combination method based on Lp-norm estimators. These estimators are based on the Generalized Error Distribution, which is a generalization of the Gaussian distribution, and they can be used to solve the cases of multicollinearity and non-Gaussianity. In order to demonstrate the potential of Lp-norms, we conducted a simulated and an empirical study, comparing its performance with other standard-regression combination approaches. We carried out the simulation study with different values of the autoregressive parameter, by alternating heteroskedasticity and homoskedasticity. On the other hand, the real data application is based on the daily Bitfinex historical series of bitcoins (2014–2020) and the 25 historical series relating to companies included in the Dow Jonson, were subsequently considered. We showed that, by combining different GARCH and the ARIMA models, assuming both Gaussian and non-Gaussian distributions, the Lp-norm scheme improves the forecasting accuracy with respect to other regression-based combination procedures.

scholarly journals Equity Premium Prediction with Structural Breaks: A Two-Stage Forecast Combination Approach

2019 ◽  
Vol 11 (12) ◽  
pp. 50
Author(s):  
Anwen Yin
Keyword(s):  
Structural Breaks ◽  
Equity Premium ◽  
Model Averaging ◽  
Forecast Combination ◽  
Two Stage ◽  
Explicit Theory ◽  
Out Of Sample ◽  
Combination Approach ◽  
Averaged Models ◽  
Averaged Model

This paper introduces a two-stage out-of-sample predictive model averaging approach to forecasting the U.S. market equity premium. In the first stage, we combine the break and stable specifications for each candidate model utilizing schemes such as Mallows weights to account for the presence of structural breaks. Next, we combine all previously averaged models by equal weights to address the issue of model uncertainty. Our empirical results show that the double-averaged model can deliver superior statistical and economic gains relative to not only the historical average but also the simple forecast combination when forecasting the equity premium. Moreover, our approach provides an explicit theory-based linkage between forecast combination and structural breaks which distinguishes this study from other closely related works.

FORECASTING REALIZED VOLATILITY DYNAMICALLY BASED ON ADJUSTED DYNAMIC MODEL AVERAGING (AMDA) APPROACH: EVIDENCE FROM CHINA’S STOCK MARKET

2019 ◽  
Vol 14 (04) ◽  
pp. 1950022
Author(s):  
PING YUAN
Keyword(s):  
Dynamic Model ◽  
Model Averaging ◽  
Realized Volatility ◽  
Time Varying ◽  
Alternative Strategies ◽  
Forecasting Accuracy ◽  
Time Varying Parameters ◽  
Constant Coefficients ◽  
The Individual ◽  
Dynamic Model Averaging

In this study, we forecast the realized volatility of the CSI 300 index using the heterogeneous autoregressive model for realized volatility (HAR-RV) and its various extensions. Our models take into account the time-varying property of the models’ parameters and the volatility of realized volatility. The adjusted dynamic model averaging (ADMA) approach, is used to combine the forecasts of the individual models. Our empirical results suggest that ADMA can generate more accurate forecasts than DMA method and alternative strategies. Models that use time-varying parameters have greater forecasting accuracy than models that use the constant coefficients.

scholarly journals Technical note: Combining quantile forecasts and predictive distributions of streamflows

2017 ◽  
Vol 21 (11) ◽  
pp. 5493-5502 ◽  
Author(s):  
Konrad Bogner ◽  
Katharina Liechti ◽  
Massimiliano Zappa
Keyword(s):  
Water Resource Management ◽  
Bayesian Model Averaging ◽  
Model Averaging ◽  
Relevant Information ◽  
Technical Note ◽  
Decision Makers ◽  
Forecast Combination ◽  
Predictive Distributions ◽  
Combination Methods ◽  
Probabilistic Forecasts

Abstract. The enhanced availability of many different hydro-meteorological modelling and forecasting systems raises the issue of how to optimally combine this great deal of information. Especially the usage of deterministic and probabilistic forecasts with sometimes widely divergent predicted future streamflow values makes it even more complicated for decision makers to sift out the relevant information. In this study multiple streamflow forecast information will be aggregated based on several different predictive distributions, and quantile forecasts. For this combination the Bayesian model averaging (BMA) approach, the non-homogeneous Gaussian regression (NGR), also known as the ensemble model output statistic (EMOS) techniques, and a novel method called Beta-transformed linear pooling (BLP) will be applied. By the help of the quantile score (QS) and the continuous ranked probability score (CRPS), the combination results for the Sihl River in Switzerland with about 5 years of forecast data will be compared and the differences between the raw and optimally combined forecasts will be highlighted. The results demonstrate the importance of applying proper forecast combination methods for decision makers in the field of flood and water resource management.

scholarly journals Technical Note: Combining Quantile Forecasts and Predictive Distributions of Stream-flows

2017 ◽  
Author(s):  
Konrad Bogner ◽  
Katharina Liechti ◽  
Massimiliano Zappa
Keyword(s):  
Stream Flow ◽  
Bayesian Model Averaging ◽  
Model Averaging ◽  
Relevant Information ◽  
Technical Note ◽  
Decision Makers ◽  
Forecast Combination ◽  
Predictive Distributions ◽  
Combination Methods ◽  
Probabilistic Forecasts

Abstract. The enhanced availability of many different hydro-meteorological modelling and forecasting systems raises the issue of how to optimally combine this great deal of information. Especially the usage of deterministic and probabilistic forecasts with sometimes widely divergent predicted future stream-flow values makes it even more complicated for decision makers to sift out the relevant information. In this study multiple stream-flow forecast information will be aggregated based on several different predictive distributions, resp. quantile forecasts. For this combination the Bayesian Model Averaging (BMA) approach, the Nonhomogeneous Gaussian Regression (NGR), also known as Ensemble Model Output Statistic (EMOS) model and a novel method called Beta transformed Linear Pooling (BLP) will be applied. By the help of the Quantile Score (QS) and the Continuous Ranked Probability Score (CRPS), the combination results for the Sihl river in Switzerland with about five years of forecast data will be compared and the differences between the raw and the optimally combined forecasts will be highlighted. The results demonstrate the importance of applying proper forecast combination methods for decision makers in the field of flood and water resources management.

Optimal Hedge Ratio and Hedging Effectiveness in Stock Futures Market: Evidence from National Stock Exchange, India

2019 ◽  
Vol 118 (3) ◽  
pp. 137-152
Author(s):  
A. Shanthi ◽  
R. Thamilselvan
Keyword(s):  
Banking Sector ◽  
Stock Exchange ◽  
Research Work ◽  
Futures Market ◽  
Least Square ◽  
Time Varying ◽  
Hedge Ratio ◽  
Hedging Effectiveness ◽  
Out Of Sample ◽  
Optimal Hedge

The major objective of the study is to examine the performance of optimal hedge ratio and hedging effectiveness in stock futures market in National Stock Exchange, India by estimating the following econometric models like Ordinary Least Square (OLS), Vector Error Correction Model (VECM) and time varying Multivariate Generalized Autoregressive Conditional Heteroscedasticity (MGARCH) model by evaluating in sample observation and out of sample observations for the period spanning from 1st January 2011 till 31st March 2018 by accommodating sixteen stock futures retrieved through www.nseindia.com by considering banking sector of Indian economy. The findings of the study indicate both the in sample and out of sample hedging performances suggest the various strategies obtained through the time varying optimal hedge ratio, which minimizes the conditional variance performs better than the employed alterative models for most of the underlying stock futures contracts in select banking sectors in India. Moreover, the study also envisage about the model selection criteria is most important for appropriate hedge ratio through risk averse investors. Finally, the research work is also in line with the previous attempts Myers (1991), Baillie and Myers (1991) and Park and Switzer (1995a, 1995b) made in the US markets

Economic Institutions and Growth Nexus: The Role of Governance and Democratic Institutions—Evidence from Time Varying Parameters’ (TVPs) Models

2016 ◽  
Vol 55 (4I-II) ◽  
pp. 675-688
Author(s):  
Ghulam Murtaza ◽  
Muhammad Zahir Faridi
Keyword(s):  
Structural Changes ◽  
Jel Classification ◽  
Economic Institutions ◽  
Time Varying ◽  
Democratic Institutions ◽  
Main Hypothesis ◽  
Dynamic Relationship ◽  
Rolling Window

The present study has investigated the channels through which the linkage between economic institutions and growth is gauged, by addressing the main hypothesis of the study that whether quality of governance and democratic institutions set a stage for economic institutions to promote the long-term growth process in Pakistan. To test the hypothesis empirically, our study models the dynamic relationship between growth and economic institutions in a time varying framework in order to capture institutional developments and structural changes occurred in the economy of Pakistan over the years. Study articulates that, along with some customary specifics, the quality of government and democracy are the substantial factors that affect institutional quality and ultimately cause to promote growth in Pakistan. JEL Classification: O40; P16; C14; H10 Keywords: Economic Institutions, Growth, Governance and Democracy, Rolling Window Two-stage Least Squares, Pakistan

scholarly journals The Dynamic Impacts of the COVID-19 Pandemic on Log Prices in China: An Analysis Based on the TVP-VAR Model

Forests ◽  
2021 ◽  
Vol 12 (4) ◽  
pp. 449
Author(s):  
Chenlu Tao ◽  
Gang Diao ◽  
Baodong Cheng
Keyword(s):  
Exchange Rate ◽  
Structural Changes ◽  
Raw Materials ◽  
Supply And Demand ◽  
Oil Prices ◽  
Control Measures ◽  
Var Model ◽  
Time Varying ◽  
Wood Industry ◽  
The Impact

China’s wood industry is vulnerable to the COVID-19 pandemic since wood raw materials and sales of products are dependent on the international market. This study seeks to explore the speed of log price recovery under different control measures, and to perhaps find a better way to respond to the pandemic. With the daily data, we utilized the time-varying parameter autoregressive (TVP-VAR) model, which can incorporate structural changes in emergencies into the model through time-varying parameters, to estimate the dynamic impact of the pandemic on log prices at different time points. We found that the impact of the pandemic on oil prices and Renminbi exchange rate is synchronized with the severity of the pandemic, and the ascending in the exchange rate would lead to an increase in log prices, while oil prices would not. Moreover, the impulse response in June converged faster than in February 2020. Thus, partial quarantine is effective. However, the pandemic’s impact on log prices is not consistent with changes of the pandemic. After the pandemic eased in June 2020, the impact of the pandemic on log prices remained increasing. This means that the COVID-19 pandemic has long-term influences on the wood industry, and the work resumption was not smooth, thus the imbalance between supply and demand should be resolved as soon as possible. Therefore, it is necessary to promote the development of the domestic wood market and realize a “dual circulation” strategy as the pandemic becomes a “new normal”.

scholarly journals Development of the reproduction number from coronavirus SARS-CoV-2 case data in Germany and implications for political measures

BMC Medicine ◽  
2021 ◽  
Vol 19 (1) ◽  
Author(s):  
Sahamoddin Khailaie ◽  
Tanmay Mitra ◽  
Arnab Bandyopadhyay ◽  
Marta Schips ◽  
Pietro Mascheroni ◽  
...  
Keyword(s):  
Structural Changes ◽  
Reproduction Number ◽  
National Level ◽  
Transmission Dynamics ◽  
Federal State ◽  
Parameter Estimates ◽  
Time Varying ◽  
Short Term ◽  
Robert Koch Institute ◽  
Federal States

Abstract Background SARS-CoV-2 has induced a worldwide pandemic and subsequent non-pharmaceutical interventions (NPIs) to control the spread of the virus. As in many countries, the SARS-CoV-2 pandemic in Germany has led to a consecutive roll-out of different NPIs. As these NPIs have (largely unknown) adverse effects, targeting them precisely and monitoring their effectiveness are essential. We developed a compartmental infection dynamics model with specific features of SARS-CoV-2 that allows daily estimation of a time-varying reproduction number and published this information openly since the beginning of April 2020. Here, we present the transmission dynamics in Germany over time to understand the effect of NPIs and allow adaptive forecasts of the epidemic progression. Methods We used a data-driven estimation of the evolution of the reproduction number for viral spreading in Germany as well as in all its federal states using our model. Using parameter estimates from literature and, alternatively, with parameters derived from a fit to the initial phase of COVID-19 spread in different regions of Italy, the model was optimized to fit data from the Robert Koch Institute. Results The time-varying reproduction number (Rt) in Germany decreased to <1 in early April 2020, 2–3 weeks after the implementation of NPIs. Partial release of NPIs both nationally and on federal state level correlated with moderate increases in Rt until August 2020. Implications of state-specific Rt on other states and on national level are characterized. Retrospective evaluation of the model shows excellent agreement with the data and usage of inpatient facilities well within the healthcare limit. While short-term predictions may work for a few weeks, long-term projections are complicated by unpredictable structural changes. Conclusions The estimated fraction of immunized population by August 2020 warns of a renewed outbreak upon release of measures. A low detection rate prolongs the delay reaching a low case incidence number upon release, showing the importance of an effective testing-quarantine strategy. We show that real-time monitoring of transmission dynamics is important to evaluate the extent of the outbreak, short-term projections for the burden on the healthcare system, and their response to policy changes.

Sign in / Sign up

Export Citation Format

Share Document