Pooling in Tourism Demand Forecasting

2018 ◽  
Vol 58 (7) ◽  
pp. 1161-1174 ◽  
Author(s):  
Wen Long ◽  
Chang Liu ◽  
Haiyan Song
Keyword(s):  
Panel Data ◽  
Fixed Effects ◽  
Demand Forecasting ◽  
Spillover Effects ◽  
Ordinary Least Squares ◽  
Spatial Effects ◽  
Tourism Demand ◽  
Forecasting Accuracy ◽  
Demand Models ◽  
Forecasting Performance

This study investigates whether pooling can improve the forecasting performance of tourism demand models. The short-term domestic tourism demand forecasts for 341 cities in China using panel data (pooled) models are compared with individual ordinary least squares (OLS) and naïve benchmark models. The pooled OLS model demonstrates much worse forecasting performance than the other models. This indicates the huge heterogeneity of tourism across cities in China. A marked improvement with the inclusion of fixed effects suggests that destination features that stay the same or vary very little over time can explain most of the heterogeneity. Adding spatial effects to the panel data models also increases forecasting accuracy, although the improvement is small. The spatial distribution of spillover effects is drawn on a map and a spatial pattern is recognized. Finally, when both spatial and temporal effects are taken into account, pooling improves forecasting performance.

Decomposition Methods for Tourism Demand Forecasting: A Comparative Study

2021 ◽  
pp. 004728752110361
Author(s):  
Chengyuan Zhang ◽  
Mingchen Li ◽  
Shaolong Sun ◽  
Ling Tang ◽  
Shouyang Wang
Keyword(s):  
Decomposition Method ◽  
Demand Forecasting ◽  
Decomposition Methods ◽  
Tourism Demand ◽  
Forecasting Accuracy ◽  
Forecasting Methods ◽  
Mode Decomposition ◽  
Forecasting Performance ◽  
Intrinsic Complexity ◽  
Comprehensive Comparison

Decomposition methods are extensively used for processing the complex patterns of tourism demand data. Given tourism demand data’s intrinsic complexity, it is critical to theoretically understand how different decomposition methods provide solutions. However, a comprehensive comparison of decomposition methods in tourism demand forecasting is still lacking. Hence, this study systematically investigates the forecasting performance of decomposition methods in tourism demand. Nine popular decomposition methods and six forecasting methods are employed, and their forecasting performance is compared. With Hong Kong visitor arrivals from eight major sources as a sample, three main conclusions are obtained from empirical results. First, all the decomposition methods generally outperform benchmark at all horizons, in both the level and directional forecasting. Second, decomposition methods can be divided into four categories based on forecasting accuracy. Finally, variational mode decomposition method is consistently superior to other eight decomposition methods and can provide the best forecasts in all cases.

scholarly journals Tourism Demand Modelling and Forecasting: A Review of Literature

2021 ◽  
Vol 10(4) (10(4)) ◽  
pp. 1370-1393
Author(s):  
Musonera Abdou ◽  
Edouard Musabanganji ◽  
Herman Musahara
Keyword(s):  
Time Series ◽  
Spatial Regression ◽  
Demand Forecasting ◽  
Tourism Demand ◽  
New Developments ◽  
Forecasting Accuracy ◽  
Forecasting Models ◽  
Forecasting Performance ◽  
Modelling And Forecasting ◽  
Forecasting Techniques

This research examines 145 key papers from 1979 to 2020 in order to gain a better sense of how tourism demand forecasting techniques have changed over time. The three types of forecasting models are econometric, time series, and artificial intelligence (AI) models. Econometric and time series models that were already popular in 2005 maintained their popularity, and were increasingly used as benchmark models for forecasting performance assessment and comparison with new models. In the last decade, AI models have advanced at an incredible rate, with hybrid AI models emerging as a new trend. In addition, some new developments in the three categories of models, such as mixed frequency, spatial regression, and combination and hybrid models have been introduced. The main conclusions drawn from historical comparisons forecasting methods are that forecasting models have become more diverse, that these models have been merged, and that forecasting accuracy has improved. Given the complexities of predicting tourism demand, there is no single approach that works well in all circumstances, and forecasting techniques are still evolving.

scholarly journals Tail-Heaviness, Asymmetry, and Profitability Forecasting by Quantile Regression

2020 ◽  
Author(s):  
Hui Tian ◽  
Andrew Yim ◽  
David P. Newton
Keyword(s):  
Quantile Regression ◽  
Forecast Error ◽  
Simulated Data ◽  
Ordinary Least Squares ◽  
Shape Effect ◽  
Forecasting Accuracy ◽  
Forecasting Performance ◽  
Cash Flow Forecasting ◽  
Positive Effect ◽  
Better Than

We show that quantile regression is better than ordinary-least-squares (OLS) regression in forecasting profitability for a range of profitability measures following the conventional setup of the accounting literature, including the mean absolute forecast error (MAFE) evaluation criterion. Moreover, we perform both a simulated-data and an archival-data analysis to examine how the forecasting performance of quantile regression against OLS changes with the shape of the profitability distribution. Considering the MAFE and mean squared forecast error (MSFE) criteria together, we see that the quantile regression is more accurate relative to OLS when the profitability to be forecast has a heavier-tailed distribution. In addition, the asymmetry of the profitability distribution has either a U-shape or an inverted-U-shape effect on the forecasting accuracy of quantile regression. An application of the distributional shape analysis framework to cash flow forecasting demonstrates the usefulness of the framework beyond profitability forecasting, providing additional empirical evidence on the positive effect of tail-heaviness and supporting the notion of an inverted-U-shape effect of asymmetry. This paper was accepted by Shiva Rajgopal, accounting.

Does digital proximity between countries impact entrepreneurship?

Info ◽  
2015 ◽  
Vol 17 (5) ◽  
pp. 46-65 ◽  
Author(s):  
Maria Veronica Alderete
Keyword(s):  
Panel Data ◽  
Spatial Dependence ◽  
Fixed Effects ◽  
Spatial Models ◽  
Negative Influence ◽  
Entrepreneurial Activity ◽  
Spatial Effects ◽  
Content Type ◽  
Spatial Spillovers ◽  
Information And Communication

Purpose – This paper aims to determine if there is a spatial dependence in the entrepreneurial activity among countries. The existence of a “digital proximity” could explain the spatial pattern of entrepreneurship. Design/methodology/approach – This question is empirically addressed by using a five-period, 2008-2012, panel data for 35 countries. A spatial fixed effects panel data model is estimated by using the total entrepreneurial activity published by the global entrepreneurship monitor as the dependent variable. Findings – A significant negative influence of the digital proximity on the entrepreneurial activity is observed. Mobile broadband (MB) direct effect is positive while the indirect effect (the spatial spillovers) is negative, leading to a negative total effect on the total entrepreneurial activity. This result is contrary to non-spatial models’ results. Besides, a higher MB penetration in a country would lead to a competitive advantage fostering its opportunities for entrepreneurship, but reducing those of its neighbours’. Originality/value – This paper examines the relationship between information and communication technology (ICT) and entrepreneurship, by introducing the spatial effects is the main contribution. This paper expands the scant literature on the ICT impact on entrepreneurship. Results obtained support policies towards enforcing innovation, education and reducing entry regulations for encouraging entrepreneurship. Meanwhile, MB policies could counteract the entrepreneurial policies’ results due to the spatial dependence.

Estimating the Impact of Avian Flu on International Tourism Demand Using Panel Data

2009 ◽  
Vol 15 (3) ◽  
pp. 501-511 ◽  
Author(s):  
Hsiao-I Kuo ◽  
Chia-Lin Chang ◽  
Bing-Wen Huang ◽  
Chi-Chung Chen ◽  
Michael McAleer
Keyword(s):  
Panel Data ◽  
Pandemic Influenza ◽  
Fixed Effects ◽  
Data Models ◽  
International Tourism ◽  
Panel Data Models ◽  
Tourism Demand ◽  
Avian Flu ◽  
Potential Risks ◽  
The Impact

This paper investigates the impacts of avian flu on global and Asian tourism using panel data procedures. Both static and dynamic fixed effects panel data models are adopted to estimate the impacts of this infectious disease. The empirical results from static and dynamic fixed effects panel data models are consistent and indicate that the number of affected poultry outbreaks has significant impacts on the international tourism of global and Asian affected countries. The high mortality rate among humans, the potential of a global flu pandemic and some media frenzy with hype and speculation might adversely affect the images of these infected destinations as a safe tourist destination. Moreover, it was found that the average damage to Asian tourism was more serious, which might have been induced by an ineffective suppression in numerous Asian infected countries. In addition, Asia was the earliest affected region and the area infected most seriously by avian flu, both in humans and in poultry. Since the potential risks and damage arising from avian flu and the subsequent pandemic influenza are much greater than for previous diseases, the need to take necessary precautions in the event of an outbreak of avian flu and pandemic influenza warrants further attention and action in modelling and managing international tourism demand and risk.

The Impact of Population Aging on Economic Growth: Panel Data Evidence from Middle East Countries

2021 ◽  
pp. 67-86
Author(s):  
Abdullah Abdulaziz Bawazir ◽  
Mohamed Aslam ◽  
Ahmad Farid Osman
Keyword(s):  
Economic Growth ◽  
Panel Data ◽  
Middle East ◽  
Fixed Effects ◽  
Population Aging ◽  
Developed Countries ◽  
Ordinary Least Squares ◽  
Dependency Ratio ◽  
Middle East Countries ◽  
The Developed Countries

This study examines the relationship between population aging and economic growth in a panel of 10 selected Middle East countries for the period of 1996–2016. For this purpose, this study uses two different measures of population aging, namely population aged 65 and over and old dependency ratio, to investigate their impacts on economic growth. The study utilizes the three alternative models of static panel data comprised of the pooled ordinary least squares, random effects, and fixed effects. The results of the robust fixed effects model indicate that the population aged 65 and over and the old dependency ratio have a positive effect on economic growth. The finding supports the argument indicating that an aging population does not necessarily adversely affect economic growth in the developing countries as it does in the developed countries. Therefore, the elderly population is not a matter of concern for the Middle East and the mechanisms through which the effect can take place are savings behavior and human capital accumulation of the individuals.

scholarly journals Let’s Talk About Fixed Effects: Let’s Talk About All the Good Things and the Bad Things

2020 ◽  
Vol 72 (2) ◽  
pp. 289-299
Author(s):  
Matthias Collischon ◽  
Andreas Eberl
Keyword(s):  
Panel Data ◽  
Least Squares ◽  
Fixed Effects ◽  
Regression Models ◽  
Ordinary Least Squares

Abstract With the broader availability of panel data, fixed effects (FE) regression models are becoming increasingly important in sociology. However, in some studies the potential pitfalls of these models may be ignored, and common critiques of FE models may not always be applicable in comparison to other methods. This article provides an overview of linear FE models and their pitfalls for applied researchers. Throughout the article, we contrast FE and classical pooled ordinary least squares (OLS) models. We argue that in most cases FE models are at least as good as pooled OLS models. Therefore, we encourage scholars to use FE models if possible. Nevertheless, the limitations of FE models should be known and considered.

scholarly journals The Determinants of Economic Growth in CEMAC through a Panel Data Approach

2016 ◽  
Vol 4 (2) ◽  
pp. 483
Author(s):  
Nzingoula Gildas Crepin
Keyword(s):  
Economic Growth ◽  
Panel Data ◽  
Fixed Effects ◽  
Good Governance ◽  
Generalized Method Of Moments ◽  
Central Africa ◽  
Ordinary Least Squares ◽  
Fixed Effects Model ◽  
Main Determinants ◽  
Determinants Of Economic Growth

<div><p><em>This article highlights through a panel data approach the determinants of economic growth; observed over the last decade in the Economic and Monetary Community of Central Africa (CEMAC) and necessary to reach emerging economies stage. To do this, we essentially used Stata 12 software to come up with the results, and a panel data sample comprising six CEMAC member states, namely Congo, Cameroon, Gabon, Equatorial Guinea, Central African Republic and Chad, for the period ranging from 2000 to 2013. The results obtained after estimating ordinary least squares, fixed effects model, random effects model, generalized method of moments (GMM) and specification tests show that the best model to estimate these types of data is the fixed effects model. Besides, the main determinants of economic growth in CEMAC over that period are Foreign Direct Investment (FDI) and loans lending to the economy (LOAN). After estimation, FDI is found positive and significant on economic growth, while LOAN is significant and found negative maybe due to lack of good governance.</em></p></div>

Data hiding the truth for the last few years: a panel data analysis of crimes against women

2019 ◽  
Vol 5 (2) ◽  
pp. 132-143
Author(s):  
Aarthee Ragunathan ◽  
Ezhilmaran Devarasan
Keyword(s):  
Data Analysis ◽  
Panel Data ◽  
Violence Against Women ◽  
Fixed Effects ◽  
Panel Data Analysis ◽  
Ordinary Least Squares ◽  
Content Type ◽  
Thomson Reuters ◽  
Crime Types ◽  
Crimes Against Women

PurposeThe offence against femininity has not only destroyed India’s development but also its future. When it comes down to the most important factor like sex, the social evils like “sati” and “dowry” that had been plaguing our country have been banned in India. India is the most dangerous nation in regard to sexual violence against women, according to the summary of the Thomson Reuters Foundation, 2018. The purpose of this paper is to determine the relationship between the total populations of women with other different types of women crime in all states in India.Design/methodology/approachThis paper will review existing panel data analysis literature and apply this knowledge in finding the highly occurred women crimes in India. Using R software the following models are analysed: pooled ordinary least squares, fixed effects models and random effects models for analysing the women crimes in India.FindingsIn this paper, the authors identify that the fixed effects model is more appropriate for the analysis of women crimes in India.Practical implicationsViolence against women is a social, economic, developmental, legal, educational, human rights and health issue. This paper can be used to find the importance of women crime types. Moreover, the police or legal department can take actions according to the crime types.Originality/valueThere is a lack of literature considering the crimes against women. This will help the society to understand women crime types because the only type of violence that has received much attention by the media is rape. But, through our panel data analysis, we conclude that kidnapping, abduction and dowry death are the most occurred crimes against women in India.

Sign in / Sign up

Export Citation Format

Share Document