This paper investigates the possibility of improving predictive ability a tourism demand model with meteorological explanatory variables. The authors use as case study monthly British for Balearic Islands (Spain). For this purpose, transfer function and causal artificial neural network are fitted. results compared those obtained by non-causal methods: an ARIMA autoregressive network. indicate that incorporating variables can increase power, although most accurate prediction is using – specifically,

Abstract Domestic tourism represents a large share of the total volume in Spain, but it is still an under‐researched topic. This study focuses on determinants domestic flows Spain at provincial level. The prior assumption that demand may be affected by specific local conditions previous studies, mostly based more aggregate data, would hardly capture. A gravity model and various spatial econometric models are estimated assuming alternative weighting matrices. Results suggest income relative...

Creative tourism is a novel segment of the market that may turn into great opportunity for small cities to attract visitors. Thus, it can be possible economic and social driver local development. Despite its potentiality, not much empirical research has been conducted explore specific strengths weaknesses developing creative in cities, probably due lack reliable data. Our study aims fill this gap by using C3 Index, composite indicator developed Joint Research Center-European Commission, as...

A novel approach is employed to investigate the predictability of weekly data on euro/dollar, British pound/dollar, Deutsche mark/dollar, Japanese yen/dollar, French franc/dollar and Canadian dollar/dollar exchange rates. functional search procedure based Darwinian theories natural evolution survival, called genetic algorithms (hereinafter GA), was used find an analytical function that best approximates time variability studied In all cases, mathematical models found by GA predict slightly...

The objective of this article is to predict, both in sample and out sample, the consumer price index (CPI) US economy based on monthly data covering period 1980:1–2013:12, using a variety linear (random walk (RW), autoregressive (AR) seasonal integrated moving average (SARIMA)) nonlinear (artificial neural network (ANN) genetic programming (GP)) univariate models. Our results show that, while SARIMA model superior relative other models, as it tends produce smaller forecast errors;...

This study empirically compares domestic tourists’ behavior before and after the Covid-19 outbreak. Specifically, official data are used to characterize travel of residents in Spain who traveled through this country for reasons leisure, recreation, vacations 2019 2020. A discrete choice model is employed unravel main variables that influence decision being an inter-regional traveler. The bootstrap p-value method detect significant changes marginal effect different estimation results...

This paper investigates the feasibility of using different generalizations nearest neighbour method in a tourism forecasting problem. The is widely employed fields research but, inexplicably, it practically unknown forecasting. analysis centred not only knowing exact value arrivals (point prediction), but also anticipating direction sign movement (sign prediction). Furthermore, this study offers further evidence on subject scarcely treated economics: searching predictable non-linear...

This study explores the forecasting ability of two powerful non-linear computational methods: artificial neural networks and genetic programming. We use as a case monthly international tourism demand in Spain, approximated by number tourist arrivals overnight stays. The results reveal that methods achieve slightly better predictions than those obtained traditional technique, seasonal autoregressive integrated moving average (SARIMA) approach. slight improvement was close to being...

CR Climate Research Contact the journal Facebook Twitter RSS Mailing List Subscribe to our mailing list via Mailchimp HomeLatest VolumeAbout JournalEditorsSpecials 43:207-214 (2010) - DOI: https://doi.org/10.3354/cr00931 Statistical relationships between North Atlantic Oscillation and international tourism demand in Balearic Islands, Spain Marcos Álvarez-Díaz1,*, Mª Soledad Otero Giráldez2, Manuel González-Gómez2 1Department of Economics, 2Department Applied University Vigo,...

The main goal of this study is to estimate the price and income elasticity demand for tourism Spain. This estimation done separately major international source markets Spain: Germany, UK, Italy Netherlands. For purpose, authors use autoregressive distributed lag (ARDL) approach cointegration bootstrap method construct empirical confidence intervals each estimate. results reveal that in all countries studied has a similar elasticity, which approximately unitary. However, there an important...

Exchange rates forecasters usually assume that local methods (nearest neighbour) dominate the global ones (neural networks or genetic programming, for example). In this article, first, we use different generalizations of standard nearest neighbours to predict dynamic evolution Yen/US$ and Pound Sterling/US$ exchange one-period ahead. Second, compare our results with those employing such as neural networks, data fusion evolutionary networks. Finally, find out existence predictable structures...

Understanding the complex process of climate change implies knowledge all possible determinants CO2 emissions. This paper studies influence several institutional on emissions, clarifying which variables are relevant to explain this influence. For aim, Genetic Programming and Artificial Neural Networks used find an optimal functional relationship between emissions a set historical, economic, geographical, religious, social variables, considered as good approximation quality country. Besides...

In this article we use a generalization of the standard nearest neighbours, called local regression (LR), to study predictability yen/US$ and pound sterling/US$ exchange rates. We also compare our results with those previously obtained global methods such as neural networks, genetic programming, data fusion evolutionary networks. want verify if can generalize rate forecasting problem belief that beat ones.