De Mello, Maria M.M.Q.
Theoretical and empirical issues in tourism demand analysis.
PhD thesis, University of Nottingham.
The majority of empirical studies of tourism analysis use a static single equation approach to model the demand for tourism of one origin for one or more destination countries. The examination of such studies generally shows that the economic interpretation and policy implications drawn as conclusions are based on mis-specified models, invalid estimation and inference procedures, inconsistent estimates and poor forecasting performance. Static single equation models of tourism demand tend to neglect interdependencies among destinations, ignore nonstationarity, overlook dynamics and, generally, disregard economic theory. Empirical specifications constrained by these flaws are bound to generate biased and inconsistent estimates upon which no reliable economic analysis or policy implication can be based.
In an analytical context that focuses on the UK tourism demand for France, Spain and Portugal in the period 1969-1997, the main objective of this thesis is to demonstrate that consistent elasticities' estimates and reliable forecasts can be obtained from empirical models which are based on the principles of economic theory, and specified and rigorously tested within the rules of sound econometric methodology. The alternative models estimated in chapters 4 to 7 include error-correction autoregressive distributed lag models (ARDL), static and dynamic almost ideal demands systems (AIDS) and cointegrated vector autoregressive models (VAR).
The main findings that emerge from the study are as follow. The battery of diagnostic tests applied to the dynamic error-correction ARDL models provide sufficient evidence to classify them as statistically robust, structurally stable and well-defined specifications. The evidence obtained for the AIDS and VAR systems indicates them as data-coherent and theoretically-consistent models, complying with the utility maximisation hypotheses. The similarity, across models, of the estimates of the long-run structural parameters and the accuracy of the forecasts they provide further support the reliability of these models for explaining and predicting the UK tourism demand behaviour, in contrast to the static single equations estimated in chapter 3. The specifications of chapters 4 to 7 can easily be extended, without loss of generality, to more origins and destinations and can be adapted to alternative contexts such as the demand for specific regions within a country, specific resorts within a region or even specific types of tourism products such as accommodation or leisure facilities, within a local area.
Thesis (University of Nottingham only)
||G Geography. Anthropology. Recreation > G Geography (General)
||UK Campuses > Faculty of Social Sciences, Law and Education > Nottingham University Business School
||11 May 2010 12:15
||16 Sep 2016 12:44
Actions (Archive Staff Only)