Autoregressive conditional heteroscedasticity in daily wind speed measurements

Tol, Richard S J (1997) Autoregressive conditional heteroscedasticity in daily wind speed measurements. Theoretical and Applied Climatology, 56 (1-2). pp. 113-122. ISSN 0177-798X

Full text not available from this repository.


It is argued that the predictability of meteorological variables is not constant but shows regular variations. This is shown for the daily mean wind speeds and its meridional and zonal components at Shearwater, Canada, for the period 1963-1988. To capture this feature, a Generalised Auto Regressive Conditional Heteroscedastic model is proposed. In this model, the conditional variance of an observation depends linearly on the conditional variances of the previous observations and on the previous prediction errors. Here, conditional heteroscedasticity models are used which let the variance depend on previous prediction errors, in conjunction with an autoregressive model for the mean, using the Gamma distribution for the wind speed and the Normal distribution for its components. It is shown that these heteroscedastic models outperform their homoscedastic versions, and that heteroscedastic features are more clear in the wind speed component records.

Item Type: Article
Schools and Departments: University of Sussex Business School > Economics
Subjects: G Geography. Anthropology. Recreation > GE Environmental Sciences
H Social Sciences > HA Statistics
Related URLs:
Depositing User: Richard Tol
Date Deposited: 23 Apr 2012 10:19
Last Modified: 23 Apr 2012 10:19
📧 Request an update