In the work ozone data from the Liossion monitoring station of the Athens/P
ERPA network are analysed. Data cover the months May to September for the p
eriod 1987-93. Four statistical models, three multiple regression and one A
RIMA (0,1,2), for the prediction of the daily maximum 1-hour ozone concentr
ations are developed. All models together, with a persistence forecast, are
evaluated and compared with the 1993's data, not used in the models develo
pment. Validation statistics were used to assess the relative accuracy of m
odels. Analysis, concerning the models' ability to forecast real ozone epis
odes, was also carried out. Two of the three regression models provide the
most accurate forecasts. The ARIMA model had the worst performance, even lo
wer than the persistence one. The forecast skill of a bivariate wind speed
and persistence based regression model for ozone episode days was found to
be quite satisfactory, with a detection rare of 73% and 60% for O-3 >180 mu
g m(-3) and O-3 >200 mu g m(-3), respectively.