DETEKCE A KOREKCE PŘEDVELIKONOČNÍHO A VELIKONOČNÍHO EFEKTU
Detection and correction of the pre-Easter and Easter effect
Languages of publication
This study compares eight different alternatives of detection and correction of Easter and pre-Easter effect. These are two calendar effects, which are usually subtracted from the time series analysed before its decomposition into trend/ cycle, seasonality and irregular part. The proposed alternatives differ by the duration of these effects and are compared using regression coefficients, information criteria and recursive estimation. Data of Index of industrial production of Czech Republic, Poland and Slovak Republic and three north-Spanish provinces data of Index of industrial production of Czech Republic, Poland and Slovak Republic and three north-Spanish provinces are used in the empirical application. The conclusions, which can be drawn from the study and which are based on very different data, are that the Easter effect should be always detected and corrected separately and not together with another calendar effect.
472 – 487
Publication order reference