Title: The impact of moving holidays on official statistics time series
Authors: Bethan Russ - Office for National Statistics (United Kingdom) [presenting]
Tariq Aziz - Office for National Statistics (United Kingdom)
Abstract: The Office for National Statistics (ONS) is the UKs largest independent producer of official statistical and the recognised national statistical institute of the UK. The Time Series Analysis Branch (TSAB) within the ONS is responsible for the seasonal adjustment and analysis of tens of thousands of economic and social ONS time series. A major challenge faced when seasonally adjusting time series is accounting for annual events that move dates from one calendar year to the next, for example, Easter. If these events are not accounted for appropriately it will impact on the estimation of seasonal factors, and leave systematic calendar related effects in the seasonally adjusted series. Currently TSAB tests for Easter effects and, if identified, estimates and removes them as part of seasonal adjustment. This method assumes that daily activity changes by a fixed amount or proportion for a given number of days before Easter Sunday and remains at this level until Easter Saturday. There are other moving holidays celebrated in the UK, which may have an impact on time series despite not being public holidays. These are Chinese New Year, Ramadan, Eid al-Fitr and Eid al-Adha. Currently these holidays are not adjusted for in any seasonally adjusted time series published by the ONS. TSAB has undertaken research to test alternative windows for Easter effects and whether other moving holidays have identifiable effects on ONS time series.