CALENDAR EFFECTS IN MONTHLY TIME SERIES MODELS

1. Introduction In the 1960s the attempts to describe an economy by large macroeconometric models were under heavy critique. These models with hundreds of macroeconomic variables and equations, could track the data very well over the historical period where the model parameters are estimated but often performed poorly when are used for out-of-sample forecasting. Part of the disillusionment with these efforts was the discovery that univariate time series models with low order autoregressive and…

Calendar effects in monthly time series models

It is not unusual for the level of a monthly economic time series, such as industrial production, retail and wholesale sales, monetary aggregates, telephone calls or road accidents, to be influenced by calendar effects. Such effects arise when changes occur in the level of activity resulting from differences in the composition of calendar between years. The two main sources of calendar effects are trading day variations and moving festivals. Ignoring such calendar effects will lead to substantial distortions in the identification stage of time series modeling. Therefore, it is mandatory to introduce calendar effects, when they are present in a time series, as the component of the model which one wants to estimate.