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 effect...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.展开更多
The method of Winters(1960)is one of the most well-known forecasting methodologies in practice.The main reason behind its popularity is that it is easy to implement and can give quite effective and efficient results f...The method of Winters(1960)is one of the most well-known forecasting methodologies in practice.The main reason behind its popularity is that it is easy to implement and can give quite effective and efficient results for practice purposes.However,this method is not capable of capturing a pattern being emerged due to the simultaneous effects of two different asynchronous calendars,such as Gregorian and Hijri.We adapt this method in a way that it can deal with such patterns,and study its performance using a real dataset collected from a brewery factory in Turkey.With the same data set,we also provide a comparative performance analysis between our model and several forecasting models such as Winter’s(Winters 1960),TBAT(De Livera et al.2011),ETS(Hyndman et al.2002),and ARIMA(Hyndman and Khandakar 2008).The results we obtained reveal that better forecasts can be achieved using the new method when two asynchronous calendars exert their effects on the time-series.展开更多
文摘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.
文摘The method of Winters(1960)is one of the most well-known forecasting methodologies in practice.The main reason behind its popularity is that it is easy to implement and can give quite effective and efficient results for practice purposes.However,this method is not capable of capturing a pattern being emerged due to the simultaneous effects of two different asynchronous calendars,such as Gregorian and Hijri.We adapt this method in a way that it can deal with such patterns,and study its performance using a real dataset collected from a brewery factory in Turkey.With the same data set,we also provide a comparative performance analysis between our model and several forecasting models such as Winter’s(Winters 1960),TBAT(De Livera et al.2011),ETS(Hyndman et al.2002),and ARIMA(Hyndman and Khandakar 2008).The results we obtained reveal that better forecasts can be achieved using the new method when two asynchronous calendars exert their effects on the time-series.
