|
Abstract:
|
The Covid-19-pandemic has increased the need for timely and granular data that allow the assessment of the state of the economy in real time. As these time series often contain weekly or even daily observations, they present a challenge to traditional seasonal adjustment methods. We show how the calendar and seasonal effects of such economic indicators can be estimated reliably using the DSA approach for daily time series and an ARIMA-based adjustment strategy for weekly data. Drawing on a set of time series - namely electricity consumption, truck mileage, and Google Trends data - used in many countries to assess the economic development during the pandemic, we discuss obstacles, difficulties, and best-practices.
|
