Disaggregation methods based on MIDAS regression

摘要: Abstract The need to combine data from different frequencies plays an important role for many economic decision-makers and economists. process, which consists in using higher frequency construct a indicator its lower counterpart, is called temporal disaggregation. In this paper, we propose new disaggregation technique based on MIDAS regression time series sampled at frequencies. We first simple procedure more flexible than the traditional approaches, such as Chow–Lin (1971), extend dynamic setting. proposed enough take into account seasonality or calendar effects. An extensive simulation study examines performance of approach compared alternative approaches.