Forecasting: Methods and Applications, 3rd Edition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Tales from tails: On the empirical distributions of forecasting errors and their implication to risk (2019, methodology): “Numerous metrics have been proposed in the literature while searching for the “holy grail”, i.e. an interpretable metric of ﬁne statistic properties (Makridakis et al., 1998; Fildes, 1992; Armstrong & Collopy, 1992; Davydenko & Fildes, 2013).”
It's time to move from 'what' to 'why' (2001, background): “Perhaps part of the explanation for the remarkable performance of SES forecasts is found in Rosanna and Seater (1995) who provide empirical evidence that many aggregated economic series with relatively low sampling frequencies can be approximated by an ARIMA(0,1,1) process.”
Meta-learning for time series forecasting and forecast combination (2010, methodology): “…be described as a regression against the past error values of the series y t = ω 0 + ω 1 (cid:15) t − 1 + ...ω q (cid:15) t − q + (cid:15) t The identiﬁcation of an appropriate ARIMA model for a speciﬁc time series is not straightforward [33] and usually involves expert knowledge and intervention.”
ARIMA: An Applied Time Series Forecasting Model for the Bovespa Stock Index (2014, background): “Makridakis, Wheelwrigt and Hyndman [12] state that in this case, depending on the values of p and q, Yt will depend on the past p values of Y and past q values of Θ errors.”