Economic forecasting in theory and practice: An interview with David F. Hendry

Abstract

David Hendry has made major contributions to many areas of economic forecasting. He has developed a taxonomy of forecast errors and a theory of unpredictability that have yielded valuable insights into the nature of forecasting. He has also provided new perspectives on many existing forecast techniques, including mean square forecast errors, add factors, leading indicators, pooling of forecasts, and multi-step estimation. In addition, David has developed new forecast tools, such as forecast encompassing; and he has improved existing ones, such as nowcasting and robustification to breaks. This interview for the International Journal of Forecasting explores David Hendry's research on forecasting. an anonymous referee for helpful comments and discussion, and to Aaron Markiewitz for research assistance. Empirical results and graphics were obtained using 64-bit Ox-Metrics 7.1; see Doornik and Hendry (2013). policy's implementation, or consumers' responses to both. Consequently, my model's forecasts failed badly.NRE: Your UK model was subsequently published as Hendry (1974), which included a new test for predictive failure. It generalized Gregory Chow's (1960) single-equation predictive failure test to systems, albeit in a  2 version rather than the  version that Jan Kiviet (1986) later developed. How did that experience with your small macromodel influence your work on forecasting?DFH: It motivated me to investigate the nature of predictive failure. Why did models built from the best available economics using the latest econometrics and fairly good data not produce useful forecasts? In Hendry (1979b), I linked predictive failure to poor model formulation, but that explanation subsequently turned out to be unhelpful, or at least incomplete. NRE:Other economists were also evaluating forecasts from macro-models. In particular, Charles Nelson wrote two influential papers on ex ante forecasts: Nelson (1972) and Cooper and Nelson (1975).DFH: Charles showed that forecasts from univariate time-series models could beat forecasts from large empirical economic models such as the FRB-MIT-PENN model. From an LSE perspective, such large models treated dynamics inadequately, often simply as autocorrelated errors in static equations. Because of that dynamic misspecification, we suspected that models that included only dynamics could forecast better. I found that simple dynamic models did indeed forecast better than static economic models, even though the latter embedded economic theory whereas the former did not. However, I had misinterpreted the implications of Nelson and Cooper's results. I had not realized that models in differences-such as those in Nelson (1972)almost invariably forecast better than models in levels if the means of the variables being forecast altered. We now refer to such changes as location shifts.

A Brief History of General‐to‐specific Modelling*

“…Second, many so‐called ‘naive’ predictors are actually robust after shifts in that they quickly move back on track, unlike EqCMs that instead try to return to the previous equilibrium: see Hendry (2006) and Ericsson (2017). EqCMs continue to be used after forecast failure has occurred, despite that serious flaw.…”

Forecasting the UK top 1% income share in a shifting world

“…The system was acknowledged to be naive, both to minimize the already large computational burden for the time, and to focus attention on the stochastic properties of the error processes. The quarterly data sample was from 1957Q(1) to 1967Q(4), of which the last two observations were used for a test of its forecasts, which chanced to avoid the catastrophic forecast errors he later made for 1968Q(1) and 1968Q(2) (see Ericsson 2017). However, those later errors made him carefully analyse economic forecasting, a topic that he has continued to research with several co-authors, including those for this paper.…”