Abstract
By its emissions of greenhouse gases, economic activity is the source of climate change which affects pandemics that in turn can impact badly on economies. Across the three highly interacting disciplines in our title, time-series observations are measured at vastly different data frequencies: very low frequency at 1000-year intervals for paleoclimate, through annual, monthly to intra-daily for current climate; weekly and daily for pandemic data; annual, quarterly and monthly for economic data, and seconds or nano-seconds in finance. Nevertheless, there are important commonalities to economic, climate and pandemic time series. First, time series in all three disciplines are subject to non-stationarities from evolving stochastic trends and sudden distributional shifts, as well as data revisions and changes to data measurement systems. Next, all three have imperfect and incomplete knowledge of their data generating processes from changing human behaviour, so must search for reasonable empirical modeling approximations. Finally, all three need forecasts of likely future outcomes to plan and adapt as events unfold, albeit again over very different horizons. We consider how these features shape the formulation and selection of forecasting models to tackle their common data features yet distinct problems.
Highlights
Magdalen College and Climate Econometrics, University of Oxford, Oxford OX1 4AU, UK; Nuffield College and Climate Econometrics, University of Oxford, Oxford OX1 1NF, UK; Abstract: By its emissions of greenhouse gases, economic activity is the source of climate change which affects pandemics that in turn can impact badly on economies
Climate change has long affected pandemics like the Justinian Plagues and Black Death as well as from environmental disruptions leading to zoonotic diseases like Ebola and SARS
The time-series observations of many variables in all three disciplines are non-stationary from stochastic trends and abrupt shifts, so need robust forecasts to plan over different horizons
Summary
The massive challenges that economic, climate and pandemic forecasting have had to face during the Sars-Cov-2 pandemic have highlighted the fundamental role in forecast failures of unanticipated distributional shifts. On a very different time scale, Panel (c) reports the massive increase of almost 140 parts per million (ppm) in atmospheric CO2 in just the past 250 years compared to the ±25 ppm. GDP since 2007; (c) thousand-year changes in atmospheric CO2 in parts per million (ppm) over Ice. Ages, and last 250 years; (d) UK daily new confirmed cases of COVID-19 to August 2021. This small sample of time series in both levels and differences confirms that forecasting practice faces wide-sense non-stationary observed processes in all three disciplines. Large shifts can occur in differenced time series as shown in Figure 1b,c, where the change in atmospheric CO2 seems a relatively permanent jump, and GDP growth has already recovered, it will drop back again to a more ‘normal’ growth rate. Facing unanticipated future breaks, the fundamental problem remains as to which formulation will continue to provide useful forecasts, so in Section 6, we consider some ‘principles’ that might help avoid systematic forecast failure
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
