World Coronavirus Forecast Update: 5 April 2020

Reported cases of Covid-19 infections on a global basis continue to exceed the median forecast, based on’s 8-model combination estimate (see note below). That’s a clue that a peak on a worldwide basis remains elusive for the immediate future. By contrast, new cases that fall below the median forecast on a continual basis will strengthen expectations for assuming that a durable apex is near or has already started. Alas, we don’t appear to be at that turning point yet for the global numbers.

Unfortunately, a global peak doesn’t appear imminent at this point, at least not based on the numbers to date. But there’s reason for thinking positively: Several countries have already peaked, including China, based on reported data via Johns Hopkins. More recently, Italy is reportedly peaking. “The curve has reached a plateau and begun to descend,” says Silvio Brusaferro, head of the Istituto Superiore di Sanità, Italy’s primary health institute.

For the global outlook, however, cases continue to show an upward bias, based on today’s projection.

Previous forecasts in this project have consistently underestimated future cases, using the median combined estimate for 8 models as a benchmark. Most worrisome is the previous Mar. 29 forecast: the actual data exceeded not only the median forecast but the upper estimate at the 95% confidence level. With several key countries showing signs of peaking, however, perhaps better news awaits in the days ahead.

Note: You can find a list of the models used in this project here. Note that one of the models (vector autoregression) isn’t used for forecasting Covad-19. The reason: the dataset (published by Johns Hopkins) is univariate and vector autoregression is a multivariate application.

Learn To Use R For Portfolio Analysis
Quantitative Investment Portfolio Analytics In R:
An Introduction To R For Modeling Portfolio Risk and Return

By James Picerno