Tuesday, June 2, 2020

Pitfalls in Epidemiological Modelling


Tyler Cowen is sounding just a bit fed up with Twitter, in this Marginal Revolution post and in particular with the way Twitter has degenerated into a name calling equilibrium. Prisoners Dilemma with everyone choosing to betray (what’s the payoff structure that would support such an outcome?).  the point at issue is the explanation which one modeller has given for why his model overestimated the impact of COVID in Germany – his casual reference to Dark Matter prompted people to say that “Dark Matter” is shorthand for “my model doesn’t work, and I don’t know why”.

The sad thing is that if he’d said that it must mean that people were doing more social distancing than he’d anticipated, he would have placed himself squarely in the mainstream of COVID modelling.  At some point we’ll have to face up to the fact that the epi models for COVID have bee pretty much useless.  Most of the world fell into line behind the Imperial College London (ICL) model, despite its tendency to produce massively wide prediction bounds (you can’t call them confidence intervals since most modellers don’t assign probability weights to them).  The Babylon Bee, a satirical website, ran a headline a while ago saying that: “Latest Computer Model Predicts Between 0 And12.6 Billion New COVID-19 Deaths By Summer”  but when it comes to epi modelling, reality is well on its way to overtaking satire. 

COVID-19 and Liquidity Preference


Stephen Poloz made an observation, both in his University of Alberta lecture and also in his final appearance before the Senate National Finance Committee as Governor of the Bank that part of the reason the Bank was buying large quantities of government bonds from financial institutions (as distinct from the ones it’s buying from the government in the primary market) had to do with large firms drawing down their lines of credit.  There’s more (out of the US) on this phenomenon here as well as a VoxEU post on it here and a (pretty technical) National Bureau of Economic Research working paper on it here.

The basic idea is that one thing which a lot of firms learned in 2008 was that if you waited until they were in financial difficulty to all on their lines of credit with their banks, they could find their access truncated by banks which were worried about their own ability to support those loans.  So this time they decided to draw on their lines of credit as soon as the first signs of trouble, rather than wait and see how things played out.

Trudeau calls in the big guns from the Boston Consulting Group


A colleague of mine brings this story to my attention:  “Ottawa working with U.S consulting firm on early planning for economic recovery”.
According to the Globe and Mail report:

“One of the world’s biggest multinational consulting firms is advising Justin Trudeau’s cabinet on how Canada could emerge from its COVID-19 lockdown, as a growing number of federal ministers get involved in early discussions around an economic recovery strategy.
Canadian representatives of the Boston Consulting Group (BCG) met for several hours at the start of this week with roughly eight of Mr. Trudeau’s ministers, as part of a broader advisory role the U.S.-based consultancy is serving on an unpaid basis.”
………………………………………………………………………………………………………………………………………………………………….
“…According to the agenda for Monday’s meeting, the consultants provided an overview of the pandemic around the world, before ministers discussed “game-changing ideas” and “building blocks for recovery.” The document pointed out the government still had much work ahead.”