Event study event study: II

Thankfully, sterling has collapsed to buttress the UK economy from this huge confidence shock. It won’t be enough, but it will help.

Based on the logic of an event study applied to when confidence in Bremain had risen, Brexit was meant to be worth 40% off the FTSE.  My inference was that event studies are not worth that much, which I — predictably — wield against the advocates of US QE, which is not harmful but more pointless.

This morning in the UK, it looks like sang froid.  We had a 90% swing in the probability of a  Brexit vote, from a 10% chance to realization, and the FTSE now looks to be down only 4 to 5%. I am no fan of event studies, but I would not have expected such a tame response.

The event students can pick their poison, I guess.

More importantly, good luck to the UK.  Business will be on hold a while; you don’t know how the EU will respond (but history suggests they will screw it up somehow); and you just emboldened some of your darker political forces.

Hopefully, you take the advice of the departing PM and try to pull this off as rationally as possible.  Good luck, sincerely.  This is a much bigger deal for you than the short-run market responses.

Update: I see now that the FTSE decline has itself declined by another percentage point. That’s because sterling has plunged. I was so right that lower sterling would help! Kidding. I have no clue, beyond being confident that lower sterling ITSELF is not a problem.

But just to overkill the point about event studies, consider this passage from Larry Summers’ blog just ahead of the vote. I linked to it earlier.

Second, markets are likely to suffer extraordinary volatility in the wake of Brexit. A Black Friday could follow referendum Thursday. It is likely that foreign investors in British stocks would lose 15 percent off the bat, adding together market declines and currency losses. This is a judgement supported by the gyrations in markets induced by relatively small fluctuations in the perceived chance of Brexit and by the very high prices commanded by out of the money options. The truth is that even with all the regulatory changes that have been put in place we do not know for sure how the financial system will respond. A return of systemic risk as large losses lead to cascading liquidations cannot be ruled out. At a time when central banks have far less ammunition than they did in 2008, the consequences could be grave.

Summers was applying the logic of a one-day event study. He observed the correlation between short-run swings in the odds of Brexit and the movement of the stock market. And he inferred from that the value of Brexit for the market. I think he must have faded it a bit, a good instinct as it turns out, because my calculation of the move over the weekend, when Bremain had bounced, was that it implied a 40% decline. My interpretation of that implausibility was that it was evidence that event studies are just dumb, as mentioned above.  QE advocates use event studies not because the method is compelling, but because they support their (mistaken) case.

Anyhow, Summers did say down 15% on Brexit.  Today’s event study would say down 4%, i.e. down 3.5%/0.9, where 0.9 is the CHANGE of the probability, from 0.1 to 1.

Maybe -15% will turn out eventually to be right. My point is not to say Brexit doesn’t matter for stocks. My point is that event studies are very not reliable. The answers they give about the one question are all over the map. It depends entirely on when you look.