Email Exchange With GDPNow Creator Pat Higgins on the Model

Mish

I had an email exchange with Pat Higgins on Covid-19 modeling and Unemployment Claims.

The GDPNow model forecast for 1st-quarter GDP is -0.3% as of April 16. The NY Fed Nowcast is -0.4%.

GDPNow vs Nowcast Evolution

GDPNow and Nowcast 2020-04-17

Super Optimistic

Compared to the Blue Chip forecast these models look ridiculously optimistic. 

The GDPNow website offered this tidbit.

There are no subjective adjustments made to GDPNow—the estimate is based solely on the mathematical results of the model. 

In particular, it does not capture the impact of COVID-19 beyond its impact on GDP source data and relevant economic reports that have already been released. It does not anticipate the impact of COVID-19 on forthcoming economic reports beyond the standard internal dynamics of the model.

Stranger things have happened but I pinged Pat Higgins specifically about unemployment claims as I thought that may be the source of the error. 

Here is the response from Higgins who is always generous with his time.

Hi Mish,

The model does use initial unemployment insurance claims among the 126 series used to estimate the monthly factor used to forecast yet-to-be released data.

However, the spike in March claims is identified by the code as an outlier and replaced with a more typical value.

Our policy is to not change the code in the middle of a quarter, so we can’t change how the code handles outliers until we begin forecasting the second quarter.

Whether or not March claims is treated by the code as an outlier does not have an outsize impact on the first quarter forecast, in part because it is only 1 of 126 series and because much of the first-quarter data has been released.

I can’t really say how a spike in unemployment would effect the forecast because of the FOMC blackout which ends a week from Friday. I can follow up after that however.

Best regards, 

Pat

Mish

Comments (49)
No. 1-16
Sechel
Sechel

Thanks. this is a problem with most models when faced with new situations for which there are no correlations and regressions to draw from

njbr
njbr

I once bought a model of the USS Enterprise Star Trek ship. It ended up looking like a HeeHaw wagon..

Sechel
Sechel

when we're faced with models that we quite haven't figured out their flaws. we usually fudge them of course we come up with nicer ways of phrasing it, like when the predicts delinquencies vastly higher or lower than the pool of loans its working off of

Tony Bennett
Tony Bennett

"Compared to the Blue Chip forecast these models look ridiculously optimistic."

...

I'll take the under.

Frankly, I suspect things much worse than they are expecting (and certainly from the "experts" on tv). Just now they are beginning to grasp situation as tax revenues are being reported. And I don't expect tax revenues to rebound anytime soon ... more likely further droppage.

lol
lol

Realistically "reopen" an economy that's been dead and rotting away since 2009 will just invite a tsuname of phony lawsuit scams,everybody will be sueing every establishment claiming injury or infection,hell wanna make the big bucks,go class action.....ca ching!

MATHGAME
MATHGAME

Does anyone think the models/algorithms that do a large, if not majority, portion of stock trading these days were any more inclusive of new situations like the COVID-19 pandemic than the GDPNow model was? All they seem to be responding to these days is Fed printing ... which admittedly is a major factor.

Casual_Observer
Casual_Observer

This is all backward looking. The market is extremely forward looking at this point. The market is forcing itself into a V shaped recovery irrespective of what happens in the real economy which will probably be more like a check-mark shaped recovery.

tokidoki
tokidoki

The economy must not be so bad. I mean look at Snapchat. There seems to be no impact on ads. People must continue to spend. Tons of businesses out there like Expedia, AirBnb, etc are cutting marketing, but somehow it's not translating into a decline in online ads revenue.

Everything has to be hunky dory right?

Greggg
Greggg

"Our policy is to not change the code in the middle of a quarter, so we can’t change how the code handles outliers until we begin forecasting the second quarter".
Translation: We don't want to panic people with skin in the game.

Mish
Mish

Editor

Deflation is primarily about destruction of credit, not prices.

But if home prices were put in the CPI as they should be, price deflation would be huge.

Regardless, I expect a degree of price deflation anyway.

lol
lol

Fed will print between $7-800 Trillion this year for (if we're lucky)1% GDP ,2009 they printed $100 trillion and change for.......1% GDP...ain't inflation a bitch!

Herkie
Herkie

This morning CNBC reported that 4.43 million people filed new claims for unemployment in the last week so of course the Dow opens higher. It is interesting to note that this read is nearly identical to the estimate, which was 4.3 million.

They also said that this will equate to an unemployment rate of 21.7% for the month of April when the unemployment rate gets reported in May. It will only take one more week of multimillion claims levels to match or exceed the peak unemployment rate of the great depression which was 25%. I am not going to Google that fact, so if you disagree with it please refer criticism to CNBC which reported that.

Even if we take the stupid/suicidal move of reopening the economy in the first week or two of May quite a few of those jobs are not going to return. This will leave a lingering high unemployment rate that will evolve into a structural problem lasting years.

tokidoki
tokidoki

Restaurants are pretty much dead. Lots of smaller businesses too. And not because there's no business. Just look at this: https://www.sfgate.com/food/slideshow/Boba-Guys-reopens-SF-location-Hayes-Valley-201755.php

"Chau, who along with co-founder Bin Chen is still not taking a salary, said at least one employee said they weren’t returning because unemployment benefits were too good to give up."


Global Economics

FEATURED
COMMUNITY