Archive for the ‘Silver, Nate’ Category

Silver’s hedge: ”Bet’s off if there is a systematic polling error”

November 6, 2018

And, a Vegas odds-maker says that’s likely.

=============

Let’s connect a couple of dots today…

Nate Silver is the Democrat’s predictor of choice.

Remember, he’s the guru who said – on the day before the 2016 election – that Hillary had a greater than 90% chance of winning.

Oops.

Of course, he retroactively said that he was talking about the popular vote – not the pesky electoral college …. and Hillary’s 90% meant conversely that Trump had a slim statistical chance that happened to materialize..

Vindicated, right?

So, what is Silver saying about today’s elections?

image

Cutting to the chase, he says that Democrats have an 86% chance of taking control of the House.

But, wiser with age, Nate is explicitly hedging his bet this time….

 

==============

Here’s Silver’s final pre-election banner headline:

image

Directly on-point,  he says:

image

Hmmm

Could it be that the polling data is “systematically wrong” … again?

(more…)

Nums: Why are economists so bad at forecasting?

February 10, 2015

Wash Post had an interesting analysis titled “This graph shows how bad the Fed is at predicting the future

The crux of their argument: the Fed has a clear recent tendency to mis-forecast economic growth … not by a little, by a lot …  forecasting almost twice as rapid growth as is ultimately realized.

For example,  in 2009 the Fed was predicting 4.2 percent growth in 2011.  But then in 2010 it revised that down to 3.85 percent growth. And in 2011 they revised it further to 2.8 percent growth. And when all was said and done, the economy only grew about 2.4 percent that year. The Fed projected growth almost twice as fast as what actually happened.

 

image

What’s going on?

 

(more…)

Tuesday: A bad night for pollsters … and some other folks.

November 6, 2014

The election results looked a lot different than the pollsters predicted.

Pat Roberts was supposed to lose … he won by a comfortable margin.

Joni Ernst “might” eek out win … she romped.

Mark Warner was supposed to be popping champagne corks by 8 o’clock … he got less than 50% and the VA race hasn’t been officially called yet.

What happened?

Nate Silver’s 535 has nailed the symptoms … but not the cause.

 

image

=====

Bottom line: Silver’s crew observes that there was an average 4-point polling bias in favor of the Dems ….

(more…)

Nate Silver has spoken …

November 4, 2014

Former darling of the left for having predicted President Obama’s hefty win over Mitt Romney, stats-jock Nate Silver has given his final pre-election prediction:

76% chance that the Republicans take control of the Senate today … with odds trending their way.

 

image

 

Silver’s prediction slides between the high-end Washington Post (97%) and CNN (95%) … and the low-balling New York Times (70%).

That means that there’s a 100% chance that Silver gets neither savant accolades, nor hoot-calls …  his prediction is stuck in the middle.

#HomaFiles

Follow on Twitter @KenHoma            >> Latest Posts

Nums: Why are economists so bad at forecasting?

October 7, 2014

Wash Post had an interesting analysis titled “This graph shows how bad the Fed is at predicting the future

The crux of their argument: the Fed has a clear recent tendency to mis-forecast economic growth … not by a little, by a lot …  forecasting almost twice as rapid growth as is ultimately realized.

For example,  in 2009 the Fed was predicting 4.2 percent growth in 2011.  But then in 2010 it revised that down to 3.85 percent growth. And in 2011 they revised it further to 2.8 percent growth. And when all was said and done, the economy only grew about 2.4 percent that year. The Fed projected growth almost twice as fast as what actually happened.

 

image

What’s going on?

 

(more…)

Nums: Why’s the Fed so bad at forecasting?

April 18, 2014

Wash Post had an interesting analysis titled “This graph shows how bad the Fed is at predicting the future

The crux of their argument: the Fed has a clear recent tendency to mis-forecast economic growth … not by a little, by a lot …  forecasting almost twice as rapid growth as is ultimately realized.

For example,  in 2009 the Fed was predicting 4.2 percent growth in 2011.  But then in 2010 it revised that down to 3.85 percent growth. And in 2011 they revised it further to 2.8 percent growth. And when all was said and done, the economy only grew about 2.4 percent that year. The Fed projected growth almost twice as fast as what actually happened.

 

image

What’s going on?

 

(more…)

Nums: Why’s the Fed so bad at forecasting?

June 24, 2013

Wash Post had an interesting analysis this week titled “This graph shows how bad the Fed is at predicting the future

The crux of their argument: the Fed has a clear recent tendency to mis-forecast economic growth … not by a little, by a lot …  forecasting almost twice as rapid growth as is ultimately realized.

For example,  in 2009 the Fed was predicting 4.2 percent growth in 2011.  But then in 2010 it revised that down to 3.85 percent growth. And in 2011 they revised it further to 2.8 percent growth. And when all was said and done, the economy only grew about 2.4 percent that year. The Fed projected growth almost twice as fast as what actually happened.

 

image

What’s going on?

 

(more…)