The Right Coast

Editor: Thomas A. Smith
University of San Diego
School of Law

A Member of the Law Professor Blogs Network

Monday, October 22, 2012

Nate Silver’s Flawed Model - Josh Jordan - National Review Online

The main reason that Silver feels Obama is still an overwhelming favorite is that while Romney has surged in the polls to tie (or lead) Obama nationally, the challenger is still, in Silver’s opinion, a long shot to pull together enough battleground states to get to 270 electoral votes. This is the real problem with Silver’s model in the eyes of many Romney backers — the “weighting” he puts into state polls gives an edge to Obama, and the distribution of that weighting is highly subjective. For example, Silver currently gives Obama a 70 percent chance of winning Ohio. A component of this is a weighted “polling average” of Obama’s support at 48.2 percent to Romney’s at 45.2. The current Real Clear Politics average is nearly a full point more favorable to Romney: It has Obama at 48.1 and Romney at 46.0. The difference comes from the fact that Real Clear Politics gives equal weight to all of the polls it includes and uses only the most recent polls from each polling organization in a given timeframe.


dittos. --TS

| Permalink


OK, so Mr. Silver has attained a status because of his ability to be right and no other reason.

His ability to be right stems solely from data and a model.

So essentially the illustrious data-cruncer "Josh Gordon" as dittoed by the fair sultan of statistical analysis Tom Smith have cracked a glitch that shows that model is no more but a mere cover for pure partisanship!?! OK, Mr. Silver must have fixed every single Senate race in 2010 to prove that his nefarious personal preference indeed works thereby fooling the world, but for JOSH GORDON AND TOM SMITH!!!!

Posted by: SK | Oct 23, 2012 2:35:07 PM

The problem is that he doesn't seem to actually have a model but just assigns weights to polls based on his gut. If he turns out to be right, you can't tell if he's lucky or just has some weird talent that is not expressible in a reproducible model. That's a problem. Some people do seem to have uncanny abilities to read markets, sporting events and so on, but they can't tell you how they do it (and may have no reason to do so). This makes it impossible to tell whether you are just observing a low probability event or something more. Lucky streaks can also go on for a long time. I heard a story about a guy named Jimmy the Flea, a vagrant, who took his SS check up to $2 million at the blackjack tables at the Mirage in Vegas. They kept him playing until he back down to a few thousand bucks and then tossed him out. Without a method there's no way to tell is Silver is a genius or just Jimmy the Flea.

Posted by: Tom Smith | Oct 24, 2012 12:36:23 PM

Smith and Gordon accused Nate Silver of being a cheerleader for Obama masquerading as a data cruncher. That's a serious charge. The final results were as follows: Silver was correct in 50 out of 50 states in the presidential election, but his predictions for Senate races were wrong in three states. Unfortunately for the allegation of anti-Republican bias, Silver's errors were all in favor of Republican candidates who lost. Perhaps a mea culpa is warranted??

Posted by: Roger Conner | Nov 7, 2012 9:16:07 PM