PDP–Nate Silver’s models, political thermometers, and long term predictions

I have the sense that Nate Silver has been a bit corrupted by the position he’s in at the NYTimes. Back in 2008–he became big DURING the primaries as his statistical models mapped changing levels of support for candidates in a relatively …stable and immediate way. But he wasn’t making prognostications about events–even implicitly–that were 9 months away.

He has now been doing exactly that for like 6 months… and it’s really demonstrating both the limitations of his model–and the silliness of thinking they can be applied in this way.

Basically–his models are more like thermometers/barometers that can tell you pretty accurately what the weather is at any one time–and maybe what it’ll be like in the next week or so–but having a thermometer that tells you it is cold on Dec. 10th TELLS YOU NOTHING about whether it will be over 50′ on March 10th–and talking about your awesome data on Dec. 10th as if it really provides insight into the temperatures on March 10th is downright misleading, if not also audaciously deceptive.

Knock this shit off.



About Prof. Woland

I contain multitudes. Come meet us.
This entry was posted in Numbers and Mathematics, Politics and tagged , , , , . Bookmark the permalink.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s