Welcome to European Tribune. It's gone a bit quiet around here these days, but it's still going.
Display:
Help me out on your new analysis:  Is the Diebold affect still showing about 4.6% on Clinton's tally?

Be nice to America. Or we'll bring democracy to your country.
by Drew J Jones (pedobear@pennstatefootball.com) on Sun Jan 13th, 2008 at 05:50:38 PM EST
[ Parent ]
> Continuation!  I've been trying to hunt you down for two days, Oh Guru of Teh Regression.  Glad to see you.

Oh no please don't call me like that.  You'll be really disappointed at my credentials.  I was trying to word my findings carefully to avoid this, but let me put here a full disclaimer:

  • I am not a statistician!
  • I did not even take a single statistics course!
  • I only have a minor in math.
  • My Ph.D. is in theoretical computer science, which is very very far from statistics
  • I have an amateur interest and I like to play with R, that's all!

So you'd better take all I say as the rantings of a lunatic computer scientist and find a proper statistician/sociologist.

That being said...

> Is the Diebold affect still showing about 4.6% on Clinton's tally?

Slightly less.  With a coefficient of 3.18 percentage points, Diebold is still the non-political variable having the highest coefficient in the model.

by continuation (continuation pretzel ouvaton point org) on Sun Jan 13th, 2008 at 06:14:37 PM EST
[ Parent ]

Display:

Occasional Series