SI
SI
discoversearch

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor.  We ask that you disable ad blocking while on Silicon Investor in the best interests of our community.  If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.
Politics : PRESIDENT GEORGE W. BUSH -- Ignore unavailable to you. Want to Upgrade?


To: H-Man who wrote (308916)10/16/2002 3:26:27 PM
From: Mr. Whist  Read Replies (1) | Respond to of 769670
 
Mr. H-Bomb: You have proven zilch. On the issue of +1000 polls, I should have raised the sample population figure to +1200 or +1300. Big deal. It was you who argued that 1000 was too low, even though the sample had an acceptable margin of error. Had I realized you were an anal-retentive hair-splitter, I might have aimed for more specificity.

Fact: Of all the polls in early November 2000, only one had it right. I can't recall which one it was; you say it was Zogby; I have no reason to doubt you. CNN/ABC/USA Today/NBC/WSJ et al. had GWB winning by several percentage points; some had GWB crossing over into "landslide." Why did most polls get it wrong? Because of how they determined their "likely to vote" sample populations. Simple as that. Zogby wasn't the only poll to base its sample population on "likely to vote." So the main question is what did Zogby do differently to get it right? Perhaps you can enlighten the board since you're the expert in sample establishment.

Re: "Don't worry, all is not lost, for every poll of "adults", you ought to be able to count on 30-40 dead people voting for Democrats."

What the polls didn't track is how my union brothers and sisters got out the vote in Pennsylvania and Michigan on Election Day. I wonder if the automakers will give the UAW another day off (with pay) to do same on Election Day 2004. Shoe-leather democracy in action.