Silicon Investor (SI) -- The First Internet Community

STOCKTALK

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 : Politics for Pros- moderated -- Ignore unavailable to you. Want to Upgrade?

To: JohnM who wrote (116448)	5/26/2005 7:32:22 PM
From: Nadine Carroll	Read Replies (1) \| Respond to of 793817

I gather you are bothered by interpretive weighting when it increases Dems but not when it increases Reps. At least that appears to the usual model among these sorts of blogs. I am bothered by major re-weighting of any large sample without explanation or any reasonable rationale. The last national election was about 52% - 48% Republican - Democrat. If they had weighted to that, it would have at least made sense, though I tend to fall into the 'leave it alone' camp when it comes to reweighting polls for party afflialtions, which after all are changeable and may be said to reflect political opinions rather than demographics. But instead they took a raw sample that was 34% Dem, 34% Rep, and 32% Ind, and reweighted it to 36% Dem, 32% Rep, and 32% Ind. Where the heck did that come from? What model are they using? This was a significant change - significant to have affected the questions and altered their headlines. Yet they did not inform their readers and provided no explanation at all. Does that strike you as sound methodology? Whichever party benefits?