Should tell more about poll design

Submitted by Bruce Myers (Canada), Feb 18, 2003 at 21:41

The analysis and data presented in your article strikes me as entirely credible. However I do have a nagging concern about what I find to be your unusual description of the poll design ("a national cross-section of 1,000 likely voters"). What is a "likely voter" and how is that determined? Was this a random sampling across age and gender cohorts in each region of the U.S., or were other determinants also brought into play (e.g. education & income levels, declared religious, ethnic or racial affiliations)? Spelling out more completely the poll design would, I feel, render your stated results considerably more skeptic-proof. Keep up your valuable work.

---

Note: Opinions expressed in comments are those of the authors alone and not necessarily those of Daniel Pipes. Original writing only, please. Comments are screened and in some cases edited before posting. Reasoned disagreement is welcome but not comments that are scurrilous, off-topic, commercial, disparaging religions, or otherwise inappropriate. For complete regulations, see the "Guidelines for Reader Comments".