|
Likely
Republican Primary Voters Likely Republican Primary VotersRelease 04-2001-2MethodologyThe most recent Fairleigh Dickinson University PublicMind Poll was conducted by telephone from April 28 through May 1st. A random sample of 324 likely Republican primary voters were interviewed. The sample was drawn from registered voter lists from all 21 counties in New Jersey. Only voters who had cast ballots in the Republican primary election in 2000 and declared that the chances of their voting this June were either "excellent" or "good were interviewed. The voter lists from which the sample was drawn are maintained by Labels & Lists, Inc. of Bellevue, WA. All sample surveys are subject to two kinds of error. For a sample of 325, the sampling error is +/-5.5% at the 95% confidence level. This means that 19 times out of 20, a random sample will yield results that are no more that 5.5% different than if all likely voters were interviewed. The +/- 5.5% sampling error holds for results near 50%. For percents closer to 10% or 90%, the sampling error is +/-3.1%. In addition, all survey results are subject to non-sampling error. This kind of error, which can not be measured, arises from a number of factors including, but not limited to, non-response (eligible voters refusing to be interviewed), question wording, the order in which questions are asked, and variations among interviewers. The interviews were conducted by TMR, Inc. of Parsippany, NJ. Professionally trained interviewers using a CATI (Computer Assisted Telephone Interviewing system) conducted all interviews . Survey WordingThe wording of the questions included in this release are as follows:
see also: |
|||||||||||||||||||||||||||||||||||||||||||||||
Copyright © 2001, Fairleigh Dickinson University. All rights reserved. FDU PublicMind Poll [Latest update 010508] |