The Star Tribune Minnesota Poll findings are based on telephone interviews Sept. 18 to 23 with a representative sample of 802 adults in Minnesota telephone households. Interviews were conducted under the direction of Princeton Survey Research Associates International (PSRAI).
Results of a poll based on 802 interviews will vary by no more than 4 percentage points, plus or minus, from the population 95 times out of 100. Margins are larger for groups within the sample, such as DFLers or Republicans.
The margin of sampling error for Republicans, for example, is plus or minus 9 percentage points, for DFLers it is plus or minus 8 percentage points and for independents it is plus or minus 7 percentage points.
Sampling error does not take into account other sources of variation inherent in public opinion surveys such as nonresponse, question wording or context effects. In addition, news events may have affected opinion during the period the poll was taken.
Sample design
Samples are designed to represent all of Minnesota telephone households. The telephone samples are provided by Survey Sampling International LLC (SSI), according to PSRAI specifications and are drawn using standard list-assisted random digit dialing (RDD) methodology. Active blocks of telephone numbers (area code + exchange + two-digit block number) that contain three or more residential directory listings were selected with probabilities in proportion to their share of listed telephone households; after selection two more random digits are added to complete the number. This method guarantees coverage of every assigned phone number regardless of whether numbers are directory listed, purposely unlisted, or too new to be listed. After selection, numbers are compared against business directories and listed business numbers are purged.
Contact procedures
Multiple attempts are made to contact every sampled telephone number. The sample is released for interviewing in replicates, which are representative subsamples of the larger sample. Using replicates to control the release of sample ensures that complete call procedures are followed for the entire sample.
In each contacted household, interviewers asked to speak with the youngest adult male currently at home. If no male was available, interviewers asked to speak with the youngest female at home. This systematic respondent selection technique has been shown to produce samples that closely mirror the population in terms of age and gender.
Sample weighting
Weighting is generally used in survey analysis to compensate for patterns of nonresponse that might bias results. The interviewed sample of all adults is weighted to match parameters for sex, age, education, race, Hispanic origin and region. These parameters came from a special analysis of the Census 2000 Summary File 4 (SF 4).
Weighting is accomplished using Sample Balancing, a special iterative sample weighting program that simultaneously balances the distributions of all variables using a statistical technique called the Deming Algorithm. The use of these weights in statistical analysis ensures that the demographic characteristics of the sample closely approximate the demographic characteristics of the population.
Readers can e-mail questions to mnpoll@startribune.com.
The Star Tribune is still blowing the whistle, but our look and location have changed. Click here to get to the new blog. If you want the actual URL, it’s www.startribune.com/blogs/whistleblower.html. Our blog posts will now be easier to search on the web site, but you’ll need to register to post a comment. In the [...]
![]() Receive Customized E-mail AlertsSign up for My Car Searches & E-mail Alerts. |
Comment on this story | Be the first to comment | Hide reader comments