Opinion Counts Methodology

Each Opinion Counts survey will be fielded on the dates specified in the 2007 Opinion Counts calendar and are subject to change.  Each municipal survey will be composed of 300 completed respondents interviewed by telephone.   The margin of error for the data collected is +/- 5.66 % for a 300 response survey for the data analyzed in its entirety with a 95% confidence level; meaning that we can be 95% sure that if every resident of the population was actually surveyed, the results would vary by no more than 5.66% in either direction.

Each statewide survey will be composed of 400 completed respondents interviewed by telephone.   The margin of error for the data collected is +/- 4.9 % for a 300 response survey for the data analyzed in its entirety with a 95% confidence level; meaning that we can be 95% sure that if every resident of the population was actually surveyed, the results would vary by no more than 4.9% in either direction.

The survey sample to be used is a computer generated random list derived from a database of all Alaskan households for the statewide program, and Anchorage households for the municipal program, with working telephone numbers who have at least one member who has voted in at least two of the last four State and local elections. The sample frame is designed to accurately reflect the actual population percentages and the information is available by voting district and precinct cross tabulations for an additional fee. 

Respondents will be screened to confirm they are over 18 and each household will be attempted at least four times over a period of several days to account for non-response bias. Data will be analyzed utilizing SPSS Quancept Software.  Interviews are conducted by trained staff with on-site supervision utilizing state of the art computer assisted telephone interviewing (CATI).  Random interviews are monitored to assure quality control measures were followed.  Dialing results are analyzed daily to assure statistically accurate distribution of call disposition in order to account for “non-response” variables.

Shared Knowledge, Confidentiality & Exclusivity

Each Opinion Counts survey instrument will be developed by Hays Research Group staff with the consult of individual clients.   Individual Opinion Counts subscribers will not see the survey questions or the respondent data of other Hays Research Group clients, only those questions that are the property of each individual client will be provided to that client.

Hays Research Group also recognizes the unique nature of political polling and commits that it will  subscribe to the standard that they will contract with only one side of any given issue, initiative or campaign.

To purchase Opinion Counts questions, or to get more information please contact Hays Research Group.