Do you know or did you check to find out if this poll was done by registered or likely voters?
RE: Do you know or did you check to find out if this poll was done by registered or likely voters?
_____________________________________________________________________________
They claim it is a survey of LIKELY VOTERS ( in their words -— 500 LIKELY ALASKAN VOTERS ).
SEE HERE : http://haysresearch.com/page2/page32/page32.html
This is all there is to their Survey Methodology
This survey was fielded on June 21st-22nd, 2011 as a means to measure attitudes towards candidates and races among likely Alaskan voters (defined as having voted in at least two of the last four local or statewide elections). 500 likely Alaskan voters were interviewed for each of the four surveys.
The margin of error for the data collected is +/- 4.4 % for a 500 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 State of Alaska with working telephone numbers who have at least one member who has voted in at least two of the last four local or state elections was actually surveyed, the results would vary by no more than 4.4% in either direction.
The survey sample used was a computer generated random list derived from a database of all households within the State of Alaska with working telephone numbers who have at least one member who has voted in at least two of the last four local or state elections. The sample frame was designed to accurately reflect the actual population percentages.
Respondents were screened to confirm they were over 18 and each household was attempted at least four times over a period of several days to account for non-response bias.
Data was analyzed utilizing SPSS Quancept Software.
Interviews were conducted by trained staff with on-site supervision utilizing state of the art computer assisted telephone interviewing (CATI). Random interviews were monitored to assure quality control measures were followed. Dialing results were analyzed daily to assure statistically accurate distribution of call disposition in order to account for “non-response” variables.
For purposes of disclosure, this poll question was survey was paid for in full by Porcaro Communications.
Hayes track record on polling is terrible, his polling for 2008 was off by 17 points
Likely voters, but no other internals except to say they called a "random list."