ClydeR
09-06-2016, 11:58 AM
The Post-SurveyMonkey results are consistent with many of those findings, but not in all cases. Trump’s support in the Midwest, where the electorates are generally older and whiter, appears stronger and offers the possibility of gains in places Democrats carried recently. He has small edges in two expected battlegrounds — Ohio and Iowa — and is close in Wisconsin, Pennsylvania and Michigan, each of which Democrats have won in six consecutive elections.
At the same time, however, Trump is struggling in places Republicans have won consistently and that he must hold to have any hope of winning. These states include Arizona and Georgia, as well as Texas — the biggest surprise in the 50-state results. The Texas results, which are based on a sample of more than 5,000 people, show a dead heat, with Clinton ahead by one percentage point.
Clinton also leads by fewer than four points in Colorado, Florida and is tied with Trump in North Carolina. In Colorado, other polls have shown a larger Clinton lead. In Mississippi, Trump’s lead is just two points, though it’s doubtful that the GOP nominee is in much danger there.
More... (https://www.washingtonpost.com/politics/a-new-50-state-poll-shows-exactly-why-clinton-holds-the-advantage-over-trump/2016/09/05/13458832-7152-11e6-9705-23e51a2f424d_story.html)
A poll that shows Clinton leading in Texas and Trump leading in Michigan? The separate article below says that it was a "non-probability" poll. Eventually, polling will need to be conducted by a means other than the telephone, but my gut tells me they don't have it exactly right yet.
The Post-SurveyMonkey poll employed a “non-probability” sample of respondents. While standard Washington Post surveys draw random samples of cellular and landline users to ensure every voter has a chance of being selected, the probability of any given voter being invited to a SurveyMonkey is unknown, and those who do not use the platform do not have a chance of being selected. A margin of sampling error is not calculated for SurveyMonkey results, since this is a statistical property only applicable to randomly sampled surveys.
The ability of random samples to represent the overall population is grounded in probability theory. With non-probability samples, testing is necessary to ensure a particular sampling strategy, along with adjustments to match population demographics, can consistently produce accurate estimates.
More... (https://www.washingtonpost.com/news/post-politics/wp/2016/09/06/how-the-washington-post-surveymonkey-50-state-poll-was-conducted/)
At the same time, however, Trump is struggling in places Republicans have won consistently and that he must hold to have any hope of winning. These states include Arizona and Georgia, as well as Texas — the biggest surprise in the 50-state results. The Texas results, which are based on a sample of more than 5,000 people, show a dead heat, with Clinton ahead by one percentage point.
Clinton also leads by fewer than four points in Colorado, Florida and is tied with Trump in North Carolina. In Colorado, other polls have shown a larger Clinton lead. In Mississippi, Trump’s lead is just two points, though it’s doubtful that the GOP nominee is in much danger there.
More... (https://www.washingtonpost.com/politics/a-new-50-state-poll-shows-exactly-why-clinton-holds-the-advantage-over-trump/2016/09/05/13458832-7152-11e6-9705-23e51a2f424d_story.html)
A poll that shows Clinton leading in Texas and Trump leading in Michigan? The separate article below says that it was a "non-probability" poll. Eventually, polling will need to be conducted by a means other than the telephone, but my gut tells me they don't have it exactly right yet.
The Post-SurveyMonkey poll employed a “non-probability” sample of respondents. While standard Washington Post surveys draw random samples of cellular and landline users to ensure every voter has a chance of being selected, the probability of any given voter being invited to a SurveyMonkey is unknown, and those who do not use the platform do not have a chance of being selected. A margin of sampling error is not calculated for SurveyMonkey results, since this is a statistical property only applicable to randomly sampled surveys.
The ability of random samples to represent the overall population is grounded in probability theory. With non-probability samples, testing is necessary to ensure a particular sampling strategy, along with adjustments to match population demographics, can consistently produce accurate estimates.
More... (https://www.washingtonpost.com/news/post-politics/wp/2016/09/06/how-the-washington-post-surveymonkey-50-state-poll-was-conducted/)