from 100,000 respondents. How the heck can they do that?
There is little difference between a poll of 2,858 people and 100,000 people
The poll of 2,858 has a margin of error of 1.83% while a poll of 100,000 has a margin of error of .31%.
The 97,000 extra respondents don’t make all that much of a difference.
Internals? Party breakdown even to +2D? Gender 52-48 or 53-47 F?
All I get are a bunch of ads. No detail. Just vague text.
Come on! No one is going to win this election by more than 5%, let alone by 28%. This poll is as bogus as the network polls.
I believe the tracking polls showing a dead heat at this time are probably the most accurate. But after a good couple days, I hope to see Trump move up a bit.
Strange verb choice in the headline. Does Monica Lewinski work there?
Their argument that a few hundred is not a large enough sample size does not hold water. It is large enough--provided the method one uses to select the sample is accurate. If the method is not accurate, then increasing the sample size will not help. This is strictly mathematics, not really a judgement call.
The judgement call comes in determining what a valid method of selecting a sample is. While I am not sure the professional pollsters have it down for this election, I suspect they are far closer than these guys.
Any new polling method like this should regularly also ask,,,
,,, “Who did you vote for in 2012?” so that today’s preferences can be judged if they are weighted correctly.
Considering the biased nature in the way the question was framed the response was shocking: 64% told Zip they would vote for Trump and only 36% responded that their choice was Clinton.
Figure out WHO these respondents actually are and you may have something. The election may tell us...
If there is truth to this, then the other msm polls will begin to swing in a couple weeks or they will all be out of business forever. Even the Democrats won’t use them. So while they can use the polls to influence up to about Labor Day, after that it will be about the ones who “foresaw” the results.
Sorry, but if it’s not a scientific poll it’s basically worthless no matter how many respondents there are. Even with 100,000 people, there is no way to know if they are in any way representative of the electorate as a whole.
I am also suspect of the polls being fed to us by the media, but placing your faith in something like this is worse.
the most significant feature of this poll is that it was done using social media. I presume they used facebook or twitter, but regardless, the main users of social media are young users.
If Trump wins over these young voters then Hillary is truly in trouble.
This is a crazy election and a crazy electorate.
Is it an on line poll or phone calls?
What period of time?
100,000...how did the poll contact the respondents?
Oversampling of Rats by 15% no longer cuts it. They may have to double, or even triple it. Go TRUMP/PENCE!
A poll through an app Poll, is the same as an internet poll. It doesn’t matter that 100,000 people responded... Zip is an app you have to download it and it seems given the variety of questions any participant of zip can ask.... it’s mostly conservatives using it. Every question on social values or 2nd amendment right and Donald vs Hillary shows about 90+ towards the right.
If more dems or leftists start using zip, perhaps we can look at it as an indicator, but I will say the app is fun and certainly gives you a mood boost.
Social Media. Well, there’s the problem. Not everyone is on social media.
The problem is that it did in the outcome. Is it weighted for democrat, republican, independent and undecided? If so what are the parameters. I could not get the page to scroll down so I could not read further. On line polls are not very accurate historically. If they were then we have been betrayed by massive vote fraud for several elections now.