Page 4 - Sample Sizes News Today

With 100 or 200-person sample sizes and saying, oh, you know, hillarys going to win by a landslide was just ridiculous. what trump was trying to say was, im not going to believe this stuff. i continued to show mr. trump there was multiple paths to victory. >> you are feeling very confident. how do you draw the lessons that you learned from the campaign into the next administration? do you have a role in the next administration? >> at this point, im still working on the campaign, spending my time...

But those who show up at caucuses in particular and primaries as well are actually a subset, a relatively small subset of republicans. thats one reason. there are many. thats one reason why we see all of these variable results. >> so kaylee, you talk to a lot of republicans. what is the sense from republicans about these polls? which polls do they really buy into? >> you know, when you talk to republicans, you get an overwhelming sense that this is an outsider election. and i think that material...

Difficult. you have small sample sizes. you see wide swings on who is in the lead based on the sample. if you looked at the polls this week, one had ted cruz ahead in iowa by a significant margin. one had donald trump. if you dug into the statistics of why that is, one poll registered voters. one poll is likely who turns out. that is big in the early states. polls not capture it at this point. who will show up and vote? >> a lot of time ahead of us. >> tal, thank you. nice seeing you this mornin...

I think everyones heading to milwaukee next week. i will say, i asked him what point do you realize, look at numbers and say i dont have the juice to make it to new hampshire he says its going to happen after voters vote. he wants to see how iowa is, new hampshire. national polls are tough to move, these are small sample sizes. chris christie sounds like hes in it at least through new hampshire. >> it is interesting, maybe the drug issue hes been talking about so much now maybe might help him in...

I think its horrific, but he is not going to make it and donald trump is going to make it to that first stage. >> fox is saying that theyre going to run the kids table debate. it comes to a point in time and the eye balls and probably good for those participating. here is the other things you have those polls and the margin of error on the polls is all over the place. youre dealing with tiny sample sizes and no references. >> youre looking at 250 samples. its ridiculous. >> right. so you have th...

Traffic highway safety administration as it is of other agencies. theres got to be a moratorium on the work that people can do if they are in government, for industry, and vice versa. number three, you have a system in which gm or any company when it makes a settlement out of court with people who have had problems in this case with ignitions, they dont have to be reported back to the safety administration. so the safety administration doesnt even know very often about settlements. >> lets talk ...

But the fact is that politics has always been extremes, often flying in the face of what many experience as reality. the only difference now is that the extremes seem to be all that exists. we no longer share the facts upon which our opinions are based. because when multiple polls with scientifically accurate sample sizes all give the same numbers and are still questioned for accuracy or even when the bipartisan independent bureau of labor statistics which is firewalled from both the white house...

President obama took office. 42% say the country is worse off. ezra, anything jump out as you look at those numbers? >> you always have to be careful with battleground polling dealing with smaller sample sizes and brings higher levels of error. you want to see a number of them. in this election so far, the pattern has been that obama is stronger in battleground states than he is nationally. usually youre seeing the battleground polls return better than the national polls. the margin is a little ...

Way. can it not? >> yeah, race is clearly an important factor. i dont think on average we have the white population that high. no question that race is an important factor. so are the other variables. age is highly related to the context as well. so is education and gender and so is having a cell phone only or land line. all of these are important factors. our statusticians and methodologists have been doing this for a long time and take those into account and try to put our samples and give the...

It is based on 3,000 interviews with registered voters and we provide analysis based on 9,000 interviews based on three-week rolling average. we are able to give people a stable picture of whats happening with the race as opposed to other polls where we saw obama was ahead by 13 points. clearly an out liar and daily tracking with large sample sizes, we think that we are making a real contribution to understand the trajectory, the trend line of the race. >> its funny you bring up the out liar and...