Associated Press: Rasmussen poll does not call cell phones, explaining dubious 50% Trump approval

[Upstate One]

80% percent of respondents to the Rasmussen poll use landline, a demographic that skews Republican.

The rest are pulled from an online panel. No cell phone users are contacted.

https://apnews.com/59ef870461a8417daf4ffc71dc331d4c

[ProudLib72]

1. Good. This is what I always thought was happening

Calling the troglodytes in their caves via string and tin can.

[fleabiscuit]

2. One has to go to 538 to get the straight talk.

They never did have trump that high.

Currently the orange manic is sitting at 54.0%Disapprove / 40.0%Approve

[procon]

3. LOL - its a geezer poll! No wonder Trump like it. nt

[dsc]

4. that may, or may not, be a problem

Rasmussen wasn't forthcoming about what it does, which is actually a bigger problem in my mind, but there are ways around this. Some young people can be contacted on land lines (either due to living in a house with one or having one themselves) and there is no reason to believe they are significantly different from the young people who don't have them. Two, they could use the online panel to make up for it. But since they aren't saying what they do, it is fair to have suspicion of the numbers they produce. A reasonable explanation for their out of whack pro Trump numbers is that they over sample the old and under sample the young. Even when you account for that via weight, you have the problem of a small sample possibly being unrepresentative.

[pnwmom]

11. Actually, there is a reason to think that people with no cell phone are different

than people with one. That's why the more reliable firms deliberately include a significant proportion of cell phones in their sample.

http://www.pewinternet.org/2008/05/24/polling-in-the-age-of-cell-phones/

Polling in the age of cell phones
BY LEE RAINIE, JONATHAN BEST AND EVANS WITT

Introduction
In the past few years, the growing number of Americans living in households without landline telephones has challenged survey researchers to develop a variety of approaches to deal with this non-coverage issue. One approach is to add interviews over the cell phone to traditional random digit dial surveys of landline telephones.1

Adding cell phone interviews attempts to include people who cannot be interviewed via landlines, i.e. those without landline phones, particularly younger Americans. The major reason this is done is to seek as complete coverage of the population as possible. The secondary reason for these efforts (which can add substantially to the costs of surveys) is that those who are not covered may, in fact, differ from those reachable via landline on the key variables being studied. Findings from the National Health Interview Survey have provided a detailed look at the issue.

[Cha]

5. Not too many peeps

I know have a landline.

[mercuryblues]

8. Me either

My daughter gets a basic cable package and it included a free phone line. I was watching TV with her and the caller ID came across the screen. She said. Even if I had a phone, I wouldn't answer that.

One of my sons, when he lived at home refused to answer the house phone. All his friends call him on his cell.

Not a 1 of my kids, nieces, nephews, & their friends, have a house phone. Just like my son & daughter, even if they have access to one they don't use it.

[yardwork]

15. I'm in my 50s and we don't have a landline.

My mother, in her 80s, doesn't have a landline. My sons, in their 20s, have no landlines.

The only demographics I can think of that are likely to have landlines are older people who have lived in the same house for a long time, and maybe suburban stay-at-home moms. If Trump has only 50% approval in those groups, he's in big trouble.

[mercuryblues]

16. Hey, I still have a land line

But you are right. We have lived here for 20 years. But the biggest reason is I can't keep up with my cell. I really hate it when I leave it somewhere and the battery has gone dead. Good luck finding that still in my jacket pocket or in the car console, sofa cushions etc.

I am getting better at keeping up with it. Practicing for when we move.

[RandySF]

6. My experience with Rassmussen.

They called me during the 2012 election year. First question I got was right direction/wrong track, and disconnected as soon as I hit the keypad for Right Direction.

[Wellstone ruled]

9. Rassmussen Polling

apparently works the same call sheet . And yes they tend to call only Republican Registered Voters.

[David__77]

7. I believe that Rasmussen intentionally skews right.

And then corrects polls closer to Election Day.

[mr_lebowski]

10. There is no more 'fundamental' aspect to the process of using samples to predict population ...

Than the concept of 'random sampling'.

The moment your methodology of sample collection veers in ANY WAY from being 'truly random', any extrapolations from your data essentially become meaningless. It doesn't matter what kind of 'weighting' you apply to make 'adjustments', those are just masking the fact that your data is SHIT to begin with.

Without truly random surveys, you get Garbage-in, Garbage-Out, period.

Rasmussen's polls are NOT based on random sampling, therefore they are shit.

[beachbum bob]

12. I never pay attention to polls like rasmussen, ever

its a waste of time. I look at special election results. That is the real poll

[Blue_true]

13. Explains things.

But let Trump and his supporters keep deluding themselves, November will wake them up.

[yardwork]

14. Well, that explains a lot.