Support for RKBA at highest levels

utbagpiper · Dec 11, 2014

This report out of the Pew Research Center is getting coverage in a lot of media. I like the article at NPR because it includes a nice photo of a Utahn (I presume) at a pro-RKBA rally at Utah's State Capital last year (2013).

Full article and photo at:

http://www.npr.org/blogs/thetwo-way...rights-outweigh-gun-control-in-new-pew-survey

Excerpt:

For the first time in at least 20 years, significantly more Americans say it's more important to protect the right to own guns than to control gun ownership, according to the Pew Research Center.

The survey found that more than half of Americans (52 percent) sided with gun rights compared with the 46 percent who favored gun control.

The findings represent the continuation of a shift that was only briefly interrupted by the Newtown, Conn., school shootings in 2012.

In April 2007, the Pew survey found only 32 percent of Americans said it was more important to protect the right to own guns, while 60 percent said it was more important to control gun ownership.

Charles

OC for ME · Dec 11, 2014

I'm confident that the numbers were worked to be as close as possible to each side without discrediting their own poll/survey.

Logan 5 · Dec 11, 2014

I read the article. I think the poll appears to be reasonably accurate.

utbagpiper · Dec 12, 2014

OC for ME said:
I'm confident that the numbers were worked to be as close as possible to each side without discrediting their own poll/survey.

On what basis do you believe the poll is anything but accurate on its face?

There are any number of potential problems with any poll, I'm just wondering if you've read through the poll itself or its methodology and can enlighten us. I haven't. But would be interested if others have and have seen something amiss.

Charles

J_dazzle23 · Dec 12, 2014

I'm actually studying for a statistics final right now, so this is a fun case study for me.

I looked at the methodology, and they had a 95% confidence interval. Basically this means if they did the study 100 times over, 95 of those times or better they would have the exact same results within a very narrow margin of error. It seems the data is normally distributed, unbiased, and independent. Unless I'm missing something it seems to be a very accurate survey.

*edit- it looks like they also used a weighted measurement as well to control non response bias, which is another good measure, imo.

davidmcbeth · Dec 12, 2014

J_dazzle23 said:
I'm actually studying for a statistics final right now, so this is a fun case study for me.

I looked at the methodology, and they had a 95% confidence interval. Basically this means if they did the study 100 times over, 95 of those times or better they would have the exact same results within a very narrow margin of error. It seems the data is normally distributed, unbiased, and independent. Unless I'm missing something it seems to be a very accurate survey.

*edit- it looks like they also used a weighted measurement as well to control non response bias, which is another good measure, imo.

You need to study more young man ... that is not what a 95% confidence interval means ...

J_dazzle23 · Dec 12, 2014

davidmcbeth said:
You need to study more young man ... that is not what a 95% confidence interval means ...

From my text:

"If independent samples are taken repeatedly from the same population, and a confidence interval calculated for each sample, then a certain percentage (confidence level) of the intervals will include the unknown population parameter. Confidence intervals are usually calculated so that this percentage is 95%, but we can produce 90%, 99%, 99.9% (or whatever) confidence intervals for the unknown parameter."

I'm NO statistician, and although I'm getting an A in the course, its by what I'm sure is a miracle. But I'm open to explanation if I'm incorrect. [emoji1] [emoji1] [emoji1]

*edit- actually, I'm more than open to it. I'd appreciate it. My final is on monday. LOL

Logan 5 · Dec 12, 2014

I think it depends on the poll, who took the poll and how they took it. That to me is my confidence level.
If Opencarry.org were to hold a poll here on their sight, there is a fair chance it would lean in the direction of Opencarry's views. Members could go in and make multiple votes.
Likewise with the Brady gun control groups.

On the other hand, if you have students in public taking either a door-to-door poll and an in-person poll (like at a mall), or hiring a pollster like RasmussenReports, Gallup, Zogby, Angus-Reid to do a telephone poll, you stand a fair chance of getting a more accurate results.

J_dazzle23 · Dec 12, 2014

Logan 5 said:
I think it depends on the poll, who took the poll and how they took it. That to me is my confidence level.
If Opencarry.org were to hold a poll here on their sight, there is a fair chance it would lean in the direction of Opencarry's views. Members could go in and make multiple votes.
Likewise with the Brady gun control groups.

On the other hand, if you have students in public taking either a door-to-door poll and an in-person poll (like at a mall), or hiring a pollster like RasmussenReports, Gallup, Zogby, Angus-Reid to do a telephone poll, you stand a fair chance of getting a more accurate results.

They reported it as a Random telephone poll, a mix of home phones and cell phones. Seems like, after looking at their site, it's a well respected group that prides in their polling and statistics accuracy.

It seems legit to me, but like I said earlier, I'm fairly rudimentary in my statistics knowledge so my opinion may not be worth much, lol.

Logan 5 · Dec 12, 2014

Ok. I'll look at it again.

To the best of my knowledge "confidence interval" means that if the poll is re-done they expect the same results 95% of the time. Doing polls is different than doing statistics, though they are used to create statistics.

OC for ME · Dec 12, 2014

utbagpiper said:
On what basis do you believe the poll is anything but accurate on its face? ...

What states were called, what area codes?

About the Survey

The analysis in this report is based on telephone interviews conducted December 3-7, 2014 among a national sample of 1,507 adults, 18 years of age or older, living in all 50 U.S. states and the District of Columbia (605 respondents were interviewed on a landline telephone, and 902 were interviewed on a cell phone, including 513 who had no landline telephone).

A link to the raw data should be provided for this poll along with the questions asked.

The combined landline and cell phone sample are weighted using an iterative technique that matches gender, age, education, race, Hispanic origin and nativity and region to parameters from the 2012 Census Bureau’s American Community Survey and population density to parameters from the Decennial Census.

In addition to sampling error, one should bear in mind that question wording and practical difficulties in conducting surveys can introduce error or bias into the findings of opinion polls.

http://www.people-press.org/2014/12/10/growing-public-support-for-gun-rights/

I hold little faith in any poll, public or private, other than the results of the vote.

OC for ME · Dec 12, 2014

OC for ME said:
What states were called, what area codes?A link to the raw data should be provided for this poll along with the questions asked.

I hold little faith in any poll, public or private, other than the results of the vote.

Can you spot the flawed premise in the below?

Currently, 52% say it is more important to protect the right of Americans to own guns, while 46% say it is more important to control gun ownership.

But, I'm biased because I know what the B stands for in RKBA.

For example, re questions and their construction.

An example of a wording difference that had a significant impact on responses comes from a January 2003 Pew Research survey. When people were asked whether they would: “favor or oppose taking military action in Iraq to end Saddam Hussein’s rule,” 68% said they favored military action while 25% said they opposed military action. However, when asked whether they would “favor or oppose taking military action in Iraq to end Saddam Hussein’s rule even if it meant that U.S. forces might suffer thousands of casualties, [and save hundreds of thousands of innocent lives in Iraq]” responses were dramatically different; only 43% said they favored military action while 48% said they opposed it. The introduction of U.S. casualties altered the context of the question and influenced whether people favored or opposed military action in Iraq.

http://www.people-press.org/methodology/questionnaire-design/question-wording/

http://www.people-press.org/methodology/

Overly complex questions to a binary premise. I added the blue.

Polls will reach the conclusion desired by the pollster.

PeterNSteinmetz · Dec 13, 2014

OC for ME said:
Polls will reach the conclusion desired by the pollster.

I think that one of the strengths of this result is that the same questions have been asked for many years with roughly the same sampling methodology. So the shift to more support for gun rights likely represents a real result.

utbagpiper · Dec 14, 2014

OC for ME said:
I hold little faith in any poll, public or private, other than the results of the vote.

While it is easy enough to manipulate polls, it is also possible to create and conduct polls that do a very good job of telling us where a population stands on various issues. Or perhaps more importantly, how an issue will influence their votes.

If you have actually studied this poll I'd like to know what you've learned. If you are simply trying to glean too much from a news article about a poll, I think you may have missed the boat.

Charles

OC for ME · Dec 15, 2014

utbagpiper said:
If you have actually studied this poll I'd like to know what you've learned. If you are simply trying to glean too much from a news article about a poll, I think you may have missed the boat.

Charles

Back-handed insult is noted. There are links in the article that lead to the Pew website, there are links there as well.

Pew should provide the raw data. What are states/area code of those who responded?

ASK ALL: Q.53 What do you think is more important – to protect the right of Americans to own guns, OR to control gun ownership?

ASK ALL: Q.55 Do you think that gun ownership in this country does more to [INSERT OPTION; RANDOMIZE] or does more to [NEXT OPTION]?

Dec 3-7 2014
Protect people from becoming victims of crime
Put people’s safety at risk
Don’t know/Refused (VOL.)

http://www.people-press.org/files/2014/12/12-10-14-Guns-release.pdf

Q.53 - The above is a bogus question. Q.55 - Vague options except the last.

utbagpiper · Dec 20, 2014

OC for ME said:
Back-handed insult is noted.

I think you're being overly sensitive. No insult was intended.

Charles

utbagpiper · Dec 20, 2014

PeterNSteinmetz said:
I think that one of the strengths of this result is that the same questions have been asked for many years with roughly the same sampling methodology. So the shift to more support for gun rights likely represents a real result.

Very good point.

Thank you.

Charles

J_dazzle23 · Dec 20, 2014

OC for ME said:
Back-handed insult is noted. There are links in the article that lead to the Pew website, there are links there as well.

Pew should provide the raw data. What are states/area code of those who responded?

Q.53 - The above is a bogus question. Q.55 - Vague options except the last.

I don't know if you actually were able to the full report- the phone numbers were randomly selected in 50 states.

The analysis in this report is based on telephone interviews conducted December 3-7, 2014 among a national sample of 1,507 adults, 18 years of age or older, living in all 50 U.S. states and the District of Columbia (605 respondents were interviewed on a landline telephone, and 902 were interviewed on a cell phone, including 513 who had no landline telephone). The survey was conducted by interviewers at Princeton Data Source under the direction of Princeton Survey Research Associates International. A combination of landline and cell phone random digit dial samples were used; both samples were provided by Survey Sampling International. Interviews were conducted in English and Spanish. Respondents in the landline sample were selected by randomly asking for the youngest adult male or female who is now at home. Interviews in the cell sample were conducted with the person who answered the phone, if that person was an adult 18 years of age or older.

I'm not altogether sure what "raw data" you are referring to that you need. It has nearly everything in the study report.

Studies can be manipulated, sure. But this particular one seems to have their ducks in a row with their methodology. Confidence intervals and sampling error bias seem to be exactly where they should be for an accurate extrapolation on what the general public thinks about the topics polled.

davidmcbeth · Dec 20, 2014

OC for ME said:
Back-handed insult is noted. There are links in the article that lead to the Pew website, there are links there as well.

Pew should provide the raw data. What are states/area code of those who responded?

Q.53 - The above is a bogus question. Q.55 - Vague options except the last.

Q 53 should have been 2 different questions. For sure.

Support for RKBA at highest levels

utbagpiper

Banned

OC for ME

Regular Member

Logan 5

Regular Member

utbagpiper

Banned

J_dazzle23

Regular Member

davidmcbeth

Banned

J_dazzle23

Regular Member

Logan 5

Regular Member

J_dazzle23

Regular Member

Logan 5

Regular Member

OC for ME

Regular Member

OC for ME

Regular Member

PeterNSteinmetz

Regular Member

utbagpiper

Banned

OC for ME

Regular Member

utbagpiper

Banned

utbagpiper

Banned

J_dazzle23

Regular Member

davidmcbeth

Banned