Firearms and Self Defense

G

ghbucky

New member
Serious question:

Who answers random people about rather they own guns and have used them in self-defense?
 
E

eflyguy

New member
lol..

Like TV ratings and such - nobody has ever asked me. 54k is a pitiful sample of educated and active shooters.
 
O

OldMarksman

Staff
54k is a pitiful sample of educated and active shooters.
Click to expand...
I do not think I agree. That number seems quite sufficient to me.

My problem is with their defining incidents that do not involve the display of firearms as defensive gun use incidents. I think it likely that that exaggerates the numbers.

When I stumbled into a store robbery about to happen around a decade ago, I moved into position to defend agains the robber, and my action caused him to bolt and run. I was armed and ready, but I did not have to draw.

I do not consider that to have been a defensive gun use.
 
O

OldMarksman

Staff
So you were polled by this company?
Click to expand...
No.

That means nothing.

The sample size is far larger than samples that are commonly used in the making of major investment and marketing decisions that can seriously affect the financial performance of companies

The methodology is described in detail in the report.

By the way, the details indicate to me that my concern about the numbers having been skewed was overstated. Numbers for different kinds of encounters are compiled separately.

I have displayed firearms when threatened in the house by violent criminals on three occasions--over quite a long period.
 
D

DaleA

New member
Lies, damn lies, and statistics---a quote used many times in this forum.

Is 54K enough for a survey?

I can remember way, way back to a basic statistics class where some proof was offered that 1500 samples was adequate to predict failure rates when it was something like light bulbs or nuts and bolts or cans of pop or aspirin tablets...check 1500 of 'em and you'll have a pretty good idea of what your failure rate is going to be.

"The above info is for things when all the things are the same. For people it's more complicated," says Captain Obvious.

For people you have to know the make-up of your total group and get valid representation from each group that matters. That is, you don't need to poll guys if it is a product only gals use. This gets tricky (again a statement by Captain Obvious) and that's why legit surveys cost a lot to do. Really good pollsters that know what they are doing don't need a huge number of responses if they can get the representative responses.

How many people would you have to poll and how do you determine and get real answers from the representative people? Goodness, it was ONE statistics course years and years ago and I'm lucky I remember the 1500 number for the light bulb failure survey.

Also, as I've said many times, I know quite a few people that lie to pollsters just for sport.
 
O

OldMarksman

Staff
Is 54K enough for a survey?
Click to expand...
It is HUGE in comparison with the survey populations that have been used in the past for supporting critical decisions. A revolution in technology has made that practical.
....some proof was offered that 1500 samples was adequate to predict failure rates when it was something like light bulbs or nuts and bolts or cans of pop or aspirin tablets...
Click to expand...
Entirely different animal. And, of course one has to specify the desired confidence level.

For people you have to know the make-up of your total group and get valid representation from each group that matters...How many people would you have to poll and how do you determine and get real answers from the representative people?
Click to expand...
The Kinsey Report, which addressed far more variables than the one at hand, was based on a sample size of 300.
 
E

Ed4032

New member
It is worthy of discussion. If it’s ten percent true then it may just be all the new gun buyers are actually reflected.
 
S

stinkeypete

New member
The entire validity of any survey is determined by using a chance mechanism to elicit responses from an unbiased random sample of the population.

That's really hard to do. How are you going to get a broad section of the population to honestly self-report, to strangers.

Maybe you go to gun shows and get people to answer. Maybe you go to Vegan cooking classes. Maybe the survey imparts bias by it's questions.

Surveys are basically useless. The outcome is.. there are a lot of guns out there. I believe that part.
 
R

rodfac

New member
The Kinsey Report, which addressed far more variables than the one at hand, was based on a sample size of 300.
Click to expand...
And Kinsey's bizarre skewed results have been widely criticized for the researcher's biases.

To trust a poll, you must place an inordinate trust in the pollsters themselves as well as their professional qualifications to conduct the research. Not to mention the questions of who funded the project, who are included in the sample and their truthfulness, and to what purpose are the results to be used.

The sheer number of variables in the above questions, has, long ago, destroyed any faith I have in the "?science?" of polling. For those who retain their faith, I point to the last 5-6 pre-presidential elections for the accuracy of the polling.

P.T. Barnum, often quoted, once opined that, "there is a sucker born every day". I'd agree with his amateur polling analysis. YMMv Rod
 
S

stinkeypete

New member
Maybe people don’t understand the internet. It’s basically paid for by advertising.

A lot of money goes into targeted advertisements. That means some companies get paid to sell other companies lists of names and what that person is like so that advertisements can be directed at them based on what they are likely to purchase.

One of the oldest tricks in the marketing book is the “fake survey.” It’s a couple chapters in marketing books.

Doing a decent REAL survey is a couple of statistics classes and a couple PhDs to really understand and do well. Just because you can’t do it doesn’t mean it can’t be done.

Another of the most basic marketing game is “tribalism”. Get people to buy stuff based on status, or fitting in. People are not good at rational decision making.

Example: far more people die each year due to tick bites than bear attacks, yet count the number of threads here on Permethrin vs. Products to one-shot-stop bears. Men don’t seem to derive status from talking about the clothes they wear in the field unless you look like you’re constantly Turkey hunting, or look like a lost member of a SWAT unit.

People buy camo colored flashlights. Think about all The ways that is wrong.
 
4

44 AMP

Staff
As I see it, the problem with polls is that they rely on a number of factors that are not givens, and that the results are accepted and treated as if they were a truly representative result, when such is not necessarily the case.

One of the basic problems is that people are NOT a homogenous mixture. We are individuals, who may or may not be found in groups of people with similar opinions and experiences.

Think of it as a chemical make up tank without being stirred. All the different chemicals are dumped in, but they are not stirred and properly mixed to a uniform content.

Sample size and LOCATION make a difference in the result. Sample 1oz in one spot and you get one result. Sample 4oz in that same spot and you MAY get a different result. Sample in a different spot and you may get yet anther and different result.

Sample 1,000 or 50,000 in the urban metro areas and I'm willing to bet your results will be different than sampling the same number of people in rural areas.

Another thing about surveys, which is not found in chemical sampling, chemicals don't lie to throw off your survey.

People do.
 
S

stinkeypete

New member
In my intro stats class these issues had names:
Random Sample
Representative Random Sample
Self Reporting

You also need to watch out for various Survey Biases.

I know it’s not the popular thing in some circles, but education is good.
 
You must log in or register to reply here.
Top