Previous Post
Next Post


In the aftermath of a certain incident involving a 9-year-old and an Uzi, the usual gun control extremist suspects have been shopping around the idea that firearms and children are a bad combination. As we know from our own polling, over 50% of TTAG readers started shooting before the age of 11 years old. Huffington Post seems to think that’s a terrible idea, and so produced an equally terrible poll to promote their agenda. Why is it a terrible poll? Mainly because it breaks the one golden rule about how to conduct a survey in a statistically valid manner . . .

Here’s Huffpo’s conclusion:

According to the new poll, only 26 percent of Americans think it’s appropriate for a child under 10 years old to learn how to fire any kind of gun under supervision at a shooting range, while 63 percent said that is inappropriate. Only 7 percent said that it’s acceptable for a child under 10 to fire submachine gun like the Uzi, while 86 percent said it’s inappropriate.

In fact, an earlier HuffPost/YouGov poll, also conducted after the shooting, found that the median age at which Americans think it’s appropriate for someone to learn how to fire a gun is 16. That poll found variation along party lines on the median age listed as most appropriate — Republicans said 14, independents said 15, and Democrats said 18.

That would be an interesting result — assuming that you ignore the source of the polling information.

The HuffPost/YouGov polls were conducted Aug. 28-Sept. 2 and Sept. 4-8 among 1,000 U.S. adults using a sample selected from YouGov’s opt-in online panel to match the demographics and other characteristics of the adult U.S. population. Factors considered include age, race, gender, education, employment, income, marital status, number of children, voter registration, time and location of Internet access, interest in politics, religion and church attendance.

The issue I have with their methodology is that it breaks the golden rule about conducting a survey. A good survey requires a randomized sample of people from the population in question. There was nothing randomized about their survey.

There’s an inherent bias that comes with using a self-selecting group of people in any survey. The point of the exercise is to get a randomized group of people to respond to a question, and the most effective way to do that is by cold-calling people over the phone. It’s still not ideal, but it’s better than anything else out there at the moment. By using a website and its members for responses instead of a randomized group, you no longer get an accurate sample of the population. Rather than sampling the American public, all you’re really sampling are the users of that website.

Websites tend to become an echo chamber. People will gravitate toward sites that line up with their viewpoints, and it makes sense that a poll pulled from the Huffington Post’s readership will attract users who agree with their self proclaimed crusade to eliminate American gun ownership. So while I fully believe that most of HuffPo’s users really do think kids and guns don’t mix, I do not believe for a minute that their sample is a representative slice of the American population.

According to HuffPo’s methodology, it would be equally valid in saying 100% of Americans are against an “assault weapons” ban or magazine capacity restrictions based on our own survey, especially since our sample size was four times greater. But I know better, since I passed high school statistics.

Previous Post
Next Post


  1. My 3 three old will sit on a cooler behind me with his eyes and ear pro on to watch me shoot. He loves it for some reason, he just sits and watches as my wife and I transition from watching him to shooting. Probably the only time he is calm and self controlled.

    • My 6 year old sits behind me with a pair of binoculars watching me shoot in service rifle competition. He is counting the years until he is old enough to join dad in the fun. He does like to help me clean the rifle afterwards. He has been going with me to the range since the age of 3.

      The worst thing he has done at the range was to go swimming fully clothed in a large puddle. Luckily I had a full change of clothes for him in the car.

  2. 320 million people living in America (give or take), used a sample size of 1000 for any survey…. Sounds legit.

    Their survey sampled 0.0003125% of the total population. That’s totally reasonable to extrapolate to represent all of America right?

    • As Nick mentioned, the real problem with this data set is not the size of the sample, but that that sample population was “selected from YouGov’s opt-in online panel”.

      Selection bias is a problem they cannot control out of the data. The folks that opt-in to stuff on a single web site are not necessarily randomly representative of the population at large.

    • It’s actually quite reasonable, given a truly random sample. The smaller the sample size is in comparison to the population, the larger the error factor (that ±X% you see next to the poll numbers). And the only way to get that to zero is to sample the entire population.

      • on the contrary.
        the correct survey method can be more accurate because compilation erors can easily exceed sampling errors.
        sampling a few thousand v 320 million

        • You are correct that compilation errors do increase with the size of the sample.
          But that’s a different error. He was talking about sampling errors, which are proportional to the difference between the population and the sample size.

  3. Or
    Even 26% of rights-hating HuffPuff readers believe that a child under 10 should be allowed to learn how to operate a firearm, and 10% of those statist zombies think it’s appropriate to teach a child of that age how to use a submachine gun.

  4. Another anti-gun hit piece designed to use bent polling results to create predetermined results.

    Open kids young eyes about shooting; start ’em young, show and teach ’em the right way, trust but verify.

  5. I wonder what they think DOES mix well with guns? We already know it’s none of the things we believe in (liberty, self defense, personal accountability, etc.) so what on earth could it be?

    • They’d probably like guns with a secret government police force to ensure you always live in your government approved Cabrini Green style housing and rode the government approved cattle cars….er trains to get around. 100% of SnuffPo readers would say that mixes well.

    • Something along the lines of checking your trap gun in and out of a government controlled locker to shoot a round of environmentally safe frozen water “clay” birds way out in the middle of nowhere.

  6. Most Americans that voted thought it was a good idea to continue the failed experiment of Obama in 2012 too.

  7. Hmmm…in between watching the BEARS win I caught Miss America. A “judge” asked one of the gals if after the 9year old range killing if kids & guns mixed. Of course she said NO. PC & all that s##t. Huff is irrelevant…

    • Yeah, I saw that, really turned me off on her, When they finished asking the question, I was hoping she would be one of the POTG, No such luck!

  8. BREAKING NEWS: Leftist media submits poll to leftist media-watching participants.

    I’d bet sharing the demographics of the participants of said “poll” would murky the water quite a bit, here.

    In other words, clearly, the results here are unbiased. (/sarc)

  9. Misspelling in headline.

    HuffPo… They are akin to a toddler believing that something isn’t there just because they put their hands over their eyes and can’t see it.

    Unfortunately for the paint sniffers over there, there’s a whole lot of gun rights activists and gun owners on our side who are making damn sure kids get infected with the fun and excitement of shooting sports.


    • “…there’s a whole lot of gun rights activists and gun owners on our side who are making damn sure kids get infected with the fun and excitement of shooting sports.”

      Agreed, Sir.

      Just saw a Boy Scouts of America commercial last night. Sure enough, they were shooting at clay birds with what looked like a 20 gauge, right there on the commercial. Showed the bird busting and a kid racking a shell out. Good stuff, there.

      The real question is: how many states aired the “revised” BSA Commercial, minus the shotgun and clay bird scene. Lol

  10. Now if you want a valid poll of what Americans think about kids and guns, look at the sales of toy guns – including all of the water guns, AirSoft, Leggo, and millions of other toy guns sold every year to PARENTS for their kids. That will give you a far more accurate number of Americans who “think it’s appropriate for a child under 10 years old to learn how to fire any kind of gun”.

    And please, don’t give me that “those are toy guns, not real guns” BS – the left has been trying to convince parents that toy guns are the same as real guns, because they “promote violence among children”. Look at the school districts with their “zero tolerance” policies, where a kid chewing a pop-tart into the outline of the state of Idaho is expelled because he “held it like a gun”.

  11. I once answered a poll from YouGov. The questions were slanted to get the desired results the the poll wished to obtain. I was invited to take another and quit answering when questions could almost pinpoint my identity and location. I still get email from them to answer polls, I don’t.
    I did not know they were the shill of Huf-Post. Now I do.

  12. Even if most Americans don’t think they mix, again, it’s an uneducated decision they are making. Here’s another one:

    Should all school buses be required to have seat belts?

    For those that don’t know, there are actually various arguments that argue that NO, they should not. But why not? Common sense (that phrase the antis love so much) tells any moron that seatbelts on a school bus are a good thing, right? Well, it depends, as there are various ways that seat belts on school buses can be more dangerous for kids.

    So questions about things like kids with guns, the average American is probably not qualified to answer.

  13. I don’t care about polls. I do care about laws, laws that are respectable and laws that are not. Knowledge of gun safety and operation of firearms are the business of myself and my child. Not the state or US government. There are two kinds of criminal – those that break the law because they don’t respect the law and those that break the law because those laws merit no respect. If a law were proposed to address this – it would fall in the latter.

  14. So what you’re telling me is that 26% of HuffPost readers don’t think kids and guns mix… That’s honestly kind of surprising. I’d imagine it would have been lower.

  15. This just in…!!!

    New HuffPo polls shows that 99.3% of Americans read and like the Huffington Post.

    Note: Poll accounts for a .7% margin of error.

  16. Who cares about what Huff Post says? Pravda and The Weekly World News printed lies that were much more entertaining.

  17. Lefties love any poll, using any method, that they can add to their echo chamber. As an (extremely right wing) independent thinker, I have no need of polls to arrive at a conclusion.

    Also, there are millions of shooters who happen to be under 18 who *haven’t* killed anyone with an Uzi. Lefties love gun accidents because they get to focus on what goes wrong with firearms, and interject their “expert” opinion: ban firearms. And for God’s sakes, we need more laws. Lots more. Because you’re less dead if you die doing something illegal.

  18. Most Americans buy their kids toy guns, video games that have guns, let them watch cartoons, tv shows and movies with guns so HuffPo is full of crap as are any parents who do the things I listed yet vie for gun control.

  19. Does this mean that it is so difficult to get the results they want that they have to resort to such an obvious biased methodology? Or are they simply that lazy?

  20. Self-selection surveys are insidious bastards. Not only are they biased towards the source readership – such as 95% of TTAG readers don’t believe in gun control – but they are easier and cheaper to conduct. Hey folks, take our website survey! These aren’t issues for people who want to use statistics to deliberately mislead people, such as the liberal progressive left.

    Many simply throw up their hands and say that you can prove anything with statistics. However, a study properly conducted has great value. Most people just don’t do them these days because they cost more, and the results might not agree with the politics of those running the study. Climate scientists, for example, are well known for disregarding data which holds to their religion of global warming. While people such as me would argue that the expansion of polar ice would mean that we are not on the precipice of an ecological disaster.

  21. I was taught to shoot at 8 yrs old, my brother and two sisters, my children and their childen and on one has shot themselves or anyone else yet. Funny, this was one of those YOUGOV polls I didn’t receive. But not that I answer them anyway.

  22. Didn’t CNN have a similar poll? It was in the international web page, way down at the bottom. What I recall was either the updates were very slow or not being counted.

    • The Puff Ho’s:

      Nieman Labs:

      “The site initially received tepid reviews and has been criticized as shallow, predictably liberal, breathless, sexist, plagiaristic, and a parasitic.”

      Bill Keller, past editor of the New York Times:
      “The queen of aggregation is, of course, Arianna Huffington, who has discovered that if you take celebrity gossip, adorable kitten videos, posts from unpaid bloggers and news reports from other publications, array them on your Web site and add a left-wing soundtrack, millions of people will come. “

  23. AHa! Here is where the antigunners are focussed- in trying to destroy gun culture by making children and guns taboo! It explains a lot about where the branding of Moms Demand Action is heading, trying to divide families and conquer.

    • Yep, no one cares more about kids than Moms Demand Action!

      They have the moral high ground because they’re…well…moms.

      Dads don’t count.

      Used to be the role of dads in a family was to help prepare children to move out into the world, beautifully counterbalancing the role of moms in providing reassurance and a warm hearth.

      Dads were also considered the protector and guardian of the family.

      Now, men are considered generally…well…irrelevant by Leftists.

      Unless, of course, you are a New Age Sensitive Guy. Then you’re totally cool.

  24. When I was 7, my Dad let me shoot his BSA.22 single shot rifle. I don’t remember whether I was aiming at anything, most likely my short sightedness prevented it, but I did enjoy it. My brother wanted to do most of the shooting! That Christmas we got matching plastic Winchester rifles which shot plastic bullets (weakly). Best Christmas ever. I should say my Dad was an avid deer hunter in his youth.

    At 13 my cousin let me shoot a shotgun at some rabbits on their farm. I never noticed the recoil in the excitement. Again, my eyesight let me down. I walked around a gorse bush, and found a rabbit sitting down 10 feet away, looking at me. The gun was broken, and I didn’t have fast enough reactions to lift it up, close it up and shoot in time. Lucky rabbit.

    I had to wait until I had a cataract operation before getting into firearms as an adult. I wonder why I waited so long. The early experience as a child in no way deterred me from considering owning a firearm. That plus the frequent Westerns on TV, made firearms an integral part of an ordinary lifestyle.

  25. They should confine the poll to gun owners. Asking the gun-ignorant what the appropriate age is for learning to shoot is like asking the Amish what an appropriate age is for military service.

  26. So what. There was a time when most Americans thought that races shouldn’t mix and that interracial marriage should be illegal. It wasn’t all that long ago that most Americans thought homosexuality should be criminalized. Even today most Americans think that illegal aliens should be deported.

    Rights are not subject to popularity or to a vote. That’s why we have a constitutional republic, not a democracy.

    Do you really want a society where the majority gets to oppress the minority? I don’t.

    • Even today most Americans think that illegal aliens should be deported.

      Um, yeah. They should. What’s wrong with deporting people who have entered our country illegally?

  27. Sorry to disagree, but I worked for many years at a phone polling research center and I still do data analysis for a living. Phone based surveys are now useless. With caller ID and cell phones, only one kind of person answers and does surveys, old lonely people who still have landlines. That is as far from a random sample as you can get. Using an online subject pool allows you to get much closer to a representative sample because you can choose the demographics of the sample frame. There is never a truly random sample, that would be impossible.

    • One more kind of person who answers phone polls, would be someone who shares my belief that we all have a moral duty to lie to pollsters. I LOVE answering their questions, making it all up as I go along. If enough of us lied consistently on polls, we could eventually put all of the polling companies out of business. Then maybe the politicians would have to tell us what they really believe, instead of what they think the majority wants to hear.

      LIE! to the pollsters! It’s your civic duty!

Comments are closed.