Skip to main content

This article describes some original research I have done on gun sales, gunshot injuries, and gun policy in America.  This article is critical of current US gun policy, and gun enthusiasts may want to avoid reading this article as it presents some facts and figures that shows our current gun policy in a negative light.

I realized that I have by this time written a couple of different articles about guns in America, and interested readers can review these post if they want.  On guns and the “stand your ground” laws here (http://www.dailykos.com/...); on statistics about gun injuries here (http://www.dailykos.com/...); on gun availability and gun violence (http://www.dailykos.com/...); on civil rights and guns here (http://www.dailykos.com/...), and on how corporate profits and guns here (http://www.dailykos.com/...).  

In the past four weeks we have learned of public mass murders in Aurora, CO. (12 dead), Oak Creek, WI. (6 dead), College Station, TX. (3 dead), the shooting of four police officers in LaPlace LI, (2 dead),  and a highly-publicized daylight mass shooting on the streets of New York City.  The rash of high-profile, highly murderous public shootings has many Americans asking questions about gun violence in our society: what causes these deadly events, and how do we prevent more needless public slaughter.  As with motor vehicle accidents and cigarette use, gun violence can be viewed as a problem of public health, and then the methodologies of public health can be employed to understand the problem empirically, and to suggest rational solutions.  Based on a public health perspective, I undertook a longitudinal examination of gunshot injuries and gun sales.  I wanted to look at overall trends in gun sales and gun injuries, and to see if there was any linkage between gun sales and injuries.

The Center for Disease Control (CDC) keeps a databank on injuries and fatalities in the US.  I collected the yearly data on fatal and non-fatal gunshot injuries, both intentional and non-intentional, for both sexes and all ages.  This data includes gunshot injuries resulting form criminal acts, shootings by law enforcement, unintentional shootings, and suicides.  For purposes of comparison, I also collected data on injuries to American bicycle riders during the same period.  I chose injuries to bicycle riders as a comparator because bicycles, like guns, are very popular and ubiquitous in the US, but unlike guns, bicycles are not sold as tools to injure others.  For data on gun sales, I used data from the FBI's National Instant Criminal Background Check System (NICS).  The FBI NICS was started in 1999 to provide a way for federally licensed firearms dealers to instantly determine if a prospective gun buyer is eligible to buy a gun or explosives.  Anytime a federally licensed firearm dealer is preparing to sell a gun to a customer, the dealer is required by law to make an inquiry to the FBI NICS: it is important to note that the inquiry does not indicate that a gun was actually sold.  So the FBI NICS data is not a direct measure of gun sales, and only tracks transactions taking place at federally licensed dealers, and not those taking place at unlicensed dealers, guns shows, private sales and the like.  I have chosen to use this data as a surrogate for gun sales because: 1) the FBI is a non-partisan and nationally recognized organization with extensive experience collecting statistics; 2) the FBI NICS data covers the nation as a whole and is available every year back to 1999; and 3) I can find no better source for good reliable data on US gun sales.  Because the FBI NICS data only involves prospective purchases at federally licensed firearms dealers, and not transactions  made through non-licensed dealers and private sales, the NICS data is widely acknowledged to underestimate national gun sales and therefore provides a very conservative measure of actual guns sales.  The data on gun injuries and NICS data were then examined for trends and correlations.

While far and away more people are injured every year using bicycles than guns, gun injuries are far more likely than bicycle injuries to be fatal: the crude (non age-adjusted) death rate for bicycles for the period 1999 – 2009 was 2.8 persons per 1 million, while the crude death rate for guns during the same period was 103.2 persons per 1 million.

The data on gunshot injuries in the US from 1999 to 2009 shows a clear and steady increase in both fatal and non-fatal gunshot injuries, rising from a low of 28,000 fatal gunshot injuries in 1999 to over 31,000 gunshot fatalities in 2009 (the last year for which data is available).  The data on non-fatal gunshot injuries shows a similar pattern.  This same pattern is also observed in the FBI NICS data; from a low of 8.5 million NICS inquires in 2000, steadily increasing to over 16 million inquiries in 2011, almost a doubling of transactions in a little more than ten years.  Interestingly, the data on bicycle injuries shows no such trend: both the numbers for fatal and non-fatal bicycle injuries jump around a good deal, without any clear overall increase or decrease.  A regression of injuries over time shows that bicycle injuries (both fatal and non-fatal) did not change significantly over time (Beta did not differ significantly from 0), while the variable for both gun injuries (fatal and non-fatal) and gun sales were all increasing significantly over time (Betas differed significantly from 0 and were all positive).  

Year - - - Fatal - - - Nonfatal - - -  Fatal - - - Nonfatal - - -  FBI
             Gunshot     Gunshot         Bicycle        Bicycle         NICS
              Injuries      Injuries         Injuries        Injuries         Data

1999 -     28,874 -                          800 -                       9,138,000

2000 -     28,663 -                          740 -                       8,543,000

2001 -     29,573 -     63,012 -          792 -       519,424 -   8,910,000

2002 -     30,242 -     58,841 -          767 -       505,233 -   8,454,000

2003 -     30,136 -     65,834 -          762 -       492,900 -   8,481,000

2004 -     29,569 -     64389 -           843 -       490,864 -   8,687,000

2005 -     30,694 -     69,825 -          927 -       481,205 -   8,952,000

2006 -     30,896 -     71,417 -          926 -       466,712 -  10,036,000

2007 -     31,224 -     69,863 -          820 -       495,500 -  11,177,000

2008 -     31,593 -     78,662 -          893 -       494,003 -  12,709,000

2009 -     31,347 -     66,769 -          785 -       519,736 -  14,033,000

2010 -                     73,505 -                         516,912 -  14,409,000

2011 -                                                                        16,454,000

I performed a correlation to look for any association of guns sales with gun injuries.  The FBI NICS data and fatal gunshot injuries were highly correlated (Pearson's r = 0.741), and this measure was highly statistically significant (p = 0.009).  The FBI NICS data and non-fatal gunshot injuries were also highly correlated (Pearson's r = 0.645), and this measure was also statistically significant.  (For those interested in this kind of thing, the Pearson's correlation coefficient – r – is a measure of how closely two variables move together.  A Pearson's r of 1.0 means that any change in one variable is perfectly mimicked by a change in the same direction of the other variable, while a Pearson's r of 0.0 means that a change in one variable is completely unrelated to changes in the other variable.  Pearson's r can take negative values from zero to -1, indicating that two variable move in congruent fashion, but in opposite directions).

The results of this study show unmistakeably that: 1) gunshot injuries, both fatal and non-fatal, have  increased steadily over the period studied; 2) guns sales as modeled by the NICS data have likewise risen steadily since this record was initiated; and 3) there exists a tight linkage between gun sales and gunshot injuries, especially for fatal gunshot injuries.  The statistics on bicycle injuries over this same period show no overall increase or decrease.  

That gun sales and gunshot injuries are highly associated is supported by other studies comparing gunshot injuries in the US with gunshot injuries in other western industrialized nations where gun ownership is more tightly controlled: while the US enjoys the highest number of guns per capita of any nation studied, the US also has the highest rate of fatal gunshot injuries of any country studied (Krug EG. Intl J Epidemiology. 1998; 27:214-22).

The increasing number of gunshot injuries is also occurring at a time of decreasing incidence of violent crime.  According to reports issued by the FBI, violent crime statistics have been decreasing over the past several years (http://www.fbi.gov/...).  The divergence of violent crime and gunshot injury statistics occurs because gunshot injuries occur in a variety of settings, not just during violent crimes.

It is important to note that a correlation of rising guns sales with increasing gunshot injuries does not prove that rising gun sales cause more gun injuries.  It only proves that the variables guns sales and gunshot injuries move in tandem.  However, because we now have evidence that guns sales and gunshot injuries tend to move in similar ways, this suggests one way to reduce gunshot injuries in the US is to sell fewer guns.  Sadly, the numbers do not show any steady decrease in gunshot injuries because, since its inception, the FBI NICS has not recorded any multi-year periods of decreasing gun sales.  

This longitudinal study show conclusively that both gunshot injuries and gun sales in the US have in recent years shown a steady increase, and that gun sales and gunshot injuries are highly associated.  This study also demonstrates the utility of examining gunshot injuries from the perspective of a public health problem.  Sadly, our nation's premier public health institution, the CDC, has been denied funding specifically for the purpose of studying gunshot injuries.  With more and more fatal gunshot injuries occurring every year, this kind of research is very much needed.

Author's notes:
1) I must first apologize for the appearence of the data table.  I have not yet learned how to properly format a table within the dk diary application.  Any tips on how to present a data table in a dk diary is greatly appreciated.
2) I have omitted many of the details of the regression and correlation analyses to make the article friendly to non-scientists.  I am happy to provide more information to any interested readers.  
3) As I noted in the article, the FBI NICS statistics provide only an indirect measurement of gun sales.  The NICS data has been used by other authors as a marker of gun sales, for the same reasons I listed above.  I would be interested in hearing from any readers who know a better source of more complete information about yearly gun sales in the US.

EMAIL TO A FRIEND X
Your Email has been sent.
You must add at least one tag to this diary before publishing it.

Add keywords that describe this diary. Separate multiple keywords with commas.
Tagging tips - Search For Tags - Browse For Tags

?

More Tagging tips:

A tag is a way to search for this diary. If someone is searching for "Barack Obama," is this a diary they'd be trying to find?

Use a person's full name, without any title. Senator Obama may become President Obama, and Michelle Obama might run for office.

If your diary covers an election or elected official, use election tags, which are generally the state abbreviation followed by the office. CA-01 is the first district House seat. CA-Sen covers both senate races. NY-GOV covers the New York governor's race.

Tags do not compound: that is, "education reform" is a completely different tag from "education". A tag like "reform" alone is probably not meaningful.

Consider if one or more of these tags fits your diary: Civil Rights, Community, Congress, Culture, Economy, Education, Elections, Energy, Environment, Health Care, International, Labor, Law, Media, Meta, National Security, Science, Transportation, or White House. If your diary is specific to a state, consider adding the state (California, Texas, etc). Keep in mind, though, that there are many wonderful and important diaries that don't fit in any of these tags. Don't worry if yours doesn't.

You can add a private note to this diary when hotlisting it:
Are you sure you want to remove this diary from your hotlist?
Are you sure you want to remove your recommendation? You can only recommend a diary once, so you will not be able to re-recommend it afterwards.
Rescue this diary, and add a note:
Are you sure you want to remove this diary from Rescue?
Choose where to republish this diary. The diary will be added to the queue for that group. Publish it from the queue to make it appear.

You must be a member of a group to use this feature.

Add a quick update to your diary without changing the diary itself:
Are you sure you want to remove this diary?
(The diary will be removed from the site and returned to your drafts for further editing.)
(The diary will be removed.)
Are you sure you want to save these changes to the published diary?

Comment Preferences

  •  Tip Jar (19+ / 0-)

    "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

    by Hugh Jim Bissell on Sun Aug 26, 2012 at 12:17:05 PM PDT

  •  What happened in New York was a mass shooting (6+ / 0-)

    by the police.  The guy they killed shot one person, everyone that got injured was shot by the police.

    Which doesn't change the point of your diary, or make it any less correct.  I just felt the need to point that out.

    Good diary.

    There revolution will not be televised. But it will be blogged, a lot. Probably more so than is necessary.

    by AoT on Sun Aug 26, 2012 at 12:30:17 PM PDT

    •  Correct. (4+ / 0-)
      Recommended by:
      Joy of Fishes, AoT, MKSinSA, murrayewv

      You are correct that the person identified in the NYC shooting as the "perpetrator" actually only shot (and killed) one person, and all others who received gunshot injuries in that incident were shot by the police.  I stand corrected.

      Thank you for reading and your feedback.

      "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

      by Hugh Jim Bissell on Sun Aug 26, 2012 at 12:37:24 PM PDT

      [ Parent ]

  •  just to make sure (14+ / 0-)

    that I understand your position.  You are stating that there exist no real evidence that increased gun sales lead directly to increased gun injuries?  Just that they seem to move up together-- not enough decreases to determine if the opposite is true.

    and;

    You are not calling for a ban on bicycles?  if not why not?  You are conceding that more people are injured by bicycles than guns.

    I think your purpose here is to push for limits on gun sales.  We will never agree on that, I will oppose limits- forever-- regardless of any thing that you present.  However, I am not disrespecting your position(as wrong as I think that it is).  Just seeking clarification.  

    Thanks

    Dwayne

    Hey! glad to see you. Hope you are doing well.

    by deedogg on Sun Aug 26, 2012 at 12:37:55 PM PDT

    •  More on correlation (9+ / 0-)

      A correlation means two variables move together: a positive correlation means that movement occurs in the same direction (one variable goes up, the other variable also goes up), while a negative correlation means the two variables move in opposite directions (one variable goes up, the other variable goes down).

      The data and analysis presented here show there is a large positive correlation of gun sales and gunshot injuries.  This means that (on average) we can expect gun sales and gunshot injuries to either move up together, or move down together.  

      So one conclusion we can draw from this research is that if gun sales were to decrease, we can expect a concommitant decrease in gunshot injuries.

      You are correct that I do not call for a ban on bicycles anywhere in the article.  A careful reading of the article will also reveal that I do not call for a ban on guns anywhere in the article.

      However, you are correct that my personal opinion on guns and gun ownership is largely negative, and I think we as a nation would be better off with fewer guns.

      "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

      by Hugh Jim Bissell on Sun Aug 26, 2012 at 12:57:10 PM PDT

      [ Parent ]

    •  In regards to bicycles (3+ / 0-)
      Recommended by:
      Sandino, Ralphdog, ZenTrainer

      The more cyclists that are out the riding the less likely they are to be injured.  Maybe we just need to figure out a way to turn guns into bicycles.

      There revolution will not be televised. But it will be blogged, a lot. Probably more so than is necessary.

      by AoT on Sun Aug 26, 2012 at 01:03:06 PM PDT

      [ Parent ]

    •  Its a bad argument to point to something else . (0+ / 0-)

      Risk A being greater than risk B does not make B any less of a risk than it is .
      Adding A with B does not change B , subtracting A form B does not change B .

      Heart problems are a greater risk than automobiles
      should we not improve the safety of automobiles because of that ?
      Or should we wait until automobiles kill more each year than heart problems ?
      If you are for less people being killed and wounded each day via bicycles
      are you not also for less people being killed and wounded each day via gun shots ?

      "Drop the name-calling." Meteor Blades 2/4/11

      by indycam on Sun Aug 26, 2012 at 01:48:52 PM PDT

      [ Parent ]

      •  So you would (7+ / 0-)

        amend the Constitution of the United States to allow banning of arms because you view them as dangerous.  However, bicycles which have no Consitutional protections and hurt more people each year get a pass. Why?

        I understand that you want to ban guns.  That is pretty clear, as is the fact that I disagree.  But what is just as clear is that your reasoning is flawed.  Safety is not the real reason or you would try to ban the more dangerous tool.  Or are you concerned about opposing bike owners?  They love their bikes, ya know.

        btw. I am glad to see ya still around, even though you are wrong on this issue.  I remember you from back when the ugog trolls were of the loose here.

        Hey! glad to see you. Hope you are doing well.

        by deedogg on Sun Aug 26, 2012 at 04:48:14 PM PDT

        [ Parent ]

        •  Where did I say "ban guns" ? (2+ / 0-)
          Recommended by:
          Sandino, AaronInSanDiego

          Your argument falls flat on its face because I never said that .

          I understand that you want to ban guns.
          You understand that ? Really ? You need to stop listening to the wrong people .  
          So you would
          amend the Constitution of the United States to allow banning of arms because you view them as dangerous.
          Who told you this ? Or did you just pull that out of thin air ?

          "Drop the name-calling." Meteor Blades 2/4/11

          by indycam on Sun Aug 26, 2012 at 05:37:41 PM PDT

          [ Parent ]

          •  I must have (5+ / 0-)

            mistaken you for another indycam that shows up in these diaries:

            http://www.dailykos.com/...

            Hey! glad to see you. Hope you are doing well.

            by deedogg on Sun Aug 26, 2012 at 07:33:15 PM PDT

            [ Parent ]

            •  So you admit you got nothing ? (2+ / 0-)
              Recommended by:
              Sandino, AaronInSanDiego

              Cause your link proves nothing .
              Nothing at all !
              Are you going to admit your comment was nothing but pure BS ?

              "Drop the name-calling." Meteor Blades 2/4/11

              by indycam on Sun Aug 26, 2012 at 07:52:05 PM PDT

              [ Parent ]

              •  are you (8+ / 0-)

                just being intentionally dense/obtuse?  I see you in RKBA threads and other related diaries all the time.  I read even if I do not always comment.  I assumed from your actions and comments that you did not support 2nd amendment rights,

                However, if I was wrong and you are a supporter of the 2nd amendment I will gladly stand corrected and invite you to join the RKBA group here at The Great Orange Satan and work with me to extend, broaden, and protect our citizen's right to bear arms.  We can always use new supporters/members.

                Thanks

                btw-- I been around.  I noticed your little tatic of arguing the nonpoint while ignoring the point I made.  Fact is simple-- the bicycle data proves all of your arguments are invalid.  You do not care about numbers of injured and mained, just about guns.  Deal with the fact that you got nothing on the actual issue.  Doesn't matter how much whining you do.

                Hey! glad to see you. Hope you are doing well.

                by deedogg on Sun Aug 26, 2012 at 08:34:38 PM PDT

                [ Parent ]

                •  You pointed to a comment that did not (0+ / 0-)

                  prove the claim "ban guns" .
                  You pointed to a comment that was recommended by  KVoimakas . Are you saying he recommended a "ban guns" comment ?

                  Recommended by:
                      KVoimakas, Calvino Partigiani, indubitably, FG, AaronInSanDiego
                  Until you come up with something more than nothing , you have failed .

                  "Drop the name-calling." Meteor Blades 2/4/11

                  by indycam on Mon Aug 27, 2012 at 07:31:23 AM PDT

                  [ Parent ]

                •  More outragous claims . (0+ / 0-)
                  I see you in RKBA threads and other related diaries all the time.
                  Oh really ? Go back the last 50 rkba diaries and count the number I have commented in . Now if you want to talk about my partisipation in non rkba diaries , whats that to you ? I'm free to comment in any diary I like . That does not prove my stance is "ban guns" .
                  You do not care about numbers of injured and mained, just about guns.
                  Prove it . Just don't pull stuff out of thin air , prove it .
                  However, if I was wrong and you are a supporter of the 2nd amendment I will gladly stand corrected and invite you to join the RKBA group here at The Great Orange Satan and work with me to extend, broaden, and protect our citizen's right to bear arms.  We can always use new supporters/members.
                  What a joke . You are wrong and I will never join that group . You request that I join to prove that I never said "ban guns" is a joke .

                  Your trying to hard .
                  You can't do what you are trying to do , it will not work .

                  Deal with the fact that you got nothing on the actual issue.
                  Right back atcha .

                  http://www.dailykos.com/...

                  My WW2 volunteer vet B24 top turret gunner / (10+ / 0-)

                  Recommended by:
                      maxomai, Ahianne, buddabelly, kestrel9000, Crashing Vor, sceptical observer, ER Doc, SomeStones, ban nock, theatre goon

                  flight engineer / served his country by flying over hostile areas where the enemy was doing their best to shoot him out of the sky / flew all of his missions / fixed the aircraft and flew in them post repair to check the operational fitness / Pops , has a pistol .

                  by indycam on Sat Apr 17, 2010 at 11:22:57 AM PDT

                  http://www.dailykos.com/...
                  I did read up on the assault weapon ban and weapons .
                  It was a joke .
                  It really was a feel good ban .
                  It did nothing to stop people from getting a weapon .
                  Under the assault weapons ban , you could still buy a semi auto rifle with as many clips and as many bullets as you would like .

                  "Drop the name-calling." Meteor Blades 2/4/11

                  by indycam on Mon Aug 27, 2012 at 08:22:23 AM PDT

                  [ Parent ]

                •  Why would I want new guns to be built with (0+ / 0-)

                  child proofing , built in locks , anti bump / dropping safety if I wanted them banned ?
                  Would make any sense to advocate for safer guns to be built if I did really want them banned .

                  http://www.dailykos.com/...

                  I would add
                  all new guns must be child proof and must include a locking mechanism built into the gun such that upon removal the gun no longer functions .

                  No gun may be made that will discharge from dropping or bumping .

                  No gun may be made in such a way that bump firing is possible .

                  You do not care about numbers of injured and mained, just about guns.
                  Child proofing , built in locks , anti bump / dropping safety , all about safety and nothing about banning guns ?

                  I challenge you and your friends to actually figure out my real position , write it down and then post it as a comment . The one who gets it correct might get some respect .

                  "Drop the name-calling." Meteor Blades 2/4/11

                  by indycam on Mon Aug 27, 2012 at 08:47:56 AM PDT

                  [ Parent ]

                •  Here is another one just for you (0+ / 0-)
                  Every gun owner must be

                  a member of a militia , the militia would be run by and for gun owners . Every member would need to be approved for membership by the other members of the militia . Every gun owned by a member would have to be approved of by the militia . Every militia member would have to buy insurance from the militia for every gun they own .
                  Its a system where the upstanding gun owners take care of the problems .

                  by indycam on Tue Aug 07, 2012 at 05:21:25 PM PDT

                  Do you read ban in there anywhere ?

                  Do you see

                  Its a system where the upstanding gun owners take care of the problems .
                  as a problem for you ?

                  "Drop the name-calling." Meteor Blades 2/4/11

                  by indycam on Mon Aug 27, 2012 at 09:01:27 AM PDT

                  [ Parent ]

                  •  Do you really (0+ / 0-)

                    not know my history, at all.  I used to post at FSZ, I have posted at other places as Deedogg.  There is no secret as to who i am, I have posted links to my facebook page before were I post as myself:

                    http://www.facebook.com/...

                    I say that to say this:  

                    Using your little tatic will not work on me.  I will not get mad and call you names.  I will not get angry and lose my cool.  I will not chase rabbits for you or allow any of your basic trolling tatics influence me.  I have seen it all.  The question is Bikes.  Do you support banning bikes or not?  You do admit they hurt more people than guns?

                    I got to go.  We got a Hurricane in the Gulf, ya know.  If you ever want to actually answer the real question, let me know.

                    Hey! glad to see you. Hope you are doing well.

                    by deedogg on Mon Aug 27, 2012 at 05:26:45 PM PDT

                    [ Parent ]

                    •  I could not care less who you are or where (0+ / 0-)

                      you have posted before . Not even one little bit .

                      Using your little tatic will not work on me.  I will not get mad and call you names.  I will not get angry and lose my cool.  I will not chase rabbits for you or allow any of your basic trolling tatics influence me.
                      You have a vivid imagination , you should put it to profitable use .
                      The question is Bikes.  Do you support banning bikes or not?  You do admit they hurt more people than guns?
                      You want to talk about bicycles ?

                      The question is hearts .  Do you support banning hearts or not ?  You do admit they hurt more people than guns ?

                      If you ever want to actually answer the real question , let me know .

                      "Drop the name-calling." Meteor Blades 2/4/11

                      by indycam on Mon Aug 27, 2012 at 07:45:49 PM PDT

                      [ Parent ]

                      •  more (0+ / 0-)

                        101 stuff.  You got to better if you want to troll me.

                        The question is about bikes.  I would not ban bikes, hearts, or guns.  You?

                        Hey! glad to see you. Hope you are doing well.

                        by deedogg on Mon Aug 27, 2012 at 08:22:34 PM PDT

                        [ Parent ]

                        •  You are still going on about a question (0+ / 0-)

                          that was answered long ago .
                          Its been answered many different ways .
                          Are you having trouble understanding the answers ?

                          And your repeated going on about troll / trolling ...
                          That's just your problem .  
                          False accusations , repeated false accusations , such as you have done and are continuing to do are against the rules and an indicator .  

                          "Drop the name-calling." Meteor Blades 2/4/11

                          by indycam on Tue Aug 28, 2012 at 08:03:40 AM PDT

                          [ Parent ]

              •  usual.schtick.argue.in.circles.till.everyone.gets (5+ / 0-)

                so.tired.of.it.they.just.stop.responding.to.you......

                One.of.the.shittiest.schticks.on.a.site.full.of.them.......

                And.a.sanctimonious.jerk.to.boot.who.enjoys.telling.others.how.wrong.they.are.as.often.as.possible.......

                Vaya con Dios Don Alejo
                I want to die a slave to principles. Not to men.
                Emiliano Zapata

                by buddabelly on Sun Aug 26, 2012 at 08:47:24 PM PDT

                [ Parent ]

            •  like twigg said there... (2+ / 0-)
              Recommended by:
              deedogg, IndieGuy

              This machine kills Fascists.

              by KenBee on Sun Aug 26, 2012 at 09:13:39 PM PDT

              [ Parent ]

            •  That comment looks almost as if (0+ / 0-)

              he is arguing against banning "assault weapons", or at least, he doesn't think it will do much good.

              "Okay, until next time. Keep sending me your questions, and I will make fun of you... I mean, answer them." - Strong Bad

              by AaronInSanDiego on Sun Aug 26, 2012 at 10:39:56 PM PDT

              [ Parent ]

              •  For what it's worth... (3+ / 0-)
                Recommended by:
                theatre goon, buddabelly, deedogg

                ...you have to take a holistic approach to this one's comments in any of these diaries.  Any one comment can seem pretty innocuous.  Plus, his rhetorical style is all over the map in terms of consistency so if you're not used to it, it can be hard to follow just what he's getting at.  Once you've seen enough from him, though, the picture comes through very clearly:  There is no desire on his part to honestly engage.


                Time travel opportunity. Must bring your own weapons. Your safety is not guaranteed, I've only done this once before. Call 866.555.1212.

                by IndieGuy on Mon Aug 27, 2012 at 06:50:40 AM PDT

                [ Parent ]

  •  Correllation is not causation (13+ / 0-)
    It is important to note that a correlation of rising guns sales with increasing gunshot injuries does not prove that rising gun sales cause more gun injuries.  It only proves that the variables guns sales and gunshot injuries move in tandem.  However, because we now have evidence that guns sales and gunshot injuries tend to move in similar ways, this suggests one way to reduce gunshot injuries in the US is to sell fewer guns.
    You disprove your own hypothesis with your own opening statement.

    Thanks for the effort but I personally don't think you've proven anything one way or the other.

    •  Correlation is not proof of lack of causation. (7+ / 0-)

      If you think that the opening statement disproves the hypothesis you know nothing about logic.

      There are four possibilities:
      1) Gun sales cause gun injuries.
      2) Gun injuries cause gun sales.
      3) Some other factor causes both.
      4) The correlation is  random noise and a larger data set will eliminate it.

      2 and 4 don't seem very likely. So either gun sales are driving the increase in gun injuries or some other variable is driving both. If you want to propose one, that is fine. It would be useful if it is something measureable so that your hypothesis could be tested.

      Right now the hypothesis that gun sales are driving gun injuries looks pretty good.

    •  That doesn't disprove his hypothesis (8+ / 0-)

      Showing a correlation is a necessary first step to showing causation.  If there were no correlation then we could conclusively say that more gun sales does not lead to higher gun injury rates.  As it is there would have to be more research done on it.

      There revolution will not be televised. But it will be blogged, a lot. Probably more so than is necessary.

      by AoT on Sun Aug 26, 2012 at 01:05:49 PM PDT

      [ Parent ]

      •  I did not say it was disproved (9+ / 0-)

        I said it was a null set. Neither here nor there.

        •  ??? (1+ / 0-)
          Recommended by:
          Sandino

          This is what you wrote:

          You disprove your own hypothesis with your own opening statement.
          As noted by others, his opening statement does not disprove anything.

          ....no longer in SF.... -9.00, -7.38

          by TFinSF on Sun Aug 26, 2012 at 03:34:56 PM PDT

          [ Parent ]

          •  Two different things (4+ / 0-)
            Recommended by:
            PavePusher, theatre goon, oldpunk, deedogg
            It is important to note that a correlation of rising guns sales with increasing gunshot injuries does not prove that rising gun sales cause more gun injuries.  It only proves that the variables guns sales and gunshot injuries move in tandem.  However, because we now have evidence that guns sales and gunshot injuries tend to move in similar ways, this suggests one way to reduce gunshot injuries in the US is to sell fewer guns.
            These words come directly from the diary.

            1) Correllation in general.

            The bolded part is true. This applies generally to the concept. As put in the title, correllation is not causation.

            2) The specific hypothesis "one way to reduce gunshot injuries in the US is to sell fewer guns."

            Read the bolded part again. the author correctly observes that one cannot do the very thing he does two sentences later.

            Since we know from the same paragraph that this is insufficient evidence to reach that conclusion, that means we need more and deeper analysis. There is no other analysis in this diary. Therefore we should conclude we do not know enough to rule on the hypothesis. More information is needed.

            In summary, the methodology here is flawed. That is what we know. However even flawed reasoning can lead to the correct answer. So while we know enough to criticize the technique used we do not know enough to judge the conclusion reached.

            This is a very good question. Thank you for asking it.

    •  Lots of Americans reject science (3+ / 0-)
      Recommended by:
      Sandino, Man Oh Man, MKSinSA

      Lots of Americans reject science in favor of their own fact-free opinions and beliefs.  You are free to ignore the data and analysis presented here if you wish.

      "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

      by Hugh Jim Bissell on Sun Aug 26, 2012 at 01:21:16 PM PDT

      [ Parent ]

  •  "Tend to move in similar ways" (14+ / 0-)

    I'm not sure that's necessarily the case.

    Sure, gun deaths have increased if your data is correct (and I shall not spend the time to confirm every number and will trust that they are the numbers from the source you say they are), but as a % gun sales have risen massively since 2007 while fatal injuries have risen at a FAR small marginal rate. Nonfatal injuries are all over the place and are sort of difficult to utilize in the analysis.

    Like Quicklund says, interesting correlation, but without checking I bet population rose higher from 2007-2009 as a % figure than fatal gun injuries too.

    •  Correlation is a science-based operation (4+ / 0-)

      Correlation is a common frequently used method of observing trends from disparate data.  It is accepted and used by scientists all over the world everyday.  I'm willing to wager you employ a form of correlation when you decide not to drive down certain streets because of the greater likelihood of red lights and increased traffic on some streets compared to others.

      Your point about population growth is valid.  The CDC data can be exaimined based on the US population in 2000 (i.e. population held constant), but the FBI NICS data does not allow this kind of examination.  I did not employ the "population held constant" feature of the CDC data.  In defense, any change in US population is likely to interact equally with the CDC data AND the FBI data.  I'm guessing any change in US population would not alter the overall results.  But you have a good idea, to correlate gunshot injuries and gun sales with changes in the US population.  Perhaps a topic for the nest study.  

      "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

      by Hugh Jim Bissell on Sun Aug 26, 2012 at 01:14:41 PM PDT

      [ Parent ]

    •  Lots of things "tend to move in the same ways" (14+ / 0-)

      in the US when you look at raw numbers...
            Using the diarist's data, there's about a 10% rise in deaths from gunshot injuries from 1999 to 2009. Interestingly, the US Census data estimates the population grew from 279,040,000 in 1999 to 307,007,000 in 2009, which is also about a 10% rise.
            There's about a 16% rise in injuries from 2001-2010. In the meantime, NICS checks rose from 9,138,000 to 14,033,000, which is over a 50% rise. That is a correlation, certainly, but a weak one, certainly confounded by many other variables.
           

      -7.25, -6.26

      We are men of action; lies do not become us.

      by ER Doc on Sun Aug 26, 2012 at 01:27:17 PM PDT

      [ Parent ]

  •  Also tipped for discussion. nt (7+ / 0-)
  •  Thank you, Hugh... (2+ / 0-)
    Recommended by:
    ZenTrainer, Sandino

    Several "enthusists" have been asking for the information on gun availability and the effect on gun violence you have now provided.

    I have a new question.

    Which of these groups would you consider to be
    "pro 2nd amendment" gun enthusiasts?

    I am looking forward to the predictable logical fallacies
    that will side-step the question.
    Might make an interesting collection, no?

    'Scuse me while I go make some more popcorn.
    You kids play nice now.

    One must imagine Sisyphus happy. Camus

    by Man Oh Man on Sun Aug 26, 2012 at 01:08:08 PM PDT

  •  Thanks for the article. Nice work. (4+ / 0-)

    Good luck with this part:

    This article is critical of current US gun policy, and gun enthusiasts may want to avoid reading this article as it presents some facts and figures that shows our current gun policy in a negative light.

    Tracy B Ann - technically that is my signature.

    by ZenTrainer on Sun Aug 26, 2012 at 01:18:46 PM PDT

    •  I feel it is polite (3+ / 0-)
      Recommended by:
      terabthia2, ZenTrainer, Sandino

      I feel it is a small politeness, to give fair warning to those gun enthusiasts who cannot tolerate any negative statements abut guns.  I understand that most people will make up their own minds about reading this.

      "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

      by Hugh Jim Bissell on Sun Aug 26, 2012 at 03:25:21 PM PDT

      [ Parent ]

      •  How many of those types do you think (10+ / 0-)

        will be here? At DKos? You seem to be inadvertently revealing a prejudice.

        And technically, all you are trying to do is show that as gun sales appear to have increased, so too have gun injuries appear to have increased. And then you say, "Coincidence? Maybe! Maybe Not!"

        You didn't actually say anything bad, directly, about guns, it is just insinuation.

        •  Not "appeared" - did increase (1+ / 0-)
          Recommended by:
          ZenTrainer

          Gun sales and gun injuries did not "appear" to have increased: the numbers for gun sales and gun injuries DID ACTUALLY increase.  Surely you can read numbers and know the meaning of greater than and lesser than?

          Saying that gun sales increased over the period studied is a FACT.  Saying that gun injuries increased over the period studied is a FACT.  Saying that the correlation is positive and statistically significant is a FACT.

          However, your statement that I have insinuated something about guns is your opinion, and is NOT A FACT.

          "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

          by Hugh Jim Bissell on Sun Aug 26, 2012 at 06:44:44 PM PDT

          [ Parent ]

      •  It is very polite but it has the opposite (0+ / 0-)

        effect on gun enthusiasts here on Kos. They tend to swarm in like sheep being rounded up by a border collie.

        Tracy B Ann - technically that is my signature.

        by ZenTrainer on Sun Aug 26, 2012 at 09:45:01 PM PDT

        [ Parent ]

        •  News flash: (4+ / 0-)

          There's pretend polite and there's actual polite.  Supporting an agenda with faulty reasoning wrapped up in pretend politeness, is still nothing but faulty reasoning being used to support an agenda.  

          But of course, you already knew that.


          Time travel opportunity. Must bring your own weapons. Your safety is not guaranteed, I've only done this once before. Call 866.555.1212.

          by IndieGuy on Mon Aug 27, 2012 at 06:15:22 AM PDT

          [ Parent ]

  •  Conclusions do not follow from premises. (19+ / 0-)

    For instance, take this apparently formal argument:

    The results of this study show unmistakeably that: 1) gunshot injuries, both fatal and non-fatal, have  increased steadily over the period studied; 2) guns sales as modeled by the NICS data have likewise risen steadily since this record was initiated; and 3) there exists a tight linkage between gun sales and gunshot injuries, especially for fatal gunshot injuries.
    One and two are fine, as far as they go, but number three is an assumption based on insisting that a "tight linkage" exists, where none is demonstrated.

    In other words, the diarist would have us believe that, because there are two data points regarding one particular item, then those two data points must, in fact, be tightly linked.

    This is simply not the case.  As others have mentioned, correlation does not imply causation.

    Yes, I often dress as a pirate. Your point?

    by theatre goon on Sun Aug 26, 2012 at 01:22:07 PM PDT

  •  Thanks for providing real data (8+ / 0-)

    Too often discussions about guns in the US involves only emotions and word-of-mouth accounts. It's really nice to see some real data.

  •  All of the examples cited in the third paragraph (5+ / 0-)

    is an average weekend in the gun-free city of Chicago.

    Children have imaginary friends, adults have god.

    by soros on Sun Aug 26, 2012 at 01:36:26 PM PDT

  •  A plot (3+ / 0-)
    Recommended by:
    PavePusher, Tom Seaview, oldpunk

    A plot with the regression line drawn on it would help a lot.

    •  There are multiple variables. (17+ / 0-)

      A simple linear least squares regression would not show all the possibilities, nor would it show a true picture.  It would take something like a multiple regression equation in order to avoid a post hoc, ergo propter hoc fallacy, such as this diary presents.  

      There are too many dependent variables.

      The general who wins the battle makes many calculations in his temple before the battle is fought. The general who loses makes but few calculations beforehand. - Sun Tzu

      by Otteray Scribe on Sun Aug 26, 2012 at 02:23:31 PM PDT

      [ Parent ]

    •  I have such a plot (3+ / 0-)
      Recommended by:
      Joy of Fishes, ZenTrainer, Sandino

      My statistical analysis includes exactly such a plot (and a scatterplot of gun sales and gunshot injuries)  and I would love to include it in this diary, but I do to know how to embed such an image in the diary.

      The dk help instructions start out saying that the instructions on embedding images apply only to people who are subscribers, which I unfortunately am not.

      Any help on how to do this would be greatly appreciated.

      "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

      by Hugh Jim Bissell on Sun Aug 26, 2012 at 03:36:18 PM PDT

      [ Parent ]

      •  Correlation and causation (15+ / 0-)

        are not the same thing.  This is one of the most basic fallacies in statistics, and is how many people use statistics to lie or mislead.   Only by using a multiple regression analysis can any positive or negative relationship be statistically analyzed.  All possible variables must be entered into the fields and then rotated on all possible axes in a fourth dimensional hyperplane.  Then MAYBE, you can find causation, which is always going to be relative, and never in a straight line.  

        A simple Pearson's Product Moment analysis or some other linear statistic ain't gonna cut it.

        The general who wins the battle makes many calculations in his temple before the battle is fought. The general who loses makes but few calculations beforehand. - Sun Tzu

        by Otteray Scribe on Sun Aug 26, 2012 at 05:34:26 PM PDT

        [ Parent ]

        •  Absolutely incorrect!! (2+ / 0-)
          Recommended by:
          Sandino, Joy of Fishes

          Correlation is a statistical technique that examines relationships between variables.  To say ONLY multiple regression analysis provides an examination of relationships among variables is absolutely false.

          Moreover, correlation and regression are similar in many regards.  Indeed the r of a linear regression analysis is identical to the Pearson's r of regression, and Pearson's r is used to calculate the r(squared) that is reported as part of a regression analysis.

          In addition, I performed a regression analysis as part of the work presented here.  I did not include the details of that work to make this diary friendly to people like you whose only knowledge of statistics is the famous saying that correlation does not equal causation.  But I am happy to tell you anything about the regression that was done that you want to know.  Simply ask.

          "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

          by Hugh Jim Bissell on Sun Aug 26, 2012 at 07:01:55 PM PDT

          [ Parent ]

          •  Post Hoc, Ergo Proptoer Hoc waiting to happen. (12+ / 0-)

            Correlation is required to prove causation, but correlation and causation is not automatic.  There was a famous illustration, I think it was in an article by Paul Meehl, that showed trains arriving in the Stockholm, Sweden train terminal was correlated highly with time of birth of babies in Chicago.

            The general who wins the battle makes many calculations in his temple before the battle is fought. The general who loses makes but few calculations beforehand. - Sun Tzu

            by Otteray Scribe on Sun Aug 26, 2012 at 07:08:37 PM PDT

            [ Parent ]

          •  I did not say the multiple regression analysis (13+ / 0-)

            was the ONLY way.  There are a number of multivariate analysis techniques that might be useful.  Your problem is that you are not taking into account all possible variables and feeding them into the equation.  I once did a study with so many variables it shut down the mainframe computer in the engineering department of the University.  Threw all the other users off and went to error mode.  We had to process the data in segments because it ate all the available memory.  Your hypothesis, in order to be fully tested, will require almost as many variables to be fed into the equation.  

            When doing science, you start with a null hypothesis.  You do not have a conclusion and try to fit the data to "prove" your conclusion.  That is what the Republicans do.  Start with an empty slate and see what the data show, not the other way around.  

            The general who wins the battle makes many calculations in his temple before the battle is fought. The general who loses makes but few calculations beforehand. - Sun Tzu

            by Otteray Scribe on Sun Aug 26, 2012 at 07:17:37 PM PDT

            [ Parent ]

            •  I used the available data (3+ / 0-)
              Recommended by:
              Sandino, ZenTrainer, Joy of Fishes

              I used the available data.  

              No doubt there are other variables we would like to include.  My question for you is what other variables do you think are needed to improve the existing analysis, and does that information exist and from a reliable source?

              I stand by my data and analysis (and my conclusions) until a better study is done.  Feel free to do that better study, and if you write it up here, you and I can then review and discuss it.

              "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

              by Hugh Jim Bissell on Sun Aug 26, 2012 at 07:47:49 PM PDT

              [ Parent ]

              •  If I did such a study, (10+ / 0-)

                it would not be published on a blog.  It would be in a peer reviewed professional journal.  This blog is a pastime, not a job.  I have too many pressing things to do than engage in pointless pie in the sky wild goose chases.  I would rather spend my limited time helping put criminals in jail and helping keep innocents out.  

                The general who wins the battle makes many calculations in his temple before the battle is fought. The general who loses makes but few calculations beforehand. - Sun Tzu

                by Otteray Scribe on Sun Aug 26, 2012 at 08:08:37 PM PDT

                [ Parent ]

                •  Ha!!! So busy you waste your time on bs! (0+ / 0-)

                  Yes, I understand: you are so important and busy you waste your time pretending that correlation is meaningless and making non-sensical and spurious take-downs of research that is way over your head!!  What a mensch!!

                  You can't do such a study as I did here.  You lack the knowledge and comprehension; you lack the knowledge and comprehension to even make a coherent critique of this study (simple as it is).

                  Go back to keeping people out of prisons.  Your time is much better spent doing that.

                  "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

                  by Hugh Jim Bissell on Mon Aug 27, 2012 at 07:05:00 AM PDT

                  [ Parent ]

                  •  Now this is hilarious. (3+ / 0-)
                    Recommended by:
                    KVoimakas, Joy of Fishes, oldpunk

                    When shown that your claims are completely unsupported by the information you provided and that your methodology is so flawed so as to be meaningless, you now insist that those who have shown your many flaws are not informed enough to keep up with your dizzying intellect.

                    The word "arrogance" comes to mind.

                    Yes, I often dress as a pirate. Your point?

                    by theatre goon on Mon Aug 27, 2012 at 10:46:35 AM PDT

                    [ Parent ]

              •  No, you did not use the available data. (3+ / 0-)
                Recommended by:
                theatre goon, Joy of Fishes, oldpunk

                You used some of the available data, found the answer you had already chosen, and consciously ignored any and all other data points.

                This isn't a "study."  If you spent as much time and effort doing an actual study as you've spent defending this diary you might be heading in the direction of a proper study.  But in keeping with your disparaging remarks above regarding "science" I'd advise you to do some actual science:  Posit a hypothesis, find all the available facts, test them against the hypothesis.  If your hypothesis is borne out, congratulations.  You can publish a research paper.  Which will then, of course, be torn apart by actual scientists.

                In the meantime, this is just another in a long string of opinion pieces.


                Time travel opportunity. Must bring your own weapons. Your safety is not guaranteed, I've only done this once before. Call 866.555.1212.

                by IndieGuy on Mon Aug 27, 2012 at 06:30:53 AM PDT

                [ Parent ]

      •  HJB flikr is your friend (10+ / 0-)

        then use that "link" thingy down below the text box.

        Can't wait to see the evidence.

        •  I want to see the proofs. (10+ / 0-)

          Geeks are funny that way.  We want to see how you got from point A to point B without stepping on your own pecker in the process.

          The general who wins the battle makes many calculations in his temple before the battle is fought. The general who loses makes but few calculations beforehand. - Sun Tzu

          by Otteray Scribe on Sun Aug 26, 2012 at 06:13:32 PM PDT

          [ Parent ]

          •  Proofs of what?!?!?!? (1+ / 0-)
            Recommended by:
            Sandino

            What proofs would you like to see?

            Do you want to see the proof by which we know that 31k gunshot fatalities/yr are greater than 28k gunshot fatalities/yr?

            Do you want to see the proof of the normal distibution and how it applies to correlation.  That is available in any standard statistics text.  I reccomend Probability and Statistics for Engineering and the Sciences, 8th ed., by Jay Devore.  Knock yourself out.

            "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

            by Hugh Jim Bissell on Sun Aug 26, 2012 at 07:13:45 PM PDT

            [ Parent ]

            •  If you do not know what proofs are, (11+ / 0-)

              You have no business trying to do a scientific data analysis.

              If you are going to try to do a statistical analysis, may I dirct you to one of the better books on how to do a statistical investigation.  Experimental and Quasi-Experimental Designs for Generalized Causal Inference by Shadish, Cook and Campbell.

              The general who wins the battle makes many calculations in his temple before the battle is fought. The general who loses makes but few calculations beforehand. - Sun Tzu

              by Otteray Scribe on Sun Aug 26, 2012 at 08:54:42 PM PDT

              [ Parent ]

              •  I am so, so glad... (8+ / 0-)

                ...that my coffee isn't quite ready yet -- or the "proofs of what?!?!" bit would have led to a caffeinated keyboard.

                Oh, my...

                Yes, I often dress as a pirate. Your point?

                by theatre goon on Mon Aug 27, 2012 at 04:08:19 AM PDT

                [ Parent ]

              •  I noticed you didn't answer the question (0+ / 0-)

                I noticed you didn't answer the question: proofs of what?

                You tell me what "proofs" you think are relevant to the study that was done.  This is not engineering; it is medical science, and you are obviously out of your league.

                The proofs of regression and correlation are available in most texts on statistics, perhaps even the one you mentioned.  Look through any original research article published in a peer-reviewed medical journal and notice that not a single article prints the "proofs" of their statistical analysis.  Why?  Because space is at a premium, everyone already learned that material back in grad school, and no one is going to bother re-printing it or even re-reading it.

                "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

                by Hugh Jim Bissell on Mon Aug 27, 2012 at 06:54:35 AM PDT

                [ Parent ]

                •  If you do not know what proofs are (12+ / 0-)

                  then you do not have a clue as to how to do a correlation analysis.  Proofs are an essential part of any analytical process so your work can be checked.  What you did just now was reveal your lack of understanding of how to analyze data.  Anything you claim henceforth is suspect in the extreme.  Now I am done here.  I have work to do.  Good day, sir.

                  The general who wins the battle makes many calculations in his temple before the battle is fought. The general who loses makes but few calculations beforehand. - Sun Tzu

                  by Otteray Scribe on Mon Aug 27, 2012 at 07:17:51 AM PDT

                  [ Parent ]

                  •  I noticed you AGAIN did not answer the question!!! (0+ / 0-)

                    Hmm..... could it be that you are avoiding something?!?!

                    OK for the third time: what "proofs" do you want to see?

                    As for how to do a correlation analysis, I have shown you one above.  You have yet to tell me what is wrong with it other than to say I did not provide any "proofs".  And when asked what "proofs" you want to see, you dodge and refuse to answer the question.

                    Let's try this:  here is a proof:

                    Segment PQ is congruent to segment ST because PQ = ST = 4.
                    Angle Q is congruent to angle T because angle Q = angle T = 100 degrees.
                    Segment QR is congruent to segment TV because QR = TV = 5.
                    Triangle PQR is congruent to triangle STV by Side-Angle-Side.
                    There: I have now providced a "proof".  So you can no longer tell me this study is flawed because I did not supply a "proof".

                    "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

                    by Hugh Jim Bissell on Mon Aug 27, 2012 at 07:31:37 AM PDT

                    [ Parent ]

                    •  Copy and paste is a wonderful thing (7+ / 0-)

                      for the unthinking.

                      The general who wins the battle makes many calculations in his temple before the battle is fought. The general who loses makes but few calculations beforehand. - Sun Tzu

                      by Otteray Scribe on Mon Aug 27, 2012 at 07:33:03 AM PDT

                      [ Parent ]

                      •  The study is sound - I provided a "proof"! n/t (0+ / 0-)

                        "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

                        by Hugh Jim Bissell on Mon Aug 27, 2012 at 07:34:37 AM PDT

                        [ Parent ]

                        •  You are simply trolling (7+ / 0-)

                          If you understand what a proof is, you would provide it based on your data.

                          Trolling is frowned upon at Daily Kos.

                          I don't know which lie to believe anymore.

                          by Captain Janeway on Mon Aug 27, 2012 at 07:44:25 AM PDT

                          [ Parent ]

                        •  What the hell does a geometry problem (4+ / 0-)

                          have to do with a nonparametric statistical analysis?  The only thing you "proved" was that you know nothing of math.  Or geometry.  My guess is that you struggled with ninth grade algebra and may have failed geometry, based on the aggregate of your responses.  

                          I just got home from the office and have not had time to fiddle with this blog.  There are much more interesting things going on over at professor Turley's law blog.  At any rate, I have been looking at replies to my comments.

                          You claim to be some kind of medical researcher who publishes in peer-reviewed journals?   Give me a fricking break!  We all know that you can claim to be anything you want on the internet.  You gave yourself away with that comment and the so-called proof above.  A bloviator.  And certainly "creative" with the truth.  

                          Just a troll, and not a very good one at that.  And don't lecture people with advanced degrees on how to do math or correlations when you clearly don't know the difference between algebra, calculus and geometry.  

                          The general who wins the battle makes many calculations in his temple before the battle is fought. The general who loses makes but few calculations beforehand. - Sun Tzu

                          by Otteray Scribe on Mon Aug 27, 2012 at 03:50:39 PM PDT

                          [ Parent ]

                •  Medical science and I am "out of my league? (10+ / 0-)

                  Oh noes, I guess ER Doc, labwitchy, myself and some others here are going to have to turn in our degrees since you know more than the rest of us.  How sad.  Thirteen years of university education gone to waste because you say so.  Out of our league?  Bullshit!

                  It is somebody else here that is out of their league.  Have a nice day playing with your Dunning-Kruger Effect.

                  The general who wins the battle makes many calculations in his temple before the battle is fought. The general who loses makes but few calculations beforehand. - Sun Tzu

                  by Otteray Scribe on Mon Aug 27, 2012 at 07:30:27 AM PDT

                  [ Parent ]

                •  Interesting that you'd say "medical science" (7+ / 0-)
                  You tell me what "proofs" you think are relevant to the study that was done.  This is not engineering; it is medical science, and you are obviously out of your league.
                  In reference to the above recommended book:

                  About the Author:
                  William Shadish (Ph.D., 1978, Purdue University) is a professor of psychology at the University of Memphis. His recent research pertains to experimental design, meta-analysis, methodology, and program evaluation theory. In the past, he has done extensive research on long-term care for the chronically mentally ill. With his colleagues at the University of Memphis, Dr. Shadish has studied the psychology of science, both theoretically and empirically.

                  Thomas D. Cook (Ph.D., 1967, Stanford University) is a professor of sociology, psychology, education and social policy, as well as a Faculty Fellow, Institute of Policy Research at Northwestern University. His major research interests include examining routes out of poverty and methodology, dealing with the design and execution of social experiments, methods for promoting causal generalization, and theories of evaluation practice. Dr. Cook has written or edited seven books and has published numerous articles and book chapters. He was the recipient of the Myrdal Prize for Science from the Evaluation Research Society in 1982 and the Donald Campbell Prize for Innovative Methodology from the Policy Sciences Organization in 1988. He is a trustee of the Russell Sage Foundation and a member of its committee on the Future of Work.

                  I fail to see "Engineer" listed in either biography, rather we see a impressive resumes based on psychological and sociological fields of expertise.

                  Thus pertinent to the topic of crime, violence, gun control, mental illness, suicide, and the published study thereof.

            •  You and Otteray got on a tangent here. (0+ / 0-)

              I think it would  be more useful to simply supply the calculations applied.  There's no need to conduct a refresher course in random variables here, but since this is not a peer reviewed piece and people are short on time, it'd be nice to see something a bit more explicit.

              If you can handle LaTeX, I'd advise using your personal page on Wikipedia as a scratch sheet and supply the link.

        •  Please explain. (0+ / 0-)

          Can you please explain to me how I use "flikr" to put images in a dk diary?  Sorry for my obvious ignorance.

          "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

          by Hugh Jim Bissell on Sun Aug 26, 2012 at 07:04:51 PM PDT

          [ Parent ]

      •  Link offsite. (2+ / 0-)
        Recommended by:
        IndieGuy, KVoimakas

        Write up a Wordpress or Blogger version of this piece.

  •  statistical waters are muddied (10+ / 0-)

    by lack of presentation of length of time of one particular gun's ownership, number of existing guns in circulation, new gun ownership versus increase of actual population.

    There are so many undefined variables, that a sound conclusion one way or another seems unlikely and subject to subjective interpretation.

    Have you hugged your Boeuf Bourguignon today?

    by wretchedhive on Sun Aug 26, 2012 at 02:50:35 PM PDT

  •  According to the table in the diary... (15+ / 0-)

    If we compare 2001 and 2009 data on gun fatalities vs. NICS data we see:

    --Gun sales went up by a whopping 57.5%
    --Fatal injuries went up by only 6%

    There may be a correlation between increased sales and increased fatalities, but it takes nearly a 10% increase in sales to produce a 1% increase in fatal injuries.  Reducing that to a single purchase, I can buy a gun without appreciably increasing my risk of fatal injury.  Throw in safe storage practices and proficiency training, and I further mitigate the risk.

    I almost fell today when my treadmill belt suddenly stopped.  By the way, this treadmill was given to me after its previous owner fell and broke her hip upon first using the device.  Should we outlaw treadmills, or should I lubricate the walking belt, make a few tension adjustments, and learn how to use the damn thing?

    "First they ignore you, then they laugh at you, then they fight you, then you win". Mohandas K. Gandhi

    by DaveinBremerton on Sun Aug 26, 2012 at 03:01:20 PM PDT

  •  Do we account for gun injuries that (10+ / 0-)

    are a result of:

    -accidents (ie, not attempted homicide)
    -suicide
    -people injured by any authorized gun use (ie, police/military/security guards/lawful civilian defense/etc)

    ...or is it just "X amount of injuries, Y amount of sales, draw your own conclusions"?

    I'm all for increasing safety standards and training, for example, but linking random statistics with no corroborating facts or contexts is just a waste of time.

    •  The diarist is operating under the delusion that (8+ / 0-)

      linking random statistics with no corroborating facts or contexts is "science".

      Non enim propter gloriam, diuicias aut honores pugnamus set propter libertatem solummodo quam Nemo bonus nisi simul cum vita amittit. -Declaration of Arbroath

      by Robobagpiper on Sun Aug 26, 2012 at 03:48:56 PM PDT

      [ Parent ]

      •  This is not "random" data (1+ / 0-)
        Recommended by:
        ZenTrainer

        Wedging that word in where it does not belong is not productive.

        The data is incomplete, the number crunching is incomplete, but there is no reason for ad homs. The author put effort into trying to back his position. That's 100,000 times more laudable than belittling his effort.

        •  Thank you (2+ / 0-)
          Recommended by:
          ZenTrainer, Sandino

          thank you for your positive feedback.

          But please tell us what data (in your opinion) would make this study complete?  What analysis would you do?

          And tell us how to proceed when the data you want is not actually available (as often happens in the medical and social sciences)?  Does that then mean that no can or should be done?  (Keep in mind that a lot of the data we might want to "prove" evolution or climate change is not available.  Does that mean - as many fundamentalists suggest - that evolution and/or climate change can not be "proved"?)

          "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

          by Hugh Jim Bissell on Sun Aug 26, 2012 at 07:28:37 PM PDT

          [ Parent ]

          •  You won't get the data (3+ / 0-)
            Recommended by:
            IndieGuy, theatre goon, oldpunk

            There are no objective observers either flesh or machine that records each event when a gun is used. Just look at one case, the Zimmerman case, and notice all the differences in witness comments and the number of facts in dispute.

            Analyze all you want using the existing data but do not announce a definitive answer has been reached. Say, "what do you think of this?' that's fine. that gets discussion rolling. But don't claim a proof has been established when it hasn't.

            Are you seriously comparing the two-dozen data points you used with the billions or trillions of data points available to climate change scientists? The tens of thousands of them?

            That's kinda the point. Look how many years, experiments, man-years and calculations that have gone into climate science. And only now are they starting to use the language of certainty.

            And they "just" apply physics. You are delving into the realm of human behavior which is magnitudes more complicated and chaotic.

            So crunch numbers all you want. Just present your work as food for thought.

            •  The techniques are the same (0+ / 0-)

              I used the exact same techniques as the scientists who study climate change: collect data, calculate regression and correlation, report results.

              Now the climate scientists have tens of thousands of temperature recordings to work with.  But the FBI only started collecting NICS data in 1999, and they only report their data once a year.  

              So the only difference between what the climate scientists do and what I did here is the number of available data points.

              Now, if you want to say "hey, you only have 10-12 years worth of data, and I'm not sure your results will hold over 100 years worth of data", then I would say that is a valid criticism, and I will be happy to redo the study after those 100 years have gone by.  But until that time, we have to live with the FACT that we used the available data, and when the available data was analyzed (using the same techniques as climate scientists (and since when have climate scientists become the arbitrators of what is correct or incorrect in science? )), we found the results reported above.

              And those results will have to stand for the time being - gun sales and gunshot injuries have both been increasing over the past decade, and are highly correlated.

              "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

              by Hugh Jim Bissell on Mon Aug 27, 2012 at 07:19:54 AM PDT

              [ Parent ]

        •  he.put.effort.into.blowing.smoke.that.is.it (4+ / 0-)

          Vaya con Dios Don Alejo
          I want to die a slave to principles. Not to men.
          Emiliano Zapata

          by buddabelly on Sun Aug 26, 2012 at 09:12:59 PM PDT

          [ Parent ]

        •  One of the problems is... (4+ / 0-)
          Recommended by:
          kestrel9000, IndieGuy, oldpunk, deedogg

          ...that the diarist cobbled together some woefully inadequate data with something between fatally-flawed and nonexistent analysis to arrive at a conclusion that he already held.

          When his methodology is shown to be wholly inadequate, he reverts to personal insult, equivocation, and the Internet version of sticking one's fingers in one's ears and loudly saying "lalalalalala."

          I mean, c'mon, there wasn't even an attempt at control for population increase.  It's not like we're talking about some arcane, unheard-of data point here.

          No, there was no real attempt at reaching any new insight here, it was an attempt to support a previously held position and bolster it with a foundation of meaningless numbers.

          The only question that remains -- and it's not a particularly important one -- is whether he didn't know what he was doing in the first place or if he purposefully tried to bamboozle readers with flawed statistics.

          Yes, I often dress as a pirate. Your point?

          by theatre goon on Mon Aug 27, 2012 at 04:19:26 AM PDT

          [ Parent ]

          •  It still was not random data (0+ / 0-)

            The data was germane to the study. Criticize that which deserves criticizing.

            •  I didn't say it was random. (1+ / 0-)
              Recommended by:
              IndieGuy

              I said it was inadequate and did not support the conclusions that the diarist took from it.

              I also said that the numbers are meaningless -- and they are, as they are presented without full explanation and without any meaningful analysis, nor any consideration of the myriad of other variables that would be necessary for any such discussion.

              Yes, I often dress as a pirate. Your point?

              by theatre goon on Mon Aug 27, 2012 at 06:28:47 AM PDT

              [ Parent ]

    •  The data includes ALL gunshot injuries (3+ / 0-)
      Recommended by:
      Sandino, ZenTrainer, Joy of Fishes

      The data on gunshot injuries includes ALL injuries, regardless of cause.

      Please, tell us, what is (according to you) the proper way to test for a correlation of gun sales and gun injuries?

      As an aside, I would have preferred to test the association of guns owned, instead of guns sold.  But there was no reliable yearly information on guns owned.  If you know of where I can find information of this sort, I am happy to make use of it.

      "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

      by Hugh Jim Bissell on Sun Aug 26, 2012 at 03:49:30 PM PDT

      [ Parent ]

      •  That's the problem, there is no reliable (9+ / 0-)

        source that is unbiased. The most reliable sources I know of for gun ownership (and there are many) run the gamut from a low of 50 million to a high of 80 million, and that's too big of a spread to base reliable statistics from. And, of course, a lot of gun information also comes from unreliable sources, such as both NRA and the Brady Center. Both have axes to grind and their numbers cannot always be trusted.

        The problem with law enforcement numbers, from FBI or any other agency, is that they also reflect only crimes or injuries that happened --whereas in the event that someone thinks they may have prevented ac rime by telling someone "go away-- a have a gun!" they probably did not bother to call the police to tell them that a crime didn't just happen.

        Law-enforcement numbers also don't always reflect whether the firearm involved in an injury or crime event was legally owned by the wielder, or stolen or even smuggled from overseas. Firearm crime and injury rates may also reflect a wide variety of factors such as poverty in a given area, or even institutional bias by police who will respond to a report of a Black person with a gun, but not to a report of a White person with a gun.

        So, your statistics might be reflecting nothing at all: it could be that tens of thousands of guns were sold, yet not a one of them was used in a injury of any sort... while at the same time, police shootings of criminals in the line of duty might have gone up (maybe as a result of better training) and thus, more injuries from police service weapons are being misinterpreted as mass civilian carnage.

        Likely? Probably not. But not impossible under the broad brush you have painted with. Firearms topics are influenced by too many factors, too much disinformation, and too much misunderstanding to be dealt with by easy, broad applications.

        •  The FBI NICS data (1+ / 0-)
          Recommended by:
          Sandino

          The FBI NICS data does not "reflect only crimes or injuries that have happened".  The FBI NICS data is a direct measurement of how many inquiiries were made to the NICS system.

          Your suggestion that " it could be that tens of thousands of guns were sold, yet not a one of them was used in a injury of any sort... while at the same time, police shootings of criminals in the line of duty might have gone up (maybe as a result of better training) and thus, more injuries from police service weapons are being misinterpreted as mass civilian carnage."  is entirel irrelevant to the study that I described in the article.  That study had nothing whatsoever to do with crimes, but was only about the number of guns sold (modeled by FBI NICS data), and the number of gun injuries of ANY sort suffered.  

          "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

          by Hugh Jim Bissell on Sun Aug 26, 2012 at 07:20:22 PM PDT

          [ Parent ]

          •  No, you're studying gunshot wounds. (7+ / 0-)

            Period. With no differentiation between whether said gunshot wound was an attempted murder, or a hunting accident, or a suicide... or even a police officer lawfully discharging his firearm in the line of duty.

            These are all very different types of gunshot wounds, or I should say, the context is very different. NICS data reflects an attempted sale, and that's it. You even admit that there is no proof said sale went through. So you've probably already got far more NICS checks than "actual" sales.

            While it is a logical assumption that the increase in checks means an increase in sales, and an increase in sales means an increase in ownership and use, and an increase in ownership will eventually mean there are more chances for accidents to happen, by the time you reach that conclusion you are way out on a limb and drawing inferences that are unsupportable.

            An increase in gunshot wounds might be because more first-time buyers are purchasing weapons and making mistakes with them. Or, the increase in gunshot wounds might have nothing to do with civilian sales and reflect more accurate shooting by law enforcement agents-- presumably outside New York City.

            Occam's Razor may support "increased sales = increased wounds" but I don't know if that truly counts as "scientific reasoning". It wouldn't stand up in a court of law and I don't think it would stand up to peer review, since the cause and effect correlation is not clearly delineated.

            •  then there's taken out of service and losses (5+ / 0-)

              due to rust, buybacks, confiscation during arrest etc...and overseas sales from private sellers to foreign  purchasers  for who ever..and exported. Criminals and rule breakers failed to check in when they checked out.

              This machine kills Fascists.

              by KenBee on Sun Aug 26, 2012 at 11:24:37 PM PDT

              [ Parent ]

              •  That's true: it assumes the (4+ / 0-)
                Recommended by:
                IndieGuy, theatre goon, KenBee, oldpunk

                firearms entering society expands and piles on top of existing constants. All it takes is one house fire at the home of a collector to remove several dozen from circulation, and spark a mini-boom when the guy gets back on his feet and starts to restock.

                An interesting angle on this also is the "gunwalking" schemes done by both Republican and Democratic administrations-- how many sales technically would have been denied, but then went on to be guaranteed crime weapons because of an ongoing investigation? Even though the stats from that will be small, it will probably push the "margin of error" rate to unacceptable levels.

      •  I'd like to see your gun *sales* data. (2+ / 0-)
        Recommended by:
        theatre goon, IndieGuy

        Last I checked, there was no reliable dataset for that as well.

  •  You are missing a particularly telling stat..... (10+ / 0-)

    that of injury rate per population (i.e. x per 100K people).

    If the total number of incidents went up, but the population went up faster, overall rate is likely to drop.

    •  Agreed - need to control for population change (0+ / 0-)

      From this discussion, I have gotten a couple of good ideas for futrue research.  Controlling for population change is one such good idea.

      "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

      by Hugh Jim Bissell on Mon Aug 27, 2012 at 10:45:35 AM PDT

      [ Parent ]

  •  Would you mind linking to your source data? (4+ / 0-)

    Especially gun sales data.

    •  It would appear... (6+ / 0-)

      ...that it is not actually based on gun sales data -- but on the number of NICS checks performed.

      So, not only do we have flawed analysis, we have inclusion of numbers that don't even show what the author claims that they show.

      Oops.

      Yes, I often dress as a pirate. Your point?

      by theatre goon on Mon Aug 27, 2012 at 06:30:11 AM PDT

      [ Parent ]

      •  I'm actually willing to consider NICS a good proxy (5+ / 0-)

        But I'd like to still see the raw take myself.

        •  it's not though.... (4+ / 0-)

          .... purchase multiple firearms at the same time from a licensed dealer and there's only one background check.  Purchase a firearm in some "waiting period" states and there may well be two background checks, one at time of purchase, and another at time of pick-up.

          Then there's private party sales, which are not regulated in most states, and only partially (handguns) regulated in others.

          There are four boxes to be used in the defense of liberty: soap box, ballot box, jury box and ammo box. Use in that order.

          by Crookshanks on Mon Aug 27, 2012 at 09:53:36 AM PDT

          [ Parent ]

          •  I'm plowing through some of it now. (2+ / 0-)
            Recommended by:
            KVoimakas, oldpunk

            We can mitigate certain problems with the set by omitting states with waiting periods.  That's one of two ways I can think of that you can make gun sale numbers look larger than the actually are.  The other two are positive hits on NICS killing the sale, or declining to purchase for some reason after the check.  I think we can adjust for the latter if I can break down data on NICS hits into cleared and rejected.  Not sure how to address the third problem, though.

            But if you could, NICS checks on the reduced set should actually understate sales.

            In fact, by jiggering with this proxy set, I can actually deduce at least one additional covariate against the diarist's original assumption.  If, for example, the strength of correlation does not change significantly for muted gun sales data, it may indicate another underlying variable (or variables) not yet taken into account.

            •  I'm impressed! (0+ / 0-)

              I'm impressed that you are willing to take the time and effort to go through the data and consider possible flaws.  That suggest to me that you are willing to honestly consider and think about the research.  Thank you for that.

              You said in your comment that the FBI NICS data might actually understate sales of guns.  Do keep in mind that  the FBI NICS data only reflects gun buyers at federally-licensed dealers, and carries no information about transactions occurring from non-licensed dealers and private sales.

              So I think we can safely say that the FBI NICS data DOES INDEED underestimate ALL gun sales across the country.

              I think we can also safely say there are indeed underlying variables not yet taken into account.   As I said in the article:

              "It is important to note that a correlation of rising guns sales with increasing gunshot injuries does not prove that rising gun sales cause more gun injuries.  It only proves that the variables guns sales and gunshot injuries move in tandem."
              Notice that nowhere do I claim that increasing gun sales CAUSES increases in gunshot injuries.  I only claim that there exists an association of rising gun sales with rising gunshot injuries.  The exact mechanisms that result in rising gun sales and increasing gunshot injuries are not modelled, and indeed not even needed to demonstrate that an association exists.  This study says only that a linkage exists and it is a strong one.  What causes gun sales or gunshot injuries (those unknown underlying variables) to rise or fall is beyond the scope of this study.

              "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

              by Hugh Jim Bissell on Mon Aug 27, 2012 at 11:27:37 AM PDT

              [ Parent ]

              •  Hard to safely say that. (2+ / 0-)
                Recommended by:
                theatre goon, oldpunk

                For one, the secondary market doesn't increase the number of armed civilians, just the number of hands through which a firearm passes.  Second, private transfers at say...gun shows...are almost negligible--it's unclear as to whether they'd have an appreciable impact on total transactions.

                I'd point out one thing you're missing.  You've demonstrated tandem movement in a single direction; this is largely because your two variables do not oscillate greatly.  This is why we need to at least vary the proxy data.

                •  Good point (0+ / 0-)

                  You make a good point - used gun sales do not mean more guns, only that a gun changed hands.

                  There is probably also a number of guns "retired" every year: broken, discarded, "buy back" programs by authorities, dropped down a sewer grating, etc.

                  So if we are to model the number of guns available to users, we need to know not just how many are sold, but how many are taken out of circulation.  And good data on those two things is going to be very hard to come up with.  

                  The variable gun sales is imperfect.  But it still makes sense to study gun sales, because of the oft-reported story that "gun sales are increasing".  As imperfect as the FBI NICS data is, it is real-world data that we can check against the claim that "gun sales are increasing".

                  It is not necessary to show up AND down variation in order to prove a correlation exists.  Proving a correlation requires only that you have multiple measurements of two variables.  Two variable can still be correlated even if it is shown that neither variable increases or decreases.    

                  "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

                  by Hugh Jim Bissell on Mon Aug 27, 2012 at 12:14:01 PM PDT

                  [ Parent ]

          •  There is also... (2+ / 0-)
            Recommended by:
            KVoimakas, oldpunk

            ...no consideration of the percentage of NICS checks that disallow the sale altogether -- it may or may not be a large enough percentage to throw off the conclusions based on it, but since it wasn't considered at all, we won't know.

            At least, not in the "analysis" presented here.

            Yes, I often dress as a pirate. Your point?

            by theatre goon on Mon Aug 27, 2012 at 10:41:23 AM PDT

            [ Parent ]

      •  Give me a better source (0+ / 0-)

        I am happy to consider another source for inoformation about gun sales.

        What I would actually prefer is numbers of guns owned or "in circulation" in order to test the hypothesis that more guns "in circulation" is positively correlated with more gunshot injuries.

        But there is no good reliable data on number of guns owned or "in circulation" ('cause apparently, lots of gun-owners refuse to register their weapons with the authorities, even though all gun-owners are law-abiding citizens).  So because there are no good numbers on number of guns owned, I used guns sales instead.

        Here is what is needed: 1) the number of guns sold has to be available for every year; two or three years isn't enough, ten or so years is accptable, and 20 or more would be great; 2) the data should reflect the country as a whole, not just certain regions; 3) the data should come from a credible, verifiable source: the FBI is good (nationally-recognized), Joe's Blog About Gunz is not good (who the hell is Joe, and how do we know he's not just pulling numbers out of a hat?).

        So, tell me a better source.    

        "The fool doth think he is wise: the wise man knows himself to be a fool" - W. Shakespeare

        by Hugh Jim Bissell on Mon Aug 27, 2012 at 10:59:40 AM PDT

        [ Parent ]

Subscribe or Donate to support Daily Kos.

Click here for the mobile view of the site