* "About 99.8% of firearms and more than 99.6% of handguns will not be used to commit violent crimes in any given year."[1]

* Reason for elimination: This statistic neglects key information such as the number of guns in the U.S. Thus, it can create a misleading impression, given that, in 2008, roughly 436,000 violent crimes were committed by offenders visibly armed with a gun.[2] [3] [4]

* States "with higher gun ownership rates and weak gun laws have the highest rates of gun death."[5]

* Reasons for elimination:

1) The phrase "weak gun laws" is subjective and ill-defined.[6]

2) This assertion is missing key information and can be deceptive because it accounts for murders committed with guns but fails to account for lives saved with guns. Hence, it neglects the primary issue, which is the overall rate of violent deaths. This is significant because, as the chart below shows, many states with higher gun ownership rates also have the lowest homicide rates:

[7]

* "Right-to-carry" states allow individuals to carry firearms for protection against crime. In these states, the violent crime rate is 24% lower than the rest of the U.S., the murder rate is 28% lower, and the robbery rate is 50% lower.[8]

* Reason for elimination: This data does not account for other factors that impact crime rates, such as cultural differences, arrest rates, illegitimacy rates, poverty, etc.

Note that many gun control studies attempt to control for such factors, but opposing sides inevitably point to other factors that are uncontrolled,[9] and due to data limitations, it is practically impossible to control for all relevant factors.[10] Conversely, some researchers fault studies that do not show significant results until the effects of controls are considered.[11]

In accordance with our mission to provide verifiable facts, Just Facts uses time-series data and lets this data speak for itself instead of subjecting it to statistical analyses. For example, we provide homicide rates in the state of Florida in the years leading up to and after passage of the Florida "right-to-carry" law. Such data does not prove cause and effect, but it does allow us to observe trends and limits the impact of numerous variables because the data is drawn from a large population set with limited demographic changes from year to year. To provide additional context, Just Facts sometimes provides comparative data (such as homicide rates for the nation as a whole over the same time period), but we provide this data in unadulterated form; we do not control for it in our calculations.

* "In homes with guns, the homicide of a household member is almost 3 times more likely to occur than in homes without guns."[12] [13]

* Reasons for elimination: This statistic is based on a three-county study comparing households in which a homicide occurred to demographically similar households in which a homicide did not occur. After controlling for several variables, the study found that gun ownership was associated with a 2.7 times increase in the odds of homicide.[14] This study does not meet Just Facts' Standards of Credibility because:

1) The study blurs cause and effect. As explained in a comprehensive analysis of firearm research conducted by the National Research Council, gun control studies such as this (known as "case-control" studies) "fail to address the primary inferential problems that arise because ownership is not a random decision. ... Homicide victims may possess firearms precisely because they are likely to be victimized."[15]

2) The study's results are highly sensitive to uncertainties in the underlying data. For example, minor variations in firearm ownership rates (which are determined by interview and are thus dependent upon interviewees' honesty) can negate the results.[16] [17]

3) The results are arrived at by subjecting the raw data to statistical analyses instead of letting the data speak for itself. (For reference, the raw data of this study shows that households in which a homicide occurred had a firearm ownership rate of 45% as compared to 36% for non-homicide households. Also, households in which a homicide occurred were twice as likely have a household member who was previously arrested (53% vs. 23%), five times more likely to have a household member who used illicit drugs (31% vs. 6%), and five times more likely to have a household member who was previously hit or hurt during a fight in the home (32% vs. 6%).[18])

Back to Facts about Gun Control

 

Footnotes

[1] "NRA Firearms Fact Card." National Rifle Association, 1998.

[2] NOTE: The U.S. government publishes two primary crime measures: The FBI's "Uniform Crime Report" (UCR) and the Department of Justice's "National Crime Victimization Survey" (NCVS). The UCR is based upon incidents reported to law enforcement authorities and does not account for unreported crimes. The NCVS is based upon data gathered from extensive interviews, and hence, provides more accurate estimates of crime than the UCR.* The NCVS, however, does not provide data on: murders and nonnegligent manslaughters (because the victims cannot be interviewed), crimes committed against children under the age of 12, and commercial crimes such as robberies of banks and convenience stores.† Therefore, Just Facts uses the NCVS data as a baseline and extrapolates the missing information from UCR and NCVS data.

* Book: Firearms and Violence: A Critical Review. By the Committee to Improve Research and Data on Firearms and the Committee on Law and Justice, National Research Council of the National Academies. Edited by Charles F. Wellford, John V. Pepper, and Carol V. Petrie. National Academies Press, 2005.

Page 21: "The National Crime Victimization Survey ... is widely viewed as a "gold standard for measuring crime victimization."

Page 30: "Although the NCVS data do many things right, they are, like any such system, beset with methodological problems of surveys in general as well as particular problems associated with measuring illicit, deviant, and deleterious activities...."

† Report: "The Nation's two crime measures." U.S. Department of Justice, October 2004. http://bjs.ojp.usdoj.gov/content/pub/pdf/ntcm.pdf

The U.S. Department of Justice administers two statistical programs to measure the magnitude, nature, and impact of crime in the Nation: the Uniform Crime Reporting (UCR) Program and the National Crime Victimization Survey (NCVS). Each program produces valuable information about aspects of the Nation's crime problem. Because the UCR and NCVS programs are conducted for different purposes, use different methods, and focus on somewhat different aspects of crime, the information they produce together provides a more comprehensive panorama of the Nation's crime problem than either could produce alone. …

The FBI's UCR program … collects information on the following crimes reported to law enforcement authorities: homicide, forcible rape, robbery, aggravated assault, burglary, larceny-theft, motor vehicle theft, and arson. …

[Regarding the NCVS:] Two times a year, U.S. Census Bureau personnel interview household members in a nationally representative sample of approximately 42,000 households (about 75,000 people). Approximately 150,000 interviews of persons age 12 or older are conducted annually. …

[The NCVS] does not measure homicide or commercial crimes (such as burglaries of stores). …

Second, the two programs measure an overlapping but non-identical set of crimes. The NCVS includes crimes both reported and not reported to law enforcement. The NCVS excludes, but the UCR includes, homicide, arson, commercial crimes, and crimes against children under age 12.

[3] CALCULATION:

4,856,510 NCVS violent victimizations (not including: (a) fatal crimes, (b) crimes committed against children under the age of 12, and (c) commercial crimes)*

+ (a) 16,272 UCR murders and nonnegligent manslaughters (i.e., fatal crimes)† 

+ (b) 244,866 nonfatal violent victimizations committed against children under age 12 (extrapolated)‡

+ (c) 222,125 commercial robberies (extrapolated)§

≈ 5,339,773 violent criminal victimizations

* Bulletin: "National Crime Victimization Survey: Criminal Victimization, 2008." By Michael R. Rand. Bureau of Justice Statistics, U.S. Department of Justice, September 2009. http://bjs.ojp.usdoj.gov/content/pub/pdf/cv08.pdf

Page 1: "Violent crimes" include "rape/sexual assault, robbery, and aggravated and simple assault."

Page 1, Table 1 shows 4,856,510 violent criminal victimizations, of which 551,830 are robberies.

† Report: "2008 Crime in the United States, Murder." Federal Bureau of Investigation, U.S. Department of Justice, September 2009. http://www2.fbi.gov/ucr/cius2008/offenses/violent_crime/murder_homicide.html

"The FBI's Uniform Crime Reporting (UCR) Program defines murder and nonnegligent manslaughter as the willful (nonnegligent) killing of one human being by another. … An estimated 16,272 persons were murdered nationwide in 2008."

NOTE: Although the verbiage above could imply that "nonnegligent manslaughter" and "murder" are categorized as separate offenses, this is not the case. As explained in correspondence from the U.S. Department of Justice to Just Facts (January 15, 2010), "These two are counted as one offense, and numbers defining them are not separated." Hence, the 16,272 murders cited above also includes nonnegligent manslaughters.

‡ Report: "2008 Crime in the United States, Expanded Homicide Data – Table 9." Federal Bureau of Investigation, U.S. Department of Justice, September 2009. http://www2.fbi.gov/ucr/cius2008/offenses/expanded_...

NOTE: Extrapolating data from this source (further details available upon request), approximately 4.8% of murder victims were under the age of 12. If a similar percentage of nonfatal violent victimizations occur in this age group:

y = violent victimizations, ages 0-11

y ≈ (0.048 × 4,856,510 NCVS violent victimizations) / (1 - 0.048)

y ≈ 244,866

§ Report: "2008 Crime in the United States, Robbery." Federal Bureau of Investigation, U.S. Department of Justice, September 2009. http://www2.fbi.gov/ucr/cius2008/offenses/violent_crime/robbery.html

NOTE: Excluding hold-ups of lemonade stands, it is fairly safe to assume there are few commercial robberies of children under the age of 12. Extrapolating data from this source (further details available upon request), approximately 28.7% of robberies are commercial and 71.3% are private. Applying these proportions to the NCVS data:

y = commercial robberies

y ≈ (0.287 × 551,830 NCVS (private) robberies) / (1 - 0.287)

y ≈ 222,125

[4] CALCULATION:

343,550 NCVS violent victimizations in which the offender was armed with a firearm (not including: (a) fatal crimes, (b) crimes committed against children under the age of 12, and (c) commercial crimes).*

+ (a) 10,886 murders and nonnegligent manslaughters in which a firearm was used (extrapolated)†

+ (b) 17,385 nonfatal violent victimizations committed against children under age 12 in which the offender was armed with a firearm (extrapolated)‡

+ (c) 53,310 commercial robbery victimizations in which the offender was armed with a firearm (extrapolated)§

 + 10,706 rapes/sexual assaults in which the offender was armed with a firearm (extrapolated)#

≈ 435,837 violent victimizations in which the offender was armed with a firearm

* Bulletin: "National Crime Victimization Survey: Criminal Victimization, 2008." By Michael R. Rand. Bureau of Justice Statistics, U.S. Department of Justice, September 2009. http://bjs.ojp.usdoj.gov/content/pub/pdf/cv08.pdf

Page 6: "An offender was armed with a gun, knife, or other object used as a weapon in an estimated 20% of all incidents of violent crime in 2008 (table 7)."

Page 6, "Text table 3. Firearm use in violent crime, 1999 and 2008": violent victimizations involving a firearm = 343,550

Page 6, "Table 7. Presence of weapons in violent incidents, by type, 2008":

- percentage of robberies involving a firearm = 24%

- number of rapes/sexual assaults involving a firearm = 0 {Note: Just Facts does not take this figure at face value and instead, extrapolates an estimated number.}

NOTE: With regard to guns and other weapons, this report employs the words "presence" and "use" interchangeably. This is evident by the fact that "Text table 3. Firearm use in violent crime, 1999 and 2008" and "Table 7. Presence of weapons in violent incidents, by type, 2008" cite the same figure (303,880) for the number of violent firearm incidents. Thus, the word "use" does not necessarily mean the offender fired the gun. Instead, the word "use" means the offender was armed with a gun.

† Report: "2008 Crime in the United States, Expanded Homicide Data – Table 9." Federal Bureau of Investigation, U.S. Department of Justice, September 2009. http://www2.fbi.gov/ucr/cius2008/offenses/expanded_...

NOTE: This table states that 66.9% of all murders were committed with firearms, but this data does not account for all homicides – only those for which a "Supplemental Homicide Report" was filed (correspondence from U.S. Department of Justice to Just Facts, January 15, 2010). Hence, this table shows 14,180 total murder victims, while the UCR states: "An estimated 16,272 persons were murdered nationwide in 2008." Assuming the proportion of murders committed with firearms is approximately the same regardless of whether or not a Supplemental Homicide Report is filed:

16,272 ×.669 ≈ 10,886 people murdered with firearms

‡ 2008 NCVS data shows 4,856,510 nonfatal violent victimizations of people ages 12 and over, of which 343,550 or 7.1% involved the use of firearms. Based upon the extrapolation above, roughly 244,866 nonfatal violent victimizations were committed against children under the age of 12. Assuming the proportion of victimizations committed with firearms is approximately the same regardless of whether or not the victims are under the age of 12 (probably a high estimate):

244,866 × .071 ≈ 17,385 nonfatal violent victimizations committed against children under age 12 in which the offender was armed with a firearm

§ Based upon the extrapolation above, roughly 222,125 commercial robberies were committed in 2008. 2008 NCVS data shows 24% of noncommercial robberies are committed using firearms. Assuming the proportion of robberies committed with firearms is approximately the same regardless of whether or not they are commercial (probably a low estimate):

222,125 × .24 ≈ 53,310 commercial robbery victimizations in which the offender was armed with a firearm

# 2008 NCVS data shows zero rape/sexual assaults committed by an offender armed with a gun, and the 2008 UCR explicitly states, "Weapon data are not collected for forcible rape offenses." [Report: "2008 Crime in the United States, Violent Crime." Federal Bureau of Investigation, U.S. Department of Justice, September 2009. http://www2.fbi.gov/ucr/cius2008/offenses/violent_crime/index.html] Hence, Just Facts extrapolates the number of rape/sexual assaults involving firearms based upon several relatable NCVS and UCR metrics (further details available upon request).

[5] Press release: "States with Higher Gun Ownership and Weak Gun Laws Lead Nation in Gun Death." Violence Policy Center, May 6, 2009. http://www.vpc.org/press/0905gundeath.htm

States with higher gun ownership rates and weak gun laws have the highest rates of gun death according to a new analysis by the Violence Policy Center (VPC) of just-released 2006 national data (the most recent available) from the federal Centers for Disease Control and Prevention's National Center for Injury Prevention and Control. …

…. By contrast, states with strong gun laws and low rates of gun ownership had far lower rates of firearm-related death. Ranking last in the nation for gun death was Hawaii, followed by Massachusetts, Rhode Island, Connecticut, and New York. (See chart below for top and bottom five states.

The VPC defined states with "weak" gun laws as those that add little or nothing to federal restrictions and have permissive concealed carry laws allowing civilians to carry concealed handguns.

[6] As shown in the citation above, the Violence Policy Center characterizes Connecticut (which has the fourth lowest rate of gun death in the nation) as a state with "strong gun laws." Conversely, the VPC defines states with "weak gun laws" as those with "permissive concealed carry laws allowing civilians to carry concealed handguns." Yet, in spite of the foregoing characterization and definition, Connecticut has a "may-issue"* concealed carry law allowing civilians to carry concealed handguns that could certainly be described as "permissive."

More specifically, Connecticut law allows local police, wardens, or selectmen to issue temporary concealed carry permits to private citizens, which the state government reviews for issuance of "a state permit to carry a pistol or revolver."† Between January 1, 2000 and December 31, 2009, the state of Connecticut issued 166,190 permits, while during almost the same period (January 1, 2000- February 24, 2010), the state denied only 436 permits (2.6% of the total).‡ Thus, as the National Rifle Association's Institute for Legislation Action has explained, in Connecticut and a few other "may-issue" states, "local law enforcement will generally issue a permit to the same kinds of persons who would qualify for a permit in a Shall-Issue state, and many times these states are included on Shall-Issue state lists."§

NOTES:

* Report: "Gun Permit Issues." By Veronica Rose. Connecticut Office of Legislative Research, April 10, 2008. http://www.ct.gov/bfpe/cwp/view.asp?a=1838&Q=...

"Connecticut is a "may issue" state, in that the permit-issuing official has discretion to determine whether to issue or revoke a permit."

† Connecticut Law: Title 29, Chapter 529, Section 29-28(b): "Permit to carry pistol or revolver." Accessed March 17, 2010 at http://law.justia.com/connecticut/codes/title29/sec29-28.html

‡ Correspondence from the Connecticut Special Licensing & Firearms Unit to Just Facts, February 24, 2010 and March 18, 2010.

§ Article: "The State (by State) of Right-To-Carry." By Dave Kopel. National Rifle Association Institute for Legislative Action, July 28, 2006. http://www.nraila.org/Issues/Articles/Read.aspx?id=198&issue=003

[7] Chart constructed with data from the following sources:

a) Report: "Crime in the United States, 2001." Federal Bureau of Investigation, U.S. Department of Justice. http://www2.fbi.gov/ucr/01cius.htm

Table 5: "Index of Crime by State."

b) "Survey Results 2001 for Nationwide: Firearms." Behavioral Risk Factor Surveillance System, North Carolina State Center for Health Statistics, September 20, 2002. http://www.schs.state.nc.us/SCHS/brfss/2001/us/firearm3.html

[8] Web page: "Right-to-Carry 2009." National Rifle Association of America, Institute for Legislative Action, May 7, 2009. http://www.nraila.org/Issues/factsheets/read.aspx?ID=18

RTC [right-to-carry] laws respect the right to self-defense by allowing individuals to carry firearms for protection. ...

... RTC states have lower violent crime rates, on average, compared to the rest of the country (total violent crime by 24 percent; murder, 28 percent; robbery, 50 percent; and aggravated assault, 11 percent).

[9] For example:

a) Article: "Domestic Disputes: Bad social science and bad legal policy." By Eugene Volokh. National Review, June 17, 2003. http://www.nationalreview.com/comment/comment-volokh061703.asp

The study, however, completely failed to control for what might well be the most important factors: whether the household contained violent criminals, gang members, drug dealers, and the like. These are the very factors that might cause both gun ownership and gun death. And because the study didn't control for them, it says nothing about whether gun ownership really "increases the odds" that a law-abiding citizen will be killed. The study's results could easily flow simply from the huge set of homicide victims who are themselves criminals.

b) Book: Firearms and Violence: A Critical Review. By the Committee to Improve Research and Data on Firearms and the Committee on Law and Justice, National Research Council of the National Academies. Edited by Charles F. Wellford, John V. Pepper, and Carol V. Petrie. National Academies Press, 2005. Page 273: "The importance of controlling for the correct set of covariates is well known. In fact, much of the debate between Lott and his statistically orientated critics focuses on determining the correct set of control variables."

NOTE: The quote just above and the quote just below illustrate how there is no satisfying the opposing sides of this debate with control variables. For as Lott states, his "study uses the most comprehensive set of control variables yet used in a study of crime, let alone any previous study on gun control." [Book: More Guns, Less Crime. By John R. Lott, Jr. University of Chicago Press, 1998. Page 153.]

[10] Book: Firearms and Violence: A Critical Review. By the Committee to Improve Research and Data on Firearms and the Committee on Law and Justice, National Research Council of the National Academies. Edited by Charles F. Wellford, John V. Pepper, and Carol V. Petrie. National Academies Press, 2005.

Page ix: "One theme that runs throughout our report is the relative absence of credible data central to addressing even the most basic questions about firearms and violence. As we often state in the report, without much better data, important questions will continue to be unanswerable."

Page 1: "While there is a large body of empirical research on firearms and violence, there is little consensus on even the basic facts about these important policy issues."

Page 19: "In the committee's view, the major scientific obstacles for advancing the body of research and further developing credible empirical research to inform policy on firearms is the lack of reliable and valid data."

[11] Book: Firearms and Violence: A Critical Review. By the Committee to Improve Research and Data on Firearms and the Committee on Law and Justice, National Research Council of the National Academies. Edited by Charles F. Wellford, John V. Pepper, and Carol V. Petrie. National Academies Press, 2005.

Page 151 (conclusions regarding John R. Lott's concealed carry study): "No link between right-to-carry laws and changes in crime is apparent in the raw data, even in the initial sample; it is only once numerous covariates are included that the negative results in the early data emerge."

[12] Web page: "Factsheet: Guns in the Home." Johns Hopkins Center for Gun Policy and Research. Accessed March 29, 2010 at http://www.jhsph.edu/bin/g/k/guns_in_home.pdf

Although many gun owners keep a gun in the home for protection, studies have shown that ... the risks of keeping a gun in the home outweigh the benefits. In fact, in homes with guns, the homicide of a household member is almost 3 times more likely to occur than in homes without guns.⁵

⁵ Kellermann AL, Rivara FP, Rushforth NB et al. Gun ownership as a risk factor for homicide in the home. New England Journal of Medicine. 1993;329:1084-1091.

[13] Legal brief 07-290: "District of Columbia and Adrian M. Fenty, Mayor of the District Of Columbia, Petitioners, v. Dick Anthony Heller, Respondent. In the Supreme Court of the United States." By Linda Singer (Attorney General for the District of Columbia) and others. January 4, 2008. http://www.abanet.org/publiced/preview/briefs/pdfs/...

Page 52: "People who live in houses with firearms, particularly hand-guns, are almost three times more likely to die in a homicide, and much more likely to die at the hands of a family member or intimate acquaintance than people who do not. See Arthur L. Kellermann et al., Gun Ownership as a Risk Factor for Homicide in the Home, 329 New Eng. J. Med. 1084 (1993)."

[14] Paper: "Gun Ownership as a Risk Factor for Homicide in the Home." By Arthur L. Kellermann and others. New England Journal of Medicine, October 7, 1993. http://content.nejm.org/cgi/content/full/329/15/1084

"After controlling for these characteristics, we found that keeping a gun in the home was strongly and independently associated with an increased risk of homicide (adjusted odds ratio, 2.7; 95 percent confidence interval, 1.6 to 4.4)."

NOTE: The "odds ratio" is not the same as the "relative risk" (which is the measure of probability that most people understand).* However, Just Facts consulted with two independent authorities on statistics who stated that the odds ratio is a valid approximation of relative risk in this study.

* Paper: "Making Sense of Odds and Odds Ratios." By DA Grimes and KF Schulz. Obstetrics and Gynecology (New York), February 2008. 423-426. http://www.ncbi.nlm.nih.gov/pubmed/18238982

Page 423: Despite their growing use in the medical literature,^1,2 odds ratios remain poorly understood by clinicians (and by some researchers, as well).²

Pages 423-424:"Both clinicians and patients readily understand relative risk. It is simply a ratio of probabilities."

[15] Book: Firearms and Violence: A Critical Review. By the Committee to Improve Research and Data on Firearms and the Committee on Law and Justice, National Research Council of the National Academies. Edited by Charles F. Wellford, John V. Pepper, and Carol V. Petrie. National Academies Press, 2005. Page 5:

Because of current data limitations, researchers have relied primarily on two different methodologies. First, some studies have used case-control methods*, which match a sample of cases, namely victims of homicide or suicide, to a sample of controls with similar characteristics but who were not affected by violence. ...

Case control studies show that violence is positively associated with firearms ownership, but they have not determined whether these associations reflect casual mechanisms. Two main problems hinder inference on these questions. First and foremost, these studies fail to address the primary inferential problems that arise because ownership is not a random decision. For example, suicidal persons may, in the absence of a firearm, use other means of committing suicide. Homicide victims may possess firearms precisely because they are likely to be victimized.

NOTE:

* The study we are discussing is a case-control study. Paper: "Gun Ownership as a Risk Factor for Homicide in the Home." By Arthur L. Kellermann and others. New England Journal of Medicine, October 7, 1993. http://content.nejm.org/cgi/content/full/329/15/1084

"[W]e conducted a population-based case-control study to determine the strength of the association between a variety of potential risk factors and the incidence of homicide in the home."

[16] Book: Firearms and Violence: A Critical Review. By the Committee to Improve Research and Data on Firearms and the Committee on Law and Justice, National Research Council of the National Academies. Edited by Charles F. Wellford, John V. Pepper, and Carol V. Petrie. National Academies Press, 2005.

Page 119 [regarding case-control studies such as Kellermann et al., 1993]: "[E]ven small degrees of misreporting on ownership by either the cases or the controls can create substantial biases in the estimated risk factors (see Kleck, 1997, for an illustration of these biases)."

Page 35:

While surveys of firearms acquisitions, possession, and use are of varying quality and scope, they all share common methodological and survey sampling-related problems. The most fundamental of these is the potential for response errors to survey questionnaires. Critics argue that asking people whether they own a firearm, what kind it is, and how it is used may lead to invalid responses because ownership is a controversial matter for one or more reasons: some people may own a firearm illegally, some may own it legally but worry that they may use it illegally, and some may react to the intense public controversy about firearm ownership by becoming less (or even more) likely to admit to ownership (Blackman, 2003).⁷

⁷ While in most surveys respondents are provided confidentiality, the concern is still expressed that violations of confidentiality directly or through data mining could lead to the identification of specific respondents in a way that might allow the identification of firearms owners.

[17] Book: Armed: New Perspectives on Gun Control. By Gary Kleck & Don B. Kates. Prometheus Books, 2001. Chapter 2: "Guns and Public Health: Epidemic of Violence or Pandemic of Propaganda?" By Don B. Kates. Page 82:

To reiterate, NEJM-1993's conclusions depend entirely on there having been no substantial underestimation of the control group's gun ownership. It would take only 35 of the 388 controls falsely denying gun possession to make the control ownership percentage exactly equal to that of the homicide case households. If indeed the controls actually had gun ownership equal to that of the homicide case households (45.4%), then a false denial rate of only 20.1 percent among the gun-owning controls would produce the 35 false denials and thereby equalize ownership. Such a 20.1 false denial rate is smaller than either of the "refused consent for interview" category of the pilot study, or the "inaccurate registration data" category. Therefore the results of the pilot study are consistent with a false denial rate sufficiently high to bring the control group gun ownership rate up to a level equal to, or even higher than, the homicide case household rate, although the authors cite the pilot study to the reverse effect. Neglect of the false denial rate can produce a bias large enough, by itself, to account for the entire association between gun ownership and homicide claimed in this study.

[18] Paper: "Gun Ownership as a Risk Factor for Homicide in the Home." By Arthur L. Kellermann and others. New England Journal of Medicine, October 7, 1993. http://content.nejm.org/cgi/content/full/329/15/1084

"Multivariate analyses used conditional logistic regression, the appropriate technique for a matched-pairs design¹⁴."

NOTE: The raw data is found in Table 3: "Univariate Analysis of Hypothesized Risk on Protection."

© 2010 Just Facts

Information provided by Just Facts is NOT legal advice, and readers should consult with lawyers for legal guidance.