Worries about Inference: A Closer Look at the Family Research Council’s Report on Homosexual Assault in the Military

The Family Research Council has released a report on Homosexual Assault in the Military that is now getting picked up in the mainstream media. The central point of the report seems to be new data analysis that shows that 8.15% percent of sexual assaults in the military in Fiscal Year 2009 were of a same sex nature (p.6), the vast majority of which involved two men (see footnote 4). The report also cites data showing that 2.8% of men and 1.4% of women in the US general population identify themselves as gay, lesbian, or bisexual. On this basis, the report claims that “This suggests that homosexuals in the military are about three times more likely to commit sexual assaults than heterosexuals are” (see p.1).

This is a bold and provocative claim, and therefore ought to be subjected to serious statistical scrutiny. The first step would be to validate their coding of the 1643 reported sexual assaults. The cite this DOD report as their source; if anyone is interested in attempting to replicate their coding I would be happy to post the results here. However, for the moment, let’s just posit that the claim that that 134 of these assaults were indeed same-sex in nature is correct, and instead turn to the inference made by the authors of this report: that homosexuals serving in the army are three times more likely than heterosexuals to commit sexual assaults. What are some factors that could potentially confound this inference?

  1. First and most significantly, the study provides no evidence of the proportion of same-sex assaults that are committed by homosexuals. This is crucial to the study, because the authors want to leverage the information in the study to argue that homosexuals should not be allowed to serve in the military. But their data measure assaults by men against men or women against women, not the number of assaults by homosexuals. Thus without any understanding of the proportion of same sex assaults that are committed by homosexuals, the inference that homosexuals are more likely to commit sexual assault is invalid.
  2. Second, we don’t know if the proportion of homosexuals in the military matches the proportion in the general population. The authors of the study assume that the proportions are similar, but if homosexuals are overrepresented in the military relative to the general population, then the inference is invalid. Moreover, it is not even clear that the general population is the right reference group; the military is overwhelmingly made up of young men. So even if we think the demographic composition of the military reflects the general population – which it may very well not – we’d still want to know something like the prevalence of homosexuality among 18-30 year old males, not among the population as a whole.
  3. Moreover, even if we assume that the proportion of homosexuals in the military mirrors the proportion in the general population, the conclusions of the study are dependent on a low estimate of homosexuals in the general population (<8.15/3, or <2.7%). Other studies have found higher estimates.

There are other more detail oriented data-related questions to worry about, such as how the results would be affected if a single individual committed multiple assaults or how the authors of the study coded cases where the accused was not found guilty of misconduct (see for example USMC Case #61). But overall, any one of the three big concerns listed above should raise serious questions about the study’s conclusion that homosexuals serving in the army are three times more likely than heterosexuals to commit sexual assaults, taken together they ought to lead us to approach this claim with a very healthy degree of skepticism.

One other point I can’t help making – the report also provides a bunch of (fairly explicit) descriptions of same sex sexual assaults (not sure why these needed to be in the report?), and in one section goes on to point out that a Persian-Farsi linguist was accused of committing a same-sex sexual assault (see p.14). The heading of that section: Do we really need more homosexual linguists?. So while we’re on the subject of inference, I assume from this argument that the Tailhook Scandal would lead the Family Research Council to conclude that we no longer need more heterosexual Marine Corp aviation officers?

[Hat tip to Neal Beck and Dan Kselman.]

12 Responses to Worries about Inference: A Closer Look at the Family Research Council’s Report on Homosexual Assault in the Military

  1. Anon May 27, 2010 at 7:23 am #

    Funny, I was just talking to a student after class about this a few weeks ago. He is a Navy vet and we got to talking about DADT. He mentioned that it was not unheard of (and gave me specifics on one case) for someone to claim assault after being caught in what was actually a consensual homosexual act. The fact that DADT risks careers if the person is found out creates an incentive for false reporting of assaults, which may account for some of the FRC data.

  2. Jordan May 27, 2010 at 9:32 am #

    I, too, have questions about reporting. It is a well known fact that sexual assault is widely under-reported. If there is significant variation in under-reporting by gender then there could be a selection effect driving the difference. Such variation would generate a bias in the direction favoring the Family Research Council if women are more likely than men to under-report sexual assault. I imagine studies have examined this possibility. Of course, it would be better to know the likelihood of reporting sexual-assault for victims and perpetrators of both genders. I’m not so confident these numbers exist. In short, there are many reasons to not trust the Family Research Council’s inference without more details about their methodology.

  3. jonp72 May 27, 2010 at 3:40 pm #

    A case can be made that DADT makes same-sex assault more likely, not less so. If you make both consensual and non-consensual homosexuality can get you booted from the service, that’s not exactly putting a high priority on ending sexual assault.

  4. Lymis May 27, 2010 at 5:29 pm #

    Also consider that there is a lot of anecdotal evidence that women who report sexual assaults are often either ignored or face negative social and career consequences and further harassment.

    On the other hand, men reporting an assault would be supported, and it’s pretty solid that an actual perpetrator will be discharged.

    This also assumes that “sexual assault” is roughly equivalent between same-sex and opposite-sex encounters. I’d be interested in seeing if that’s true or if male on male sexual assault includes a lot of “inappropriate touching” or “unwanted advances” where male on female assaults would ignore those and only report actual rapes. If the nature of the crime isn’t equivalent, the data is meaningless in this context.

  5. Michael May 27, 2010 at 6:49 pm #

    The point no one seems to be making is that there is, of course, much, much, much more opportunity for same-sex assaults to occur. How much more time do men spend with other men in the military than they do with women? Of course there are going to be more same-sex assaults.

  6. Jon May 27, 2010 at 8:18 pm #

    The case law on same-sex sexual harrassment in the civilian population makes clear that most such harrassment is perpetrated by self-identified heterosexuals who target men they perceive as weak or effeminate. There’s no reason to believe circumstances would be different in the military.

  7. rob May 27, 2010 at 9:32 pm #

    Does the Family Research Council believe that prison rape is committed by homosexuals?

  8. TJ Parker May 28, 2010 at 8:58 am #

    Absolutely correct. Those in the military do not comprise a random sample of the population. If there are three times as many reported same-sex assaults in the military than in the general population, then its equally plausible to conclude that the gay population in the military is three times larger than the population as a whole. The inference itself exposes their bias and invalidates the research.

  9. Kyle Dirck May 29, 2010 at 1:21 pm #

    I believe that they would, yes. Remember, such social conservatives reject homosexuality as a sexual orientation. To them, homosexuality is the act of engaging (voluntarily?) in same-sex relations. Thus, a prison rapist is, ipso facto, a homosexual.

  10. Cliff Mather June 1, 2010 at 1:05 pm #

    I think some of the suggestions made by this post are dubious.

    Homosexual persons are perhaps overrepresented in the military relative to the general population? How can this be with DADT in place?

    The report underreports homosexual persons in the general population? It cites an amicus brief from a coalition of homosexual rights groups (go see for yourself). Why would they underreport the numbers? The counterclaim above cites a wiki page that lists a number of different studies. We don’t have the space to treat all of them here in detail, but the majority give similar numbers, and the rest arguably over-relax the requirements (“Have you ever had a same-sex experience in your lifetime?”)

    I think the numbers can be challenged on other grounds — e.g., the military is made up of males self-selected for aggressiveness, which might produce a higher percentage than the general population.

    One final point in response to the previous comments: whatever standard we apply to delineate prison rapists from homosexual persons we ought to be willing to apply equally to “heterosexual” rapists. At some point, a person is simultaneously both a sexual being and evil.

  11. Norman Rogers June 2, 2010 at 7:17 am #

    I think the numbers can be challenged on other grounds — e.g., the military is made up of males self-selected for aggressiveness, which might produce a higher percentage than the general population.

    Wait a minute–society is made up of males who are self-selected for their aggressiveness, and we call that Darwinism.

    If the military is made up of males who join for a vast number of reasons and go into over a hundred different job specialties which are differentiated across different disciplines, such as medical, infantry, signal and a slew of others, and is loosely divided between combat arms and combat support, then you get a fairly diverse number of males from American society. The Army is not a mindless bunch of infantrymen; infantrymen are actually rare in the Army since there are so many other support roles.

    They’re not “self-selected” for their aggressiveness. They join because that’s the job they want or because that’s the only job available. Economic conditions drive men and women into military service, and many are just trying to find jobs that they are qualified to do.

  12. Steve June 3, 2010 at 1:47 am #

    Lymis discusses the conflating factor of heterosexual men who have an impulse to sexually harass a woman but can’t because none are around. This isn’t actually a *conflating factor*, it’s an *explanation*. If indeed homosexuals commit more sexual assaults (a big if), then this probably is why: They have far more temptation and opportunity. This makes sense, and it’s why I wouldn’t be shocked if a more careful data analysis found the same result as FRC’s.

    Incidentally, the FRC report itself brings up the “more opportunity” factor as a possible explanation. (Although it clearly favors the competing hypothesis that homosexuals are awful people!)