How To Lie And Mislead With Rape Statistics: Part 2

In Part 1 we talked about the reasons the authors felt some of the existing research was not credible.  They wrapped up their critique of the Kanin study with the following quote (and if you read Part 1, you can probably guess who they are going to cite):

As a result of these and other serious problems with the “research,” Kanin’s (1994) article can be considered “a provocative opinion piece, but it is not a scientific study of the issue of false reporting of rape. It certainly should never be used to assert a scientific foundation for the frequency of false allegations” (Lisak, 2007, p. 1).

In contrast, when more methodologically rigorous research has been conducted, estimates for the percentage of false reports begin to converge around 2-8%.

Before I get into the primary study that they reference, let me give you an idea of just what kind of games they have in store for us.  Here is what they say about the second study used to back up their 2-8% range:

For example, Clark and Lewis (1977) examined case files for all 116 rapes investigated by the Toronto Metropolitan Police Department in 1970. As a result, they concluded that seven cases (6%) involved false reports made by victims.

Ok, so we are back to using data from a single police department, in a single year, and in this case from about 40 years prior to when the article was written, but at least it is in the range they are claiming. They then go on to say this

Read more

How To Lie And Mislead With Rape Statistics: Part 1

As it turns out, only 7.8% of rape reports are true.

I know that may seem hard to believe, but I didn’t just make it up.  Technically, it is completely true.  It is also completely horse shit.  It is so misleading and built upon so many undisclosed caveats, that most people would consider it as good as lying if they knew how it was actually derived. The thing is, that “only 2-8% of rape allegations turn out to be false” figure you may have heard?  Not only is it just as misleading (if not more), it actually comes from the exact same data set.

So where did the 2-8% number come from?  If you read about it in Zerlina Maxwell’s piece in the Washington post you might be reasonably confused that the range is from the FBI

In fact (despite various popular myths), the FBI reports that only 2-8 percent of rape allegations turn out to be false, a number that is smaller than the number (10 percent) who lie about car theft.

Maxwell linked to a 2009 paper that hypothesized the 2-8% range, but has nothing to do with FBI statistics or car thefts. However, there is an earlier version of the 2009 article that was published in 2007 with the same name that included this bit of data:

For example, the Portland, Oregon police department examined 431 complaints of completed or attempted sexual assaults in 1990, and found that 1.6%1 were determined to be false. This was in comparison with a rate of 2.6% for false reports of stolen vehicles (Oregon Attorney General’s Office, 2006).

This is from a single police department, in a single year, and is not an FBI statistic.  As it so happens, there is a relevant statistics from the FBI, but instead of 1.6%, it is 8%, which would mean it wouldn’t fit her point about stolen vehicles. On the other hand,  there is also a separate statistic2 that says about 10% of stolen vehicle reports are false.  OK, so now we have a source for the 2-8% range, an FBI estimate that is in that range, and another statistic that shows a higher percentage of car thefts.  So while she is confusing her sources a little bit and that makes what she is saying somewhat misleading, overall her point is accurate, right?

Read more

  1. This stat was from version 2 of the Oregon SART handbook.  When they updated this stat 12 years later in 2002, as described in version 3, they found it had nearly doubled to 3%
  2. Mentioned at the bottom of page 5 here, though original source is unknown