Racial profiling to limit terror attacks is fundamentally flawed: statistician

November 18, 2010, Wiley

Stop using racial profiling, says Professor William Press from the University of Texas at Austin. He claims that as well as being politically and ethically questionable, racial profiling does no better in helping law enforcement officials in their task of catching terrorists than standard uniform random sampling techniques. This is the topic of a paper publishing today in Significance, the magazine of the Royal Statistical Society and the American Statistical Association.

Racial profiling rests on the idea that people from particular racial or ethnic groups are more likely to be involved in acts of terror than people from other groups. The theory then suggests that law enforcement officers should spend a greater proportion of their time scrutinising people from the 'high risk' group. One problem with this approach is that innocent people who also belong to the targeted group rapidly become offended, and some may even become radicalised as a result.

"Racial profiling is as indiscriminate as deciding that people named Patrick are more likely to drink and drive, and so everyone who is named Patrick should be stopped and breathalysed more frequently than people with other names," says Press. Although it may be the case that some people named Patrick do drink and drive, he points out that there are clear problems in this profiling strategy. First, many Patricks don't drink and drive and will be unfairly detained. Secondly, this sort of profiling can have the appearance of success because if you keep testing more people named Patrick than other people, you are almost bound to find more Patricks who have drunk alcohol than people with other names. This then leads you to think the problem is even worse than you first suspected, and so you further increase the targeting of Patricks.

In the Significance paper Press, based in the departments of Computer Science and Integrative Biology at the University of Texas at Austin, takes a thorough mathematical and statistical view of the process that underlies racial profiling, and concludes that some forms of racial profiling may even result in a smaller chance of detaining a terrorist than carefully conducted standard sampling.

In a world threatened by terrorists from a small number of countries, it is tempting to think that racial profiling for security purposes, even if morally objectionable, might save lives. "But uniform sampling, without the use of profiling, is surprisingly good. It is robust against false assumptions, it is deterrent, it is easy to implement, it is about as effective as any real-life system can be – and it is devoid of moral and political hazard," says Press.

He believes that the choice between a strategy of profiling and one of uniform random sampling should not be viewed as difficult; uniform random sampling wins.

Explore further: Researcher proposes statistical method to enhance airport secondary security screenings

Related Stories

Study finds that discrimination varies by gender and race

April 2, 2008

Men are more likely to tolerate discrimination than women, however both sexes tend to accept prejudice against poorly educated immigrants and Arab-American airplane travelers, according to a study by the USC-Caltech Center ...

Personal genetic profiling services lack evidence for claims

October 12, 2010

Direct-to-consumer personal genetic profiling services that claim to predict people's health risks by analysing their DNA are often inconclusive and companies that sell them should provide better information about the evidence ...

Border Patrol seeks text on suspicious activity

June 8, 2010

(AP) -- U.S. Border Patrol agents often use horses to look for smugglers in the forested mountains along the Canadian border, but now will be adding a more modern tool to help them keep watch - text messaging.

Recommended for you


Adjust slider to filter visible comments by rank

Display comments: newest first

1 / 5 (2) Nov 18, 2010
These scientists will have a hard time convincing any three-letter organisation to use race-blind sampling. And, as "Patricks" actually dominate the "DUI" lists, it will be even harder.

The authors also seem to ignore the fact that profiling is resource-intensive. If it weren't, then of course, the entire population would be profiled. The profilers have to start somewhere.

But I do admit, terrorists might in the future start recruiting WASPs so they stay under the radar.
3.4 / 5 (5) Nov 18, 2010
Racial profiling is as indiscriminate as deciding that people named Patrick are more likely to drink and drive, and so everyone who is named Patrick should be stopped and breathalysed more frequently than people with other names

Ugh, this is asinine on its face. So far, every islamic terrorist ever found--EVERY SINGLE ONE--has been a Muslim! So this guy is basing his argument on the straw man of racial profiling, when race is simply one of many shortcuts to segmenting a sample by RELIGION.

Or is that also bad? Is that it? Unless we strip-search Grandma, the terrorists win?

Drivel like this is what happens when you eliminate the profit motive and allow science to feed at the government trough.
3 / 5 (2) Nov 18, 2010
i don't like racial profiles, but the stakes are too high to get on our ethicaL western high horse, terrorists aren't bothered by any of that and kind of forces our ethics downwards otherwise we cannot engage them on a level playfield, this is a moral win for them, that we have give up many freedoms, have detectors everywhere etc to keep them at bay, so we might as well play a bit dirty ourselves to make their annoyance expensive.
3.7 / 5 (3) Nov 21, 2010
So if law enforcement is targeting terrorism, which is 95% likely to be caused by someone of arabic decent, they should be checking blue eyed blondes too? If someone is targeting illegal immigration from Ireland they should be checking hispanic looking individuals? There is nothing wrong with racial profiling, only the guilty and not so smart want it stopped.
3 / 5 (3) Nov 22, 2010
In addition to making absurd and counterfactual statements about what today's airline terror suspect looks like, Professor Perry is not an honest broker in this debate, as he is a major contributor to President Obama's 2008 campaign. FEC records available to the public show $2,300 from Mr. Press to Barack Obama in 2008. That isnt chump change.

Today must be the day when all Obama defenders crawl out of the weeds to state with stern appeals to academic authority that an 80-year old Swedish American grandmother travelling with her 10-year old grandaughter presents the exact same terrorism risk profile as a trio of 21 year old Yemenis or Pakistanis or Saudis or Somalis who bought one way tickets with cash and have no luggage.

Thus in my opinion no one with an ounce of common sense should listen to this man as he is obviously a water-carrier for Obama and the TSA.
1 / 5 (1) Nov 22, 2010
Right, profiling is useless. Women over the age of 75 and under the age of 7 are as likely to be involved in a terorrist plot as men between the age of 17 and 40.

Oh wait, no they aren't... not by a longshot. If you scan everyone, that's one thing. But making the "random" less random would increase the odds of getting a terrorist screened wouldn't it?

How does the math work so that it doesn't?

I guess statistics isn't something Prof. Press is good at; or he doesn't understand how to increase the odds of a hit when not dealing with a true random sample.

Math is hard, but I'd think 20 years teaching physics at Harvard would require him to be moderately capable.
5 / 5 (1) Nov 26, 2010
Will the terrorist that is planning an attack on president Obama right now look like Timothy McVeigh? Will he be a she? Will she be old? Or will he be disguised as an old woman?

I think the professor has a point.

not rated yet Dec 16, 2010
I would have liked to see the statistical reasoning behind the claims in this article:
We get some qualitative talking points and then... the comments by PhysOrgers, who obviously don't have the data this paper is based on.
Some of us (readers) would like the meat of the papers discussed in addition to the conclusions.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.