Please create an account to participate in the Slashdot moderation system


Forgot your password?
The Courts Crime Math

How Statistics Can Foul the Meaning of DNA Evidence 215

azoblue writes with a piece in New Scientist that might make you rethink the concept of "statistical certainty." As the article puts it, "even when analysts agree that someone could be a match for a piece of DNA evidence, the statistical weight assigned to that match can vary enormously, even by orders of magnitude." Azoblue writes: "For instance, in one man's trial the DNA evidence statistic ranged from 1/95,000 to 1/13, depending on the different weighing methods used by the defense and the prosecution."
This discussion has been archived. No new comments can be posted.

How Statistics Can Foul the Meaning of DNA Evidence

Comments Filter:
  • Numbers don't lie. (Score:3, Insightful)

    by Beelzebud ( 1361137 ) on Thursday August 19, 2010 @04:58PM (#33307254)
    But liars love to use numbers!
  • Re:Hmm... Good (Score:2, Insightful)

    by Anonymous Coward on Thursday August 19, 2010 @04:58PM (#33307258)

    Your post sounds like a good reason for you to shut the hell up.

  • Whaa? (Score:5, Insightful)

    by esocid ( 946821 ) on Thursday August 19, 2010 @05:00PM (#33307282) Journal

    In the Smith case, the sample containing another person's DNA showed alleles at seven out of a possible 15 loci, but at four of these loci, the alleles matched those of both the victim and the defendant. "The 1 in 95,000 figure in effect treated these alleles as full-weight evidence that the DNA came from the victim, ignoring the alternative possibility that the allele we saw could have been from the defendant," says Balding. If the opposite position is taken, and these alleles are ignored, you come up with a figure closer to 1 in 13. "It's a question of which loci you consider," he says.

    Since when in the hell do you count common matches as proof that it comes from one person? Some of these labs are doing something very wrong, and I hate to think of both the false positives, and negatives, that came from their "expert" opinions.

  • by finarfinjge ( 612748 ) on Thursday August 19, 2010 @05:06PM (#33307348)
    The trouble that this paper and many others illustrate is the HUGE ignorance of proper statistical methods in the scientific community. Such things like a students T test are - statistically speaking - simple. Yet they are often beyond many in the science community. Thus, there is a tendency for misuse of technique, which in turn leads to divergent interpretations of what a data set means. The legal profession is even worse, as they don't care about the laws of mathematics. In a court, you are not required to answer to a professor of mathematics, hence you can assert anything. If your opponent doesn't have the necessary skill or knowledge to call BS on what you say, you can win an argument with a completely baseless assertion. Take an example. A man is fired for missing work on a Monday. The company's lawyer states "Fully 40% of this employee's absenteeism occurs on Mondays and Fridays. It is appalling that this weekend extending behaviour continues, and we must do something about it". The mathematically challenged lawyer for the poor sap can't see the issue with this and lets it stand.

    JE (always wanted to use that example. May have the justification a bit!)
  • Re:1/13 (Score:4, Insightful)

    by JW CS ( 1593833 ) on Thursday August 19, 2010 @05:07PM (#33307360)
    Sadly, your average American juror might find that logic compelling.
  • by clone53421 ( 1310749 ) on Thursday August 19, 2010 @05:08PM (#33307380) Journal

    Why don’t you just suggest that anyone who’s arrested is “statistically” guilty and we should just skip the trial...

  • Re:Hmm... Good (Score:5, Insightful)

    by Lunix Nutcase ( 1092239 ) on Thursday August 19, 2010 @05:14PM (#33307460)

    it shouldn't be used to free someone who was justly convicted with other evidence.

    And you know that the other evidence wasn't faulty, how? Police make mistakes, witnesses lie or remember things wrong, etc etc.

    You either believe your justice system is fair or else you scrap the entire thing.

    Or you ditch that false dichotomy and realize that within every system mistakes will be made. There is nothing in fixing past errors that means you throw out the whole system.

    Your alternative would mean that we would have to release every murderer and rapist.

    No, actually it wouldn't.

  • by Kitten Killer ( 766858 ) on Thursday August 19, 2010 @05:19PM (#33307522)

    You can prove anything with statistics.

    No. You can prove anything with BAD statistics. Unfortunately, most statistics are bad.

    -Scientist Statistician (enough to know that I don't know statistics)

  • by burtosis ( 1124179 ) on Thursday August 19, 2010 @05:23PM (#33307570)
    This should only suprise people who think court cases are about facts and justice. It is well known that facts just get in the way of what's true and real.
  • by Anonymous Coward on Thursday August 19, 2010 @05:32PM (#33307682)

    I'm a phd student in physics, and I am very grateful that my advisor insists on doing statistics from first principles, i.e. understanding everything from the principle of maximum likelihood. There are lots of subtle statistical errors you can make if you don't completely understand what you're doing.

  • by sjames ( 1099 ) on Thursday August 19, 2010 @05:36PM (#33307730) Homepage Journal

    Simply, DNA evidence is by nature exclusionary. The scientifically correct result of a DNA test is excluded or not-excluded.

  • Idiots like you are a perfect example of what happens to people after years of living under administrations (past and current) which have been and are, hell-bent on destroying civil liberties and due process. The remaining people who fail to fall in line will simply be arrested, and that will take care of any questions.
  • Re:Whaa? (Score:4, Insightful)

    by sjames ( 1099 ) on Thursday August 19, 2010 @05:49PM (#33307878) Homepage Journal

    Since when you're a prosecutor that doesn't really care if the defendant is guilty or not as long as he gets locked up and you get credit.

    The way the "justice system" currently works, if crime magically stopped right now, prosecutions and convictions would continue unabated.

  • by terrymr ( 316118 ) <terrymr&gmail,com> on Thursday August 19, 2010 @05:58PM (#33307974)

    DNA testing probabilities go something like this ....
    we found say 5 markers that match the defendant and the sample. (I picked a small number to make the example shorter)
    each of those has the following probabilities of occuring in a random person :

    1) 1 in 1000
    2) 1 in 10
    3) 1 in 10000
    4) 1 in 7
    5) 1 in 100

    so we multiply all those together and get a probability of mismatch of : 1 in 7,000,000,000

    I even told a guy at the state crimelab that was stupid - not that he cared.

  • by winwar ( 114053 ) on Thursday August 19, 2010 @06:17PM (#33308162)

    "Of course, I'm sure the fact that we end up paying people who get imprisoned because the government fucks up had no bearing at all on the government's desire to convince everyone they didn't fuck up."

    Actually, probably not. The DA may just not want to admit they made a mistake. It's uncomfortable to process those facts so the DA doesn't. They probably even believe that the person is guilty. Cognitive dissonance and the like is pretty powerful.

  • by fermion ( 181285 ) on Thursday August 19, 2010 @06:20PM (#33308200) Homepage Journal
    Lack of match of DNA found at a crime scene, like a fingerprint, provides reasonable doubt, so that suspect tends to go free. Note that it does not certainty of innocence, merely reasonable doubt. Since, in the US, we are required to prove beyond a reasonable doubt, it is often sufficient to kill a case.

    DNA, like a fingerprint, should not be enough to convict. Many articles have been written on the faulty statistics that are used by prosecutors to posit faulty odds like 1 in a million, when in fact the odds are more like there are many possible people who could have done this, and we have randomly chosen one. The job is then to prove that this is not just a random choice from a database, but, based on other evidence, this is person who actually committed the crime.

    This is going to become more of an issue as we get more DNA in databases and solve crimes by matching DNA to the database. In this case, the match will be a random choice between several people, and it will be a mistake to convict based primarily on DNA evidence.

  • by HungryHobo ( 1314109 ) on Thursday August 19, 2010 @06:25PM (#33308246)

    If the only thing that pointed you at him was that search of the database then it tells you almost nothing about how likely he is to be guilty on it's own.

    If you find a suspect be searching through a database of a million people with a test that has a 1 in a million chance of making a false positive and no other evidence exists then the chances of that match should not be used in any way to establish guilt in court.
    But then lawyers don't care about using stats correctly.

    If however you find someone, they have a knife with the victims blood on it and they have a motive and you compare their DNA to the DNA found at the scene then that same test with a 1 in a million chance of a false positive is a perfectly valid piece of data to submit in court.

  • DAs are rewarded for getting guilty verdicts and sending people to prison, not for finding the guilty party and punishing them. There's a very subtle difference there, and it means that a DA with so-so evidence against a defendant who's easily portrayed as scum (with a PD for a lawyer) versus rock-solid evidence against an upstanding citizen (who can afford their own attorney) will prosecute the former over the latter. It's an easy win, who cares if the guy is really guilty?

  • by mangu ( 126918 ) on Thursday August 19, 2010 @06:58PM (#33308542)

    Why dont you just suggest that anyone whos arrested is statistically guilty and we should just skip the trial...

    That's being done routinely all over the world today.

    People who drink are statistically more likely to commit traffic accidents, so they are convicted without the need to actually do any harm to anyone.

  • by mhajicek ( 1582795 ) on Thursday August 19, 2010 @07:24PM (#33308736)
    That of course assumes that there can be no correlation between markers.
  • by Anonymous Coward on Thursday August 19, 2010 @08:13PM (#33309116)

    that would be true if cops took their jobs seriously in objective manners.. they statistically do not. the kind of person that gravitates to law enforcement is one with deep seated insecurities and thus the desire to make others conform to his expectations. it's no wonder that fallacies like appeal to authority and appeal to popularity are among cops' favorite justifications.

  • by TheEyes ( 1686556 ) on Thursday August 19, 2010 @08:36PM (#33309298)

    But neither can you retry every case infinitely because there are some remaining doubts. There will always be doubts.

    You can and you should retry cases if there are doubts; you should acquit immediately if there are any reasonable doubts.

    The rule of law in this country is founded on the idea that people are innocent until proven guilty, beyond a reasonable doubt. Not "pretty sure," not "it's too much trouble to give you a fair trial, so we'll just convict you anyway." Beyond a reasonable doubt. That standard of proof will inevitably mean that people who actually committed crimes will be let free, and some will indeed go on to commit more crimes, and that is unfortunate. This country, however, is supposed to be based on the love of freedom, and the notion that everyone deserves not to be railroaded by a kangaroo court bent on throwing as many people as they can into a life of permanent second-class citizenship (convicted criminals have few rights in this country, and remain persecuted even long after they've "paid their debt to society.") You can't have that if you are willing to sacrifice freedom for temporary, largely illusory, safety.

  • by Anonymous Coward on Friday August 20, 2010 @09:18AM (#33312728)

    Why is this rant rated insightful?
    It's just an opinion. No less no more, and it gives no facts and / or examples.

    Just feeding the trolls


UNIX is many things to many people, but it's never been everything to anybody.