Slashdot Mirror
How Statistics Can Foul the Meaning of DNA Evidence
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."
Isn't it the case that we are more often in the way of our own discovery and explana-tative power
You can prove anything with statistics.
Also 99.9% of all statistics are made up.
"You want to know how to help your kids? Leave them the fuck alone." -George Carlin
"Members of the jury, there's only a 1 in 13 chance that the defendant is actually the killer based on the DNA evidence. If the defendant were sitting in the jury with you, then there's an equal chance that it was any one of you. And since we can eliminate all 12 of you, that leaves only the defendant left over. So you must find the defendant guilty of all charges since he's the only one left out of 13 people. The prosecution rests."
Want to improve your Karma? Instead of "Post Anonymously", try the "Post Humously" option.
But liars love to use numbers!
Your post sounds like a good reason for you to shut the hell up.
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.
Absolute power corrupts absolutely. indymedia
I see you have an excellent grasp of traditional literary technique. By addressing a non-present audience (in this case, the lip-readers), you have created a subtle interplay between apostrophizing and apostrophes.
And add to the fact if you have served on a jury before, many times this information is highly technical and is very easily miss-represented by the lawyers to jury members from all walks of life.
Why don’t you just suggest that anyone who’s arrested is “statistically” guilty and we should just skip the trial...
Alexander Peter Kristopeit bought his basement from his mommy for one dollar.
just use the glove and If the glove doesn't fit, you must acquit!
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.
It seems to me that the simple defense to such a charge would be to go get the person who recently sucked the defendant's dick, test that person's DNA, and compare it to the other DNA samples. Presumably, however, even a bad lawyer would have thought of this, so I must not really understand the case.
Three cheers, for sure, for an opportunity to topically discuss fellatio on Slashdot.
Genetics means "out of your control" and touches on some raw nerve issues, so there's a lot of throwing around of "statistical" information and unrealistic mental models.
For example of statistical confusion:
New research shows that at least 10 percent of genes in the human population can vary in the number of copies of DNA sequences they contain--a finding that alters current thinking that the DNA of any two humans is 99.9 percent similar in content and identity.
http://www.hhmi.org/news/scherer20061123.html
And broken mental models:
http://en.wikipedia.org/wiki/Lewontin's_Fallacy
Until our knowledge improves, you're going to see more "politicization" of DNA-related science.
Futurist Traditionalism
uncertainty.
Each time the answer comes up the same, even in a test with much less accuracy, you improve the chances it's the right answer.
Throw some statistical analysis at it and come up with a way to combine the tests you have into one probability, which will be higher than all the probabilities you got from the measurements.
Unless the tests disagree, and then you're talking a homework problem.
I speak from personal experience. I use them al the time and still don't really understand them. Not how they apply in criminal investigations anyway.
Let's say you have evidence that matches 1 in a thousand people. You search through your database of all 1000 suspects and you get a single match. Did he do it? Logically you'd expect this to mean you can be 99.9% sure. You then search through the database of a million random people. You get 1000 matches. Does this mean there's only a 0.1% chance that your original suspect was guilty? Well, maybe there's some other compelling evidence that makes it most likely that one of those 1000 people were the culprits. But you have 10000 outliers. They're each a tenth as likely to have committed the crime. You get 10 matches. So, once again we're at the 50% probability of guilt, or something in that ballpark.
I'm sure this is a somewhat different example than that given in the article but that's not the point. The point is that is there a 99.9% probability, a 0.1% probability, a 50% probability or some other probability of guilt? Or am I just trying to confuse you by throwing numbers at you?
Ladies and gentlemen of this supposed jury...
This... is Chewbacca.
Ice Cream has no bones.
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.
This sounds like a good reason to stop releasing all of those convicted murderers and rapists who were freed on DNA evidence.
Not at all.
There is no problem determining that the DNA is from somebody else than the accused. All it takes is a single marker that's different. That's easy.
The problem is going from some bunch of markers that match to saying "This IS the bum! (Well, except for a one-in-[some number] chance it really isn't.) That requires a lot of information about prevalence of genetic markers, whether there is a correlation between their distribution. That information isn't well researched and the different estimates are based on different wild guesses by different experts. Further, the whole independent-probability thing gets knocked into a cocked hat with FAR lower numbers if the police found the accused by searching a DNA database for matches. And what if he had an evil identical twin? Or somebody with access to PCR gene-amplification materials, a DNA sample, and an atomizer decided to frame him?
IMHO DNA evidence is decisive for the defense. But pending a lot more research it's still voodoo for the prosecution.
Bantam Dominique roosters crow a four-note song. Once you've heard it as "Happy BIRTHday" you can't NOT hear it that way
I would imagine the lip readers you're addressing are too interested in the sex to pay attention to your letters.
"When you have eliminated the unacceptable, whatever is left, however improbable, must be the truthiness" - Holmes
When expert A says he's certain of a match to "1 in a billion" he's really saying he's certain to 0.999999999. When expert A says he's certain to 1 in a million that's certain to 0.999999.
Compare this to the "not so far apart" difference between expert A saying "he's 1 in 10" and expert B saying "he's 1 in 5." The difference between 0.9 and 0.8 certainty is a lot greater than the difference in certainty in the first example.
By the way, if I'm on a jury, I'm interested in "who else could've done it" not raw numbers. If two people leave the crime scene and blood is a "certain to 1 in 5" match to the defendant, that is, there's a 20% chance of a mistake, and the only other person who was at the crime scene has been ruled out, the only way I'll acquit is if the defendant either makes a very very strong case he didn't do it or provides some explanation for the evidence that doesn't require either of the initial suspects to be guilty.
In more practical terms, if you can raise the odds of certainty high enough that it's implausible that two people within 100 miles of the crime scene at the time of the crime are a match, and you make a very strong claim that the DNA sample is a result of the criminal being there at the time of the crime, the defense is going to have to work very hard to get me to acquit.
Knowledge is how to play a game, intelligence is how to win, wisdom is knowing what game to play.
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.
What changed under Obama? Nothing Good
In this case, however, there were many people present at the discovery of the object from which the DNA was taken for analysis. As it happens, several of these people were relatives (brother, mother) of the person the prosecution were trying to persuade us was the person that possessed (in legal terms) the object.
The question that I kept hoping the defense attorney would ask was "what are the probabilities of an erroneous match if the people are relatives, not just two random people off the street"? Unfortunately, he didn't.
As it happened, there were so many other peculiarities in this case as well as some pretty bizarre testimony from prosecution witnesses that we voted to acquit without making much of the DNA evidence.
udin
In reality it needs to be at no more than 1/18 to be sure, 1 defendant, 12 jury, 2 lawyers(minimum if not defending yourself), 1 judge, 1 bailiff, 1 of those people who records everything said, and usually some spectators. At 1/13 there must be at least a co-conspiritor in the room!
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.
"She's a scientist and a lesbian. She's not going to let it slide." Orphan Black
I'm being purely hypothetical, but let's work out a word problem.
So let's assume that there's some DNA in question, and that dna according to all 10 other calculations (assumed accurate) has a unique match number of 1 in 100,000.
Nobody ever asked if the defendant has a twin. (Again, assuming that an identical twin would have matching DNA which I don't actually know for certain).
Let's assume for simple math that in the real world twins occur 1/100 times.
Is the statistical uniqueness now 1/1000, 1/2, 1/50,000, or 1/100,000 or some other number.
60% of the time, it works every time.
No single raindrop believes it is to blame for the flood.
... in a case I was on the jury for. (Sorry for the bait-and-switch title, couldn't resist.)
This was a case of armed home invasion. The victim was a big bruiser of a man, a multiple convicted drug addict. The defendant was a scrawny young Cape Verdean guy. (Cape Verdean drug gangs are common in the area: this is important later.) The victim testified that, after buying drugs from the defendant, he got a series of enraged voicemails demanding the return of the defendant's cell phone. A few hours later, the defendant allegedly shows up at the victim's house with a gun and barges in yelling. A struggle ensued, a shot was fired into the floor, and the guy with the gun fled.
Evidence against the defendant included eyewitness testimony from the defendant, matching ammunition found at the defendant's house, and crucially a do-rag found at the scene of the scuffle. DNA tests matched the do-rag to a mixture of at least 3 people, including the defendant. The DNA mixing was probably due to really awful police work: a paper bag borrowed from the defendant's cupboard is not a proper evidence collection container.
As in TFA, mixed DNA dramatically affected the "probability of exclusion" statistics: the state's expert testified there was a 1 in 50 chance that a random man on the street would match the DNA on the do-rag. The odds that a random *black* man on the street would match were much higher, like 1 in 20; the defense pointed out that the odds that a random *Cape Verdean* would match would be much higher.
We've grown used DNA evidence saying things like, "not one other person on the planet could match this DNA", but in this case, the odds were good that the DNA evidence would match at least one other person sitting in the *courtroom*. The defense also took the unusual tactic of introducing the defendant's sister, who testified that her *other* brother looks very much like the defendant, and she said it was *his* voice on the enraged voicemails. What are the odds that the DNA matches the *brother* instead? Damned good.
Between the fact that the eye witness seemed shifty and unreliable and was probably on crack at the time of the incident, and the fact that all the physical evidence could just as well implicate the brother as the defendant, we couldn't rule out the possibility that the cops got the wrong guy, so we found him not guilty. If I had to take a bet, I'd say he did it, but I wouldn't bet his life on it.
Anyway. Moral of the story is: on cop shows and in the public awareness, DNA evidence is rock solid and incontrovertible. But in the real world, the statistics of DNA mixtures make things a whole lot less cut-and-dried.
DNA evidence is a far more useful tool for defense than prosecution. Showing that a DNA sample really came from a certain person is difficult, and can never be 100% accurate. But showing it didn't come from someone is easy. If it obviously doesn't match, that's that. There's no question at all in how to interpret it.
"I'm too busy to research this and form an educated opinion, but I do have time to tell everyone my uninformed opinion."
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.
And you know that the other evidence wasn't faulty, how? Police make mistakes, witnesses lie or remember things wrong, etc etc.
You can't be certain of anything.
But neither can you retry every case infinitely because there are some remaining doubts. There will always be doubts.
The appeals court is a court of law.
It's only job is to decide as a matter of law whether a conviction should stand.
You raise your objections to matters of fact or opinion in pre-trial proceedings. You raise them again at trial. But you must get your objections on record before your case goes to appeal.
It is a lot to ask an appellate judge to believe that matters which seemed inconsequential to you then should be given any weight now.
That's why medical science is progressing so slowly and unpredictably.
On average anyway.
Now, if you somehow manage to get semen some place you never were
It means you should have washed your keyboard before disposing of it. Or more realistically, you should have incinerated your used condoms rather than throwing them in the trash. Great place to get false evidence.
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.
You can prove anything with statistics.
Also 99.9% of all statistics are made up.
Tongue-in-cheek aside, the real problem with statistics is that it only deals in probabilities. As such, It can never describe something conclusive. It can only tell you something is probable. (or very, very probable) It can never identify an answer/solution/event as certain. Thus, it can never tell you the absolute truth. It can only give you the most probable occurrence.
Therefore, somewhere in the evaluation of court evidence, one must decide what probability constitutes "beyond a reasonable doubt". That's a very fuzzy line, and should be drawn by the jurors, nobody else. Additionally, if I were ever on a jury, I'd want to know exactly how those numbers were reached.
From the article:
"There are some labs that are just reporting that they think it's a match- in their opinion," says Butler. "That's a problem, because the jury says: 'Oh, it's DNA? It matches? Guilty.'"
I won't join Slashcott. OTOH, If Beta goes live, I just won't be back until it's fixed. Sorry Dice.
The right way to use DNA is this. First, you find some suspects using traditional methods. When you have a set of suspects, you then do a DNA test against DNA from the crime scene that is known not to be from the victims or witnesses. It likely only matches one of your suspects. That's very likely the criminal.
The wrong way to use DNA is this. First, you find some DNA at the crime scene that doesn't belong to anyone there who is known not to be the criminal (e.g., it doesn't belong to the victims or witnesses). Then you check that DNA against some database of DNA samples. One match is spit out. You arrest that guy and try to convict him solely on the DNA match, telling jurors the odds of a match are 1 in some-large-number.
The problem with the second approach is that they don't test the whole sequence. They just test part of it--not enough to uniquely identify a single person. There may be a dozen people who match the criminal's DNA, depending on the test they use. If only one of those people happens to have done something to get himself into a DNA database that is available to law enforcement, he's screwed if any of the others who match decide to commit a crime.
The first approach (pick the suspects first, then use DNA to single out one) does not suffer from that problem.
Hey, it's Slashdot. Somebody had to notice.
Contrary to what the average lay-person imagines about DNA testing, it does not involve actually matching all of the DNA present or even most of it. Only a small bit of a person's entire genome is used. And then only statistically in comparison to some presumed statistical population reference.
To put it in other terms, DNA testing is like identifying Dickens as the author of a suspect text by comparing the first word of each chapter to a reference that is the average first words of chapters of some, but not even most, of his known works which is combined with some other unknown and undetermined books written by other authors.
Once you understand this, you quickly realize the margin for error is far bigger than typically presumed.
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. http://www.worldpixelmile.com/
Unnecessary hyperbole. One drink isn’t drunk, not the drunk who’s going to rear-end someone because he’s too pissed to drive anyway.
You’re just as bad as MADD: Drunk drivers are committing premeditated attempted murder; one drink is drunk; the legal limit should be anything above 0.000. Yeah... gimme a break. There’s a law of diminishing returns, and besides, it’s completely hypocritical if you don’t also revoke the license of just about everyone over the age of 55 since a twenty-something has better reflexes after 1 drink than they have completely sober and with 10 hours of sleep.
Alexander Peter Kristopeit bought his basement from his mommy for one dollar.
Unlike Dick Cheney, I haven’t shot anyone. Besides, I have this strange belief that people should be punished for things they actually do, not for things that potentially could have happened due to risky behaviour.
Alexander Peter Kristopeit bought his basement from his mommy for one dollar.
Whether it's 1 in 95,000 or 1 in 13, reasonable doubt exists.
1 in 95,000 is still 3,157 possible people just in the US.
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
H
Circumventing due process and putting it entirely at the discretion of the LEO? Sounds like a great idea!
I’m sure that no police officer would ever abuse that system...
Alexander Peter Kristopeit bought his basement from his mommy for one dollar.
I guess that wanking onto cars from pedestrian bridges over motorways isn't such a cool idea after all.
To have a right to do a thing is not at all the same as to be right in doing it
That holds as long as you have the capability to make reparations for the consequences for your actions.
When you no longer have that capability, you should no longer have the right to take those risks.
Get back to me when you can bring someone back from the dead, then I'll agree that you should be able to drink/drive and fire your gun randomly.
Is 1563649 a prime number?
A red light traffic cam snaps a photo of a vehicle of the same make, model, and approximate year as a vehicle that you own. The license plates are dirty and only the last digit is legible. Based on the description of the vehicle and the matching numbers from the plate, they send you the ticket. Statistically speaking, there are many other vehicles that would match the description of your car, and probably 20 with the same last digit in their license plate number. So there’s really only a 1:20 chance that it was your car, but since you aren’t given any real chance to defend yourself against the charge, you have to pay the ticket.
Alexander Peter Kristopeit bought his basement from his mommy for one dollar.
That’s funny, because I do have the right to drink and drive* and fire my gun randomly**. GFY.
*as long as I’m not over the arbitrarily-set BAC limit of 0.08 when I drive, at which point I abruptly become fall-down drunk and incompetent to operate a motor vehicle without certainly killing someone (or so the false dichotomy claims)
**in desolate areas and on private property, aimed sensibly enough so that the shot’s trajectory will not leave the property
Alexander Peter Kristopeit bought his basement from his mommy for one dollar.
I said that I'd agree with your right. I know full well that you have those rights.
Is 1563649 a prime number?
I don’t drive drunk (I have in the past, I admit; but as I know it is more dangerous and don’t much care for the consequences anyway, I don’t), but I also see things realistically, and realistically a BAC of 0.08 isn’t what I consider significant in terms of being more dangerous than normal. Certainly less dangerous than eating or texting while driving.
Driving is dangerous. Period. By your rationale, nobody should drive, ever. You are, after all, still probably about 20% as likely to get in an accident compared to if you had a BAC of 0.08. (And compared to 0.05, it’s probably closer to 40% as likely.) You are playing Russian roulette with your life and other people’s lives every time you get behind the wheel. SleazyRidr indeed... how do you live with yourself? (Or, you can look at things realistically as I do and realise that the chance of getting in an accident is basically negligible, and still pretty much negligible after having 1 drink.)
In the meantime (regardless of whether it’s practical to catch them) distracted drivers pretty much get a free pass; there’s nowhere near the same amount of social stigma against texting while you drive as there is against driving after having a couple of drinks. And if you did catch someone driving while dangerously distracted, they still wouldn’t get anywhere even remotely close to the same punishment as the guy who doesn’t even appear intoxicated but blows a 0.081 at a DUI checkpoint.
Alexander Peter Kristopeit bought his basement from his mommy for one dollar.
I don't understand exactly what's going on here, but then again, I'm smart enough to know that I don't know what's going on.
I listen to both RIAA and non-RIAA stuff if I like the music, tangential business/politics nonwithstanding.
That's a good argument to start cracking down on distracted drivers. Not a good argument to start letting people drive drunk.
Is 1563649 a prime number?
Great. When Gramma has the same legal consequences for driving with her inch-thick glasses as I’d get after having 3 beers, I’ll be satisfied that at least if the system isn’t just it’s at least fairly and consistently applied.
Alexander Peter Kristopeit bought his basement from his mommy for one dollar.
Richard Dawkins devotes a whole chapter to exactly this problem in his "Unweaving the Rainbow". It comes down to understanding the statistical probability of a chance match for the particular test method - of which there are many and some are just bad. Until lawyers can articulate this in court, juries will have problems...