"Although estimates vary, forensic DNA analysis is roughly 95% accurate."
I remember however an article I can't find now from about 20 years ago so probably things have improved since then that found only about 2/3rds accuracy - and that accuracy could be affected by stating the result you wanted. It was in Time, or New Republic or some major news magazine.
My thoughts could be colored by this, but given history of forensic abuse in the U.S I would tend to undervalue evidence that found someone guilty. I am however a cynic.
I would also think that this 95% accurate claim seems weird, since it is effected by all sorts of things, basically if DNA evidence gets admitted it is treated as bulletproof but it may still have a lower than 95% chance of being correct at that point - but when admitted the battle is pretty much lost.
I don’t think that a clearly mismatching DNA has anywhere above a one in a billion chance of belonging to the same person. So either the sample is wrong, which is near impossible with a rape case nowadays, or some technical mishandling (switch of samples?) that can of course happen but this is not likely leading to a 5% error rate. Maybe in the early days people used erratic methods for reading pieces of the DNA but it’s hard to imagine a 5% error rate even then. I guess the other way around could work, ie a match may be a twin sibling or something.
"Although estimates vary, forensic DNA analysis is roughly 95% accurate."
I remember however an article I can't find now from about 20 years ago so probably things have improved since then that found only about 2/3rds accuracy - and that accuracy could be affected by stating the result you wanted. It was in Time, or New Republic or some major news magazine.
My thoughts could be colored by this, but given history of forensic abuse in the U.S I would tend to undervalue evidence that found someone guilty. I am however a cynic.
I would also think that this 95% accurate claim seems weird, since it is effected by all sorts of things, basically if DNA evidence gets admitted it is treated as bulletproof but it may still have a lower than 95% chance of being correct at that point - but when admitted the battle is pretty much lost.