Yale med student missing?

This forum made possible through the generous support of SDN members, donors, and sponsors. Thank you.
austinap said:
I said that they weren't much better than chance. 61% isn't much better than chance. You also missed my second point, looking at the statistics of it.

Let's assume there were 100 people that were potential suspects, and only one killer. This seems to be a reasonable assumption. Taking the validity of the lie detector into account, let's use the numbers

P(fail | killer) = 0.61 (the probability that you'll fail the test given that you're the killer)
P(fail | not killer) = 0.39 (the probability that you'll fail even if you're innocent)

Then given the numbers of people, selecting any random person, we have:

P(killer) = 1 / 100
P(not killer) = 99 / 100

Putting it all together, we want to see how likely someone is to be the killer given that they failed a polygraph test:

P(killer | fail) = P(fail | killer)P(killer) / [P(fail | killer)P(killer) + P(fail | not killer)P(not killer)]

Plugging in the numbers, we get:

P(killer | fail) = 0.0156, or a 1.6% chance that the person was the killer given that they failed a polygraph. That's next to useless, given that selecting any random person would give you a 1% chance of having chosen correctly based on absolutely no evidence at all. If an individual fails a polygraph under these conditions, they still have a 98.4% chance of being innocent, only slightly down from the 99% chance they had before.

Let's make it stronger. Let's say that there were only 10 possible suspects, so now

P(killer) = 1/10
P(not killer) = 9/10

Now, P(killer | fail) = 14.8%, or ~5% more likely than having chosen a random person. Again, next to useless.
Click to expand...

holy.. spoons..
 
austinap said:
I said that they weren't much better than chance. 61% isn't much better than chance. You also missed my second point, looking at the statistics of it.

Let's assume there were 100 people that were potential suspects, and only one killer. This seems to be a reasonable assumption. Taking the validity of the lie detector into account, let's use the numbers

P(fail | killer) = 0.61 (the probability that you'll fail the test given that you're the killer)
P(fail | not killer) = 0.39 (the probability that you'll fail even if you're innocent)

Then given the numbers of people, selecting any random person, we have:

P(killer) = 1 / 100
P(not killer) = 99 / 100

Putting it all together, we want to see how likely someone is to be the killer given that they failed a polygraph test:

P(killer | fail) = P(fail | killer)P(killer) / [P(fail | killer)P(killer) + P(fail | not killer)P(not killer)]

Plugging in the numbers, we get:

P(killer | fail) = 0.0156, or a 1.6% chance that the person was the killer given that they failed a polygraph. That's next to useless, given that selecting any random person would give you a 1% chance of having chosen correctly based on absolutely no evidence at all. If an individual fails a polygraph under these conditions, they still have a 98.4% chance of being innocent, only slightly down from the 99% chance they had before.

Let's make it stronger. Let's say that there were only 10 possible suspects, so now

P(killer) = 1/10
P(not killer) = 9/10

Now, P(killer | fail) = 14.8%, or ~5% more likely than having chosen a random person. Again, next to useless.
Click to expand...

This argument is mute anyways. Lie-detectors are not admissible in court. The only reason that cops use them is to see if they have any reason to try and prove the case.
 
The person who failed the polygraph also has defensive wounds on his body, reportedly.
 
chman said:
This argument is mute anyways. Lie-detectors are not admissible in court. The only reason that cops use them is to see if they have any reason to try and prove the case.
Click to expand...

I think you meant "moot". Whether or not lie detector results are admissible in court varies by jurisdiction, but in general they can be used. Some states actually allow polygraph tests to be taken in front of juries (New Mexico).

Even if this was not allowed as evidence, something with such a high failure rate is not a very useful tool, and it disturbs me a little when I see police basing an investigation on such a flawed test**. As a clinical example, PSA screening has a much higher success rate, but its utility is in hot debate because of the same statistical phenomenon. Conditional probability is important people!

** I'm not saying they're necessarily doing that here.
 
This sucks. My condolences to the family and anyone dealing with this tragedy. Hopefully they will catch the murderer.
 
austinap said:
I said that they weren't much better than chance. 61% isn't much better than chance. You also missed my second point, looking at the statistics of it.

Let's assume there were 100 people that were potential suspects, and only one killer. This seems to be a reasonable assumption. Taking the validity of the lie detector into account, let's use the numbers

P(fail | killer) = 0.61 (the probability that you'll fail the test given that you're the killer)
P(fail | not killer) = 0.39 (the probability that you'll fail even if you're innocent)
Click to expand...

Your article suggested a false positive at 15% not 39%. Aren't P(fail | killer) and P (fail | not killer) indepedent???

_______|Pass|Fail
Killer___|.39|.61
Not Killer|.85|.15

NOT

_______|Pass|Fail
Killer___|.39|.61
Not Killer|.61|.39
 
Oh no:scared:
a statistics flame war...

...the best kind of flame war! 😀
 
Optimalsauce said:
Your article suggested a false positive at 15% not 39%. Aren't P(fail | killer) and P (fail | not killer) indepedent???

_______|Pass|Fail
Killer___|.39|.61
Not Killer|.85|.15

NOT

_______|Pass|Fail
Killer___|.39|.61
Not Killer|.61|.39
Click to expand...


You're right, my mistake. There's no reason for those numbers to be related. Even so, taking the new numbers you get:

P(killer | fail) = 3.9% when N = 100,
P(killer | fail) = 31% when N = 10 people.

Better, but still not very good if the sample size is at all large.
 
"Authorities investigating the murder of Yale graduate student Annie Le are focusing their attention on a lab tech"

Yup, shady lab tech sounds about right.
 
why is this a thread in a pre-medical forum, when this has nothing to do with medical school??? 😕
 
jjmad1201 said:
why is this a thread in a pre-medical forum, when this has nothing to do with medical school??? 😕
Click to expand...

1. At first she was being called a med student. Misinterpretation by media, sparked interest among pre-meds. Kept the thread going to find out outcome.

2. Why are you coming here if you don't want to read about it?

Advice: Next time don't click the link.
 
So do they know who did it yet?

Are Yale students allowed back in the building?
 
My friend goes to Yale and everyone there is freaked out...She actually was a med student, my friend said she was MD/PhD...Apparently the person had access to the bldg and anyone could have been the victim...this sucks.
 
Last edited:
CremasterFlash said:
for f*ck's sake... is there some giant ass crack of the internet that you people crawl out of periodically to spout nonsense?

she wasn't a med student, we're not freaked out and there is absolutely no evidence to support your penultimate sentence.

you are correct though, it does suck.
Click to expand...


"penultimate"

and who says O-chem is useless after college?
 
bamtuba said:
But her former lab mates are.

Just quit digging.
Click to expand...

I understand why some people may feel emotional but this is no reason to expect as mass "silence" on the issue or for people to stop speculating. Everyone is curious/concerned, that's natural. However, If I was feeling emotional about an issue you can believe I wouldn't be clicking on anonymous Internet forums to hear others talk about it.
 
Heh, teenmachinery calm the **** down...I am just telling you what my friend who goes to Yale told me...**** if you are not freaked out by a brutal murder, what does freak you out?
 
Forget the lie-detector. The killer is ****ed. They found bloody clothes that match the DNA of a lab tech, who has defensive wounds on him.

****ed I tell you.

EDIT: she was not MD/PhD. I know an MD/PhD at Yale (he's a second year granted) and he told me otherwise.
 
medfan303 said:
Heh, teenmachinery calm the **** down...I am just telling you what my friend who goes to Yale told me...**** if you are not freaked out by a brutal murder, what does freak you out?
Click to expand...

I think you quoted the wrong guy??
 
LOL OOPS. Sorry teenmachinery, was in a rush this morning and probably just assumed teenmachinery sounded on rage against the machine side 🙂 , the post was directed at CremasterFlash
 
why would the lab coat have the suspect's blood on it? why would he have open wounds?
 
it's so frustrating how everything is taking so long

news reporters have named a suspect, the animal lab tech
 
austinap said:
I think you meant "moot". Whether or not lie detector results are admissible in court varies by jurisdiction, but in general they can be used. Some states actually allow polygraph tests to be taken in front of juries (New Mexico).

Even if this was not allowed as evidence, something with such a high failure rate is not a very useful tool, and it disturbs me a little when I see police basing an investigation on such a flawed test**. As a clinical example, PSA screening has a much higher success rate, but its utility is in hot debate because of the same statistical phenomenon. Conditional probability is important people!

** I'm not saying they're necessarily doing that here.
Click to expand...

Yes, I meant moot. Thanks for pointing out my grammatical mistakes...(said as eyes roll).

EDIT: I just looked at the American Polygraph Association website. They say the use of polygraphs is used in only a few states in the country, and sometimes, depending on the judge, federal court. But both parties, must agree to it's use before hand, I guess. After reading their explanation I really did not have a clear answer though.

www.polygraph.org

I was under the impression that no courts accepted them..learn something new everyday.
 
Last edited:
Pinkertinkle said:
"Authorities investigating the murder of Yale graduate student Annie Le are focusing their attention on a lab tech"

Yup, shady lab tech sounds about right.
Click to expand...

Because a fellow graduate student has never committed a crime against a fellow student...
 
bamtuba said:
But her former lab mates are.

Just quit digging.
Click to expand...

👍

Please remember that these articles aren't recaps of a CSI episode, or the newest twist on Lost and that while open speculation may be entertaining for you, that it can be very hurtful to others. This is a very real story, that has people very shaken up. Many people on this site are tied to either Yale or Rochester...and for those who knew Annie, this situation evokes much more than an, "oh, how creepy/tragic" response.
 
Why is this thread still open?

She is not missing, she is dead.

This thread was and is inappropriate for SDN.

Please close this down NOW.
 
Why is this even in the premed forum? Moderators aren't doing their jobs...
 
Why would this thread be considered inappropriate?

I have been following this story in the news and am very disturbed by this case.
 
austinap said:
You're right, my mistake. There's no reason for those numbers to be related. Even so, taking the new numbers you get:

P(killer | fail) = 3.9% when N = 100,
P(killer | fail) = 31% when N = 10 people.

Better, but still not very good if the sample size is at all large.
Click to expand...

Apparently the sample size was 1 all along.
 
schrizto said:
Why would this thread be considered inappropriate?

I have been following this story in the news and am very disturbed by this case.
Click to expand...

Maybe because it has absolutely NOTHING to do with med school admissions, for starters?

What have you learned in this thread that has helped you ease your troubled mind over this case? What of value has been posted in this thread? All I see is a bunch of tasteless jokes and speculation.

How funny is it that the "mods" recently banned some dude who claimed he was an attending, but they leave a garbage thread like this up and running?
 
flip26 said:
Maybe because it has absolutely NOTHING to do with med school admissions, for starters?

What have you learned in this thread that has helped you ease your troubled mind over this case? What of value has been posted in this thread? All I see is a bunch of tasteless jokes and speculation.

How funny is it that the "mods" recently banned some dude who claimed he was an attending, but they leave a garbage thread like this up and running?
Click to expand...

whoa calm down, you're going to get yourself a hypertensive crsis.

So they finally arrested the guy, he's apparently one of those jerk off nit picky uppity lab techs. And as evidenced by being in the Asian club in HS, a probable asian fetish. Also has a history of girl trouble and looks like a shady murderer type.

He's got access to the crime scene, defensive wounds, sent the victim a text msg on the day of the disappearance asking to meet up, and bloody clothing with DNA match up. Hopefully it's not long before he's convicted and euthanized like a sick lab rat.
 
flip26 said:
Maybe because it has absolutely NOTHING to do with med school admissions, for starters?
Click to expand...

The pre-allo forum doesn't always have to be about medical school admissions. I think as long as it somehow relates to a medical school it's pretty much on-topic.
 
Also, can someone clarify if the victim was an MD/PhD student or a PhD student? I know most of the news has said she is only a PhD student, but I've seen a couple articles mention MD/PhD. It has been reported that she was a third year graduate student and was set to graduate in 2012. Yale's own website says she is MED '13. So the timeline is kind of long for a PhD.
 
schrizto said:
Also, can someone clarify if the victim was an MD/PhD student or a PhD student? I know most of the news has said she is only a PhD student, but I've seen a couple articles mention MD/PhD. It has been reported that she was a third year graduate student and was set to graduate in 2012. Yale's own website says she is MED '13. So the timeline is kind of long for a PhD.
Click to expand...

The timeline is not too long for a PhD. I believe that she was in a PhD in a graduate program sponsored by the medical school hence the MED designation which, I believe, has confused some people who are not familiar with that labeling system.
 
I HOPE this lab tech did it. Because otherwise what the media is doing to him is horrible.

Rember when Gary Condit 'killed' that girl, and then it turned out to have really been an illegal immigrant serial rapist? It's awful the way we allow the media to convict people before a trial has taken place.
 
Perrotfish said:
I HOPE this lab tech did it. Because otherwise what the media is doing to him is horrible.

Rember when Gary Condit 'killed' that girl, and then it turned out to have really been an illegal immigrant serial rapist? It's awful the way we allow the media to convict people before a trial has taken place.
Click to expand...

It is unfortunate, but it seems to me that the American judicial system is more guilty until proven innocent, than innocent until proven guilty. Especially in high profile cases, and, also, concerning socioeconomic status. Not that I am defending this guy, if he did it he is a heartless basta**.
 
Perrotfish said:
I HOPE this lab tech did it. Because otherwise what the media is doing to him is horrible.

Rember when Gary Condit 'killed' that girl, and then it turned out to have really been an illegal immigrant serial rapist? It's awful the way we allow the media to convict people before a trial has taken place.
Click to expand...

If you're innocent in this case, would you decline your interview with the police? decline any comment? I would be like telling the world I'm freaking innocent!

Gary Condit was denying it at the top of his lungs!
 
chman said:
This argument is mute anyways. Lie-detectors are not admissible in court. The only reason that cops use them is to see if they have any reason to try and prove the case.
Click to expand...


The term is "moot" not "mute."

"Mute" means that you cannot speak.

"Moot" means that an issue is no longer at stake, because of changed circumstances. A big issue for the Supreme Court in Roe v. Wade was whether the case was "moot" because the plaintiff was no longer pregnant by the time the case reached the court.

And even if you had used the correct word, you used it incorrectly. You meant that the argument about lie detectors is not pertinent or relevant because they are not admissible in court. there is no issue of mootness there.
 
slowbutsteady said:
The term is "moot" not "mute."

"Mute" means that you cannot speak.

"Moot" means that an issue is no longer at stake, because of changed circumstances. A big issue for the Supreme Court in Roe v. Wade was whether the case was "moot" because the plaintiff was no longer pregnant by the time the case reached the court.

And even if you had used the correct word, you used it incorrectly. You meant that the argument about lie detectors is not pertinent or relevant because they are not admissible in court. there is no issue of mootness there.
Click to expand...

That was already pointed out to me. My question for you is, why go through so much trouble to correct the simple misuse of a word? Do you really have nothing better to do?


I understand that mistakes in regards to the use of English can be bothersome, honestly it bothers me sometimes. But it is not necessary to call someone out on a public forum, especially when the mistake was already brought to my attention. You sir, should consider stepping down from the high-horse, and realize that people make mistakes.

It must be nice to be so perfect.

EDIT: I believe that if the argument is not relevant then its is a moot point.
 
chman said:
EDIT: I believe that if the argument is not relevant then its is a moot point.
Click to expand...


Um, no. I refer you to my previous post in which I explained that you were incorrect in your usage, as well as your spelling, of the word "moot.". "Mootness" is completely different from "relevance."

Geez.

And I always take time to fight the ruination of the English language.
 
You must log in or register to reply here.

Similar threads

D
  • Locked
  • Question Question
Honors Carolina (UNC-Chapel Hill) vs. Cornelius Vanderbilt scholarship vs. Yale for pre-med
Replies
28
Views
3K
Mr.Smile12
Mr.Smile12
1
Linguistics Missing from Foreign Languages & Literature
Replies
4
Views
379
123123321
1
F
Missing part on secondary
Replies
3
Views
1K
futureMD2321
F
TibiaOrNotTibia
Seeking Advice: Waiting To Submit Secondaries Due To LOR Missing?
Replies
4
Views
673
TibiaOrNotTibia
TibiaOrNotTibia
I
Natural science internship as an allopathic pre-med student?
Replies
3
Views
755
AJS59
AJS59
Top