How Reliable is the Truth Serum in Determining Guilt?

  • Context: Undergrad 
  • Thread starter Thread starter ballstix
  • Start date Start date
  • Tags Tags
    Probability
Click For Summary
SUMMARY

The discussion focuses on the reliability of truth serum in determining guilt among inmates, specifically analyzing a scenario where 5% of inmates are guilty and 95% are innocent. When administered to guilty inmates, the truth serum has a 90% success rate, while it has a 99% success rate for innocent inmates. The user seeks to calculate the probability of an inmate being guilty given an innocent result from the serum, and confirms the initial calculation as correct, which is (.005) / (.005 + .9405).

PREREQUISITES
  • Understanding of probability theory
  • Familiarity with Bayesian inference
  • Basic knowledge of statistical analysis
  • Ability to interpret probability trees
NEXT STEPS
  • Study Bayesian probability calculations
  • Learn about probability trees and their applications
  • Research the implications of false positives and false negatives in forensic science
  • Examine case studies involving truth serum and its effectiveness
USEFUL FOR

Statisticians, forensic psychologists, legal professionals, and anyone interested in the application of probability in criminal justice.

ballstix
Messages
1
Reaction score
0
okay so there is a group of inmates: 5% are guilty and 95% are innocent

a truth serum is being used; when used on guilty inmates, it has a 90% chance of working (causing them to end up guilty) and a 10% chance of failure (causing them to end up innocent). when used on innocent inmates, it has a 99% chance of working (resulting in innocent) and a 1% chance of failure (resulting in guilty).

I need to find the probability of an inmate being guilty if the serum's result is innocent, as well as vice-versa, but that should be trivial once I figure out how to do the first one.

I drew a tree thing but it's not really helping me:
http://img27.imageshack.us/img27/7988/treefsy.jpg

is the first one (.005) / (.005 + .9405)?
 
Last edited by a moderator:
Physics news on Phys.org
Yes.
 

Similar threads

  • · Replies 11 ·
Replies
11
Views
4K
  • · Replies 19 ·
Replies
19
Views
6K
  • · Replies 4 ·
Replies
4
Views
3K
  • · Replies 0 ·
Replies
0
Views
3K
  • · Replies 10 ·
Replies
10
Views
3K
  • · Replies 33 ·
2
Replies
33
Views
9K
  • · Replies 62 ·
3
Replies
62
Views
12K
  • · Replies 1 ·
Replies
1
Views
3K
  • · Replies 15 ·
Replies
15
Views
6K
  • · Replies 10 ·
Replies
10
Views
4K