Court Verdicts: Guilty, Not Guilty, Not Proven

  • Thread starter Thread starter cloud360
  • Start date Start date
Click For Summary
SUMMARY

The discussion focuses on calculating the probabilities associated with court verdicts: 'guilty', 'not guilty', and 'not proven'. It establishes that 65% of verdicts are 'guilty', with a 5% chance of innocence among those found guilty, while the probabilities for 'not guilty' and 'not proven' verdicts are 0.90 and 0.30, respectively. The total probability of an accused person being innocent is calculated as 0.2375, correcting an initial miscalculation of 0.2875. Additionally, the probability that an innocent person is found guilty is derived from the total number of innocent individuals across all verdicts.

PREREQUISITES
  • Understanding of Bayes' Theorem
  • Knowledge of probability theory and conditional probabilities
  • Familiarity with legal terminology regarding court verdicts
  • Ability to perform basic arithmetic calculations in probability contexts
NEXT STEPS
  • Study Bayes' Theorem in depth to understand its applications in legal contexts
  • Explore conditional probability calculations with real-world examples
  • Research the implications of different verdict types in various legal systems
  • Practice probability problems involving multiple events and outcomes
USEFUL FOR

Students of law, statisticians, and professionals in the legal field who are interested in understanding the implications of court verdicts and the associated probabilities of innocence and guilt.

cloud360
Messages
212
Reaction score
0

Homework Statement


A court returns three verdicts. ‘guilty’, ‘not guilty’ and
‘not proven’. 65% of the verdicts were ‘guilty’, 25% of the verdicts
were ‘not guilty’ and 10% were ‘not proven’.

When the court’s verdict is ‘guilty’ 5% of the accused/tried are actually innocent. The corresponding probabilities for the verdicts ‘not guilty’ and ‘not proven’ are 0.90 and 0.30, respectively.


(a) What is the probability that an accused person is actually innocent?
(b) What is the probability that an innocent person will be found guilty?


Homework Equations




The Attempt at a Solution


I know how to do Question 1.

accused = 100%
f= innocent
E1=guilty
E2=not guilty
E3=not proven...therfore maximum of 3 events possible
E1, E2, E3=Accused = 100%

Using law of total probability p(f)=p(f|E1)P(E1) + p(f|E2)P(E2)...n times

p(f)=p(f|E1)P(E1) + p(f|E2)P(E2)+ p(f|E2)P(E3)


p(f|E1)=0.05

p(f|E1)=0.9

p(f|E1)=0.3
...all other info is given also

= 0.05 × 0.65 + 0.90 × 0.25 + 0.30 × 0.10
= 0.2875


HOW DO YOU DO Question 2!
 
Physics news on Phys.org


You're trying now to find P(E1|f). Hint: Look up Bayes Theorem.
 


Suppose there were 10000 cases. Then there were 6500 "guilty" verdicts, 2500 "not guilty", and 1000 "not proven" (That's a British verdict. In the United States, a person can only be found "guilty" or "not guilty" and if found "not guilty" can never be retried for that offense).

We are told that "When the court’s verdict is ‘guilty’ 5% of the accused/tried are actually innocent." which means that 0.05(6500)= 325 innocent people are found "guilty". That "The corresponding probabilities for the verdicts ‘not guilty’ and ‘not proven’ are 0.90 and 0.30, respectively" tells us that .90(2500)= 1750 innocent people are found "not guilty" and 0.3(1000)= 300 innocent people get verdicts of "non proven".

That is, there are a total of 325+ 1750+ 300= 2375 innocent people in the 10000 cases. Unless I have made an arithmetic error (always possible) the probability that an innocent person is accused is 2375/10000= .2375, not .2875.

Of those 2375 innocent people, 325 were found "guilty", so the probability that an innocent person is found "guilty" is ____.
 

Similar threads

Replies
1
Views
2K
  • · Replies 4 ·
Replies
4
Views
3K
  • · Replies 10 ·
Replies
10
Views
3K