+ Reply to Thread
Results 1 to 3 of 3

Thread: The movie, The Parallax View

  1. #1
    TS Contributor
    Points: 7,284, Level: 56
    Level completed: 67%, Points required for next Level: 66

    Location
    MD, USA
    Posts
    465
    Thanks
    8
    Thanked 11 Times in 11 Posts

    The movie, The Parallax View




    Eighteen people were at a party to honor a prominent guest when that person was shot and killed.
    Over the next three years 1/3 of these eighteen people died of various causes.
    You have a mortality table for these surviving men and women and you may assume they were all between 30 & 50.

    If you stop the movie at this point, how would you attack the problem of proving or disproving that this series of events taken as a whole is a coincidence to some level of certainty?
    I'll be glad to do the math.

    Can the problem be solved at all?

    TIA.

  2. #2
    TS Contributor
    Points: 6,786, Level: 54
    Level completed: 18%, Points required for next Level: 164

    Location
    Sweden
    Posts
    524
    Thanks
    44
    Thanked 112 Times in 100 Posts

    Re: The movie, The Parallax View

    I suppose that one idea is to use existing mortality rates and calculate an approximate probability that this (or worse) would happen to 18 randomly selected people. If that probability is low then we'd have evidence against the null hypothesis of "nothing strange has happened".

  3. #3
    TS Contributor
    Points: 7,284, Level: 56
    Level completed: 67%, Points required for next Level: 66

    Location
    MD, USA
    Posts
    465
    Thanks
    8
    Thanked 11 Times in 11 Posts

    Re: The movie, The Parallax View


    Thanks for your reply.
    I've also received substantial help from a person in a country south and a little east of you.

    Here's his plan:

    P(no more murdering | one person was murdered) = 0.99
    P( more murdering | one person was murdered) = 0.01

    P(number of party members someone wants to murder | more murdering)
    = 1/18 = "we have no clue"
    or
    = (18!/(number! (18-number)!) 0.1^number 0.9^(18-number) = "10% chance for anybody there for the murder to have a reason to kill also this person"

    P(death of a person | somebody wants to kill this person) = 0.00x
    P(death of a person | nobody wants to kill this person) = 0.7

    Work out

    P( more murdering | 6 additional people died)
    and
    P(no more murdering | 6 additional people died)


    Not even Karl Popper knew how to handle conspiracy theories but Bayes' Theorem gives me some hope.

+ Reply to Thread

           




Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts






Advertise on Talk Stats