+ Reply to Thread
Results 1 to 3 of 3

Thread: Probability of someting that is yet to happen.

  1. #1
    Points: 4, Level: 1
    Level completed: 7%, Points required for next Level: 46

    Posts
    1
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Probability of someting that is yet to happen.




    Dear Reader,

    I was wondering if it would be possible to generate or calculate a probability or likelyhood of an event happening whilst you dont know at which time it would take place.

    As example, all the data is recorded, so there is enough historical data. Lets take a bicycle as the example. At time 0, it works and you dont know anything about what could fail. You have an idea, but that is it.

    When time 20 passes, the lights break. You register this failure, find out how to fix it, and bike some more.

    When time 48 passes, you have a flat tire.. Register it. Fix it.. Etc..

    But my question is, can you predict or calculate the probability if there is a failure on that bike that is yet to be discovered? (Like a broken cable for lights, which you will find out few months later in the winter because then you need it?)

    I also read some literature and found out about the Chinese Restaurant Process, and I believe it is somewhat the same idea. It is predicting the unpredictable. You dont know what will fail next, or how to notice that failure, because it never happened before. So an infinite amount of failures are possible, over an inifinte amount of time with an infinite percentage of you finding the failure before you need that light on your bike..

    I hope it makes any sense..
    Thanks for your time!

  2. #2
    TS Contributor
    Points: 7,081, Level: 55
    Level completed: 66%, Points required for next Level: 69

    Location
    Copenhagen , Denmark
    Posts
    515
    Thanks
    71
    Thanked 123 Times in 116 Posts

    Re: Probability of someting that is yet to happen.

    But my question is, can you predict or calculate the probability if there is a failure on that bike that is yet to be discovered? (Like a broken cable for lights, which you will find out few months later in the winter because then you need it?)
    Yes and No.

    You can make different statistical models and compare them on different measures. This is basically what the art of statistics is all about be it broken bicycles, biological systems, economies, bridges and whatever ....

    youre welcome

  3. #3
    TS Contributor
    Points: 5,246, Level: 46
    Level completed: 48%, Points required for next Level: 104
    maartenbuis's Avatar
    Location
    Konstanz
    Posts
    372
    Thanks
    3
    Thanked 146 Times in 123 Posts

    Re: Probability of someting that is yet to happen.


    I would be sceptical. At its core predictions about future events produced by statistics are extrapolations of past experience. If there is no past experience, then there is nothing to extrapolate (or based on your past experience you would predict that the probability of it happening is 0). So predictions work fine if nothing changes, but the future is not what it used to be, so prediction often proof to be spectacularly wrong.

+ 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