+ Reply to Thread
Results 1 to 4 of 4

Thread: How to test this kind statistical hypothesis ?

  1. #1
    Points: 397, Level: 7
    Level completed: 94%, Points required for next Level: 3

    Location
    Poland
    Posts
    7
    Thanks
    0
    Thanked 0 Times in 0 Posts

    How to test this kind statistical hypothesis ?




    Hey. How can I test H_{0} \: : \;\;\; \frac{\mu_{1} + \mu_{3}}{2}=\mu_{2}?
    Last edited by pajacek; 04-15-2012 at 10:26 AM.

  2. #2
    TS Contributor
    Points: 18,632, Level: 86
    Level completed: 57%, Points required for next Level: 218

    Posts
    2,796
    Thanks
    9
    Thanked 511 Times in 486 Posts

    Re: How to test this kind statistical hypothesis ?

    Usually exact test are rare. Even though in general you may form the likelihood ratio test statistic, the exact distribution is intractable and the critical region relies on simulation/numerical method. More common approach is forming the asymptotic tests.

    But these are not the most important issues. The most important one is that: what is your data structure? model? assumptions?
    Can you define your parameters more clearly? any likelihood function you can write down?

  3. #3
    Points: 397, Level: 7
    Level completed: 94%, Points required for next Level: 3

    Location
    Poland
    Posts
    7
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: How to test this kind statistical hypothesis ?

    I don't have specific data or assumptions. This is the problem submitted by one of professors as a matter of defending the thesis. But now I see that "+" is not shown properly and easy question has changed to huge one ...

    {H_{0} \: : \;\;\;\; \frac{{\mu_{1}} + {\mu_{3}}}{2}=\mu_{2}}
    Last edited by pajacek; 04-15-2012 at 10:26 AM.

  4. #4
    Beep
    Points: 63,245, Level: 100
    Level completed: 0%, Points required for next Level: 0
    Awards:
    Discussion EnderPosting AwardCommunity AwardMaster TaggerFrequent Poster
    Dason's Avatar
    Location
    Ames, IA
    Posts
    11,314
    Thanks
    266
    Thanked 2,202 Times in 1,881 Posts

    Re: How to test this kind statistical hypothesis ?


    The Tex tags are kind of weird here. The 'math' tags work a little better and end up rendering what you would expect.
    Morte a tutti i raptors
    001100010010011110100001101101110011

+ 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