Results 1 to 4 of 4

Math Help - variable dependency check

  1. #1
    Newbie
    Joined
    Aug 2008
    Posts
    9

    variable dependency check

    hi,
    i am a bit confused. i know how to check if two variables are not correlated.
    but how do i check they are independent?
    for instance i have x-y, max(,x,y)
    i guess i should see if the probability of their mult. equals the multiplication of their probabilities. is there an elegant way to do it except for just calculating by hand each of the probabilities?

    thanks
    Follow Math Help Forum on Facebook and Google+

  2. #2
    Member
    Joined
    Oct 2009
    Posts
    218
    If X and Y are indepenent, then Cov(X,Y) = 0
    Follow Math Help Forum on Facebook and Google+

  3. #3
    Moo
    Moo is offline
    A Cute Angle Moo's Avatar
    Joined
    Mar 2008
    From
    P(I'm here)=1/3, P(I'm there)=t+1/3
    Posts
    5,618
    Thanks
    6
    Quote Originally Posted by zhenyazh View Post
    hi,
    i am a bit confused. i know how to check if two variables are not correlated.
    but how do i check they are independent?
    for instance i have x-y, max(,x,y)
    i guess i should see if the probability of their mult. equals the multiplication of their probabilities. is there an elegant way to do it except for just calculating by hand each of the probabilities?

    thanks
    When dealing with random variables, rather than events, it's not as easy.

    If you're dealing with 2 discrete random variables, X & Y, check that for any x,y, P(X=x,Y=y)=P(X=x)P(Y=y).

    If you're dealing with 2 continuous random variables with pdf, X & Y, check that the joint probability density function is the product of X's pdf and Y's pdf.

    Or you can use cumulative density functions as well : check that for all x,y, P(X \leqslantx,Y \leqslant y)=P(X \leqslantx)P(Y \leqslant y)

    There's still other methods, including moment generating functions, among others (see wikipedia)

    If you're looking for the independence of X-Y & max(X,Y), try to get to something related to X and Y in the first case.
    In the second case, use a jacobian transformation.
    In the third case, which is probably the better one for X-Y & max(X,Y), get to something related to X and Y : if max(X,Y)<m, then both X and Y are < m.


    Quote Originally Posted by statmajor View Post
    If X and Y are indepenent, then Cov(X,Y) = 0
    Note that this is only useful if you want to prove that there's no indendence.
    Indeed, the contrapositive of this statement is : if cov(X,Y)≠0, then X and Y are not independent.
    But it's not useful if one wants to prove there's independence.
    Follow Math Help Forum on Facebook and Google+

  4. #4
    Member
    Joined
    Oct 2009
    Posts
    218
    Quote Originally Posted by Moo View Post
    Note that this is only useful if you want to prove that there's no indendence.
    Indeed, the contrapositive of this statement is : if cov(X,Y)≠0, then X and Y are not independent.
    But it's not useful if one wants to prove there's independence.
    Forgot about that, thank you for correcting me.
    Follow Math Help Forum on Facebook and Google+

Similar Math Help Forum Discussions

  1. Dependency between orbits
    Posted in the Advanced Algebra Forum
    Replies: 0
    Last Post: October 20th 2011, 10:20 AM
  2. [SOLVED] linear dependency
    Posted in the Advanced Algebra Forum
    Replies: 3
    Last Post: September 28th 2011, 08:12 PM
  3. A question in Set Dependency prof
    Posted in the Discrete Math Forum
    Replies: 2
    Last Post: April 15th 2011, 07:18 AM
  4. Linear Dependency
    Posted in the Advanced Algebra Forum
    Replies: 3
    Last Post: February 4th 2010, 11:35 PM
  5. Conditional dependency of events
    Posted in the Statistics Forum
    Replies: 0
    Last Post: January 24th 2010, 06:17 PM

Search Tags


/mathhelpforum @mathhelpforum