Results 1 to 4 of 4

Thread: Distribution of sum of normal and gamma random variable

  1. #1
    Senior Member
    Joined
    Apr 2009
    Posts
    310

    Distribution of sum of normal and gamma random variable

    Let $\displaystyle Z = X + Y$ where $\displaystyle X \sim N\left(\mu, \sigma^2 \right)$ and $\displaystyle Y \sim \Gamma\left(k, \theta \right)$ using this parametrization of the Gamma distribution. Also assume $\displaystyle X$ and $\displaystyle Y$ are independent. Then what is the distribution (pdf) of $\displaystyle Z$?


    ----------


    This question doesn't seem as straightforward as it sounds. For example, I have tried using the convolution formulas here, but can't seem to find a closed form expression for the integral. I have also tried multiplying the moment generating functions (mgfs) of $\displaystyle X$ and $\displaystyle Y$, but it does not seem to match up to any known mgfs.

    Does anyone have any ideas on how to find the distribution for $\displaystyle Z$?
    Follow Math Help Forum on Facebook and Google+

  2. #2
    MHF Contributor
    Joined
    Nov 2013
    From
    California
    Posts
    6,109
    Thanks
    2594

    Re: Distribution of sum of normal and gamma random variable

    I doubt that this will get you a closed form but did you try using characteristic functions?
    Follow Math Help Forum on Facebook and Google+

  3. #3
    Senior Member
    Joined
    Apr 2009
    Posts
    310

    Re: Distribution of sum of normal and gamma random variable

    Quote Originally Posted by romsek View Post
    I doubt that this will get you a closed form but did you try using characteristic functions?
    I'm not too sure what characteristic functions are, how would I apply that here?
    Follow Math Help Forum on Facebook and Google+

  4. #4
    MHF Contributor
    Joined
    Nov 2013
    From
    California
    Posts
    6,109
    Thanks
    2594

    Re: Distribution of sum of normal and gamma random variable

    it's basically the fourier transform of a probability distribution function and as such the characteristic function of the sum of 2 rvs is the product of the individual characteristic functions.

    I just came across this

    http://cran.r-project.org/web/packag...ormalGamma.pdf

    it won't give you a closed form answer but it might be of interest.
    Last edited by romsek; Nov 27th 2013 at 09:34 PM.
    Follow Math Help Forum on Facebook and Google+

Similar Math Help Forum Discussions

  1. Gamma random variable problem
    Posted in the Advanced Statistics Forum
    Replies: 2
    Last Post: Jul 25th 2011, 10:36 AM
  2. Random Variable (Normal Distribution)
    Posted in the Statistics Forum
    Replies: 1
    Last Post: Jan 19th 2011, 08:01 AM
  3. Gamma Random Variable
    Posted in the Advanced Statistics Forum
    Replies: 2
    Last Post: Aug 23rd 2010, 02:18 AM
  4. Replies: 2
    Last Post: Apr 12th 2010, 12:59 AM
  5. Replies: 9
    Last Post: Jan 28th 2010, 07:26 AM

Search Tags


/mathhelpforum @mathhelpforum