Many thanks for this reply and previously several patient answers provided.
Xi are iid gamma distribution and should have the same scale parameter. If the shape parameter and scale parameter of Xi are a and b, respectively. Then Y is still gamma distribution. Moreover, the shape parameter of Y is a, and the scale parameter of Y is nb. Is this correct? Rgds. "Robert Israel" <[EMAIL PROTECTED]> wrote in message news:[EMAIL PROTECTED] > In article <[EMAIL PROTECTED]>, > ZHANG Yan <[EMAIL PROTECTED]> wrote: > >Hea, I got the following problem. > > >Suppose Y=X1+X2+...Xn, where Xi (i=1,2...n) are positive i.i.d. gamma > >distribution. I > >hope to find the distribution function of Y, which is denoted as y(t). Or > >find the corresponding vector y with t varies from 0 to 100. > > >By using the laplace transform approach, I found that it is impossible to > >inverse the the laplace transform of y(t). and now i can not think of other > >methods to find the vector with respect the varying t. > > Hint: If you can find the laplace transform of the gamma distribution, you > can find the inverse laplace transform of the distribution of Y... > > Robert Israel [EMAIL PROTECTED] > Department of Mathematics http://www.math.ubc.ca/~israel > University of British Columbia > Vancouver, BC, Canada V6T 1Z2 > > > > > > > > > > > . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
