Re: Possibly Silly Question on Manipulating Statistical Distributions
- To: mathgroup at smc.vnet.net
- Subject: [mg9416] Re: Possibly Silly Question on Manipulating Statistical Distributions
- From: NOHAMcrose at c2.telstra-mm.net.au (Colin Rose)
- Date: Wed, 5 Nov 1997 01:56:33 -0500
- Organization: Theoretical Research Institute
- Sender: owner-wri-mathgroup at wolfram.com
Luci Ellis <elisha at dot.net.au> wrote: > I would like to plot the PDFs and CDFs of random variables, where said > r.v.'s are combinations of other random variables with known, standard > distributions. > Defining a distribution like: > > xdist = PoissonDistribution[10] > ydist = NormalDistribution[0,1] > zdist = NormalDistribution[0,2] > > Then: > wdist = ydist + zdist > udist = xdist * ydist > > return: PoissonDistribution[10]*NormalDistribution[0,1] or > NormalDistribution[0,1]+NormalDistribution[0,2] as expected. > But good luck trying to plot these beasties' PDFs. > > I know you can't just add the PDFs or anything crazy like that. Is there > a way to get these distributions without doing multiple samples from > the distribution and building it up empirically? Section 16.3 of "Varian (1996), Computational Economics and Finance with mathematica", Springer, provides a Transform[] fn for doing transformations of pdfs. Of course, it won't help you multiply a discrete density (Poisson) by a continuous one (normal), but it should otherwise prove helpful. Cheerio Colin -- Colin Rose tr(I) - Theoretical Research Institute ______________________________________ NOHAMcrose at c2.telstra-mm.net.au http://www.usyd.edu.au/su/tri/