1
$\begingroup$

I would like to simulate random variates from a transformed distribution of a joint distribution and a constant.

i.e.

joint=ProductDistribution[NormalDistribution[],BetaDistribution[1,2],BetaDistribution[2,2]];
transform=TransformedDistribution[3*joint....]

I am unsure how to complete the transformed distribution code to put in the variables.

$\endgroup$
1
  • $\begingroup$ Please, when you see good questions and answers, vote them up by clicking the gray triangles, because the credibility of the system is based on the reputation gained by users sharing their knowledge. Also, please remember to accept the answer, if any, that solves your problem, by clicking the checkmark sign! $\endgroup$ Commented Dec 21, 2014 at 23:27

2 Answers 2

1
$\begingroup$
joint = ProductDistribution[NormalDistribution[], BetaDistribution[1, 2], BetaDistribution[2, 2]];
q = TransformedDistribution[{x, y, z} w, {{x, y, z} \[Distributed]  joint, 
                                          w \[Distributed] UniformDistribution[]}]
ListPlot3D@RandomVariate[joint, 100]

Mathematica graphics

$\endgroup$
2
  • $\begingroup$ Thanks for the help. Am I allowed to just say w is distributed by 3? I have an exact constant I would like to use. $\endgroup$
    – Jim
    Commented Dec 21, 2014 at 23:14
  • $\begingroup$ @Jim Sorry, I don't understand what you mean by "w is distributed by 3" $\endgroup$ Commented Dec 21, 2014 at 23:26
1
$\begingroup$
joint = ProductDistribution[NormalDistribution[], BetaDistribution[1, 2], BetaDistribution[2, 2]];
td = TransformedDistribution[3 {x, y, z} , Distributed[{x, y, z}, joint]];

Through@{Mean, Variance}@td
(* {{0,1,3/2}, {9,1/2,9/20}} *)

PDF[td, {x, y, z}]

enter image description here

ListPlot3D[RandomVariate[td, 50]]

enter image description here

See also: this answer to a closely related question by the same OP.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.