turn on suggestions

Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

Showing results for

Find a Community

- Home
- /
- SAS Programming
- /
- SAS Procedures
- /
- Box Muller Transformation

Topic Options

- RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page

- Mark as New
- Bookmark
- Subscribe
- RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

11-14-2017 11:08 AM

Let X and Y be independent random variables from the bivariate normal distribution where

X ~ N(μ1= 15,σ1^2= 5) and Y ~ N(μ2= 10,σ2^2= 3). Generate 10000 random numbers for X and Y using the

Box Muller transformation.

-Print a histogram for both X and Y and supply the appropriate descriptive statistics to verify your

requirements.

-Print a Contour and Surface plot in SAS.

I don't know how to begin. I can't seem to find anything helpful for Box Muller Transformations coding.

- Mark as New
- Bookmark
- Subscribe
- RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

Posted in reply to trash

11-14-2017 01:29 PM

You could try looking up Box-Muller on Wikipedia, for a start.

PG

- Mark as New
- Bookmark
- Subscribe
- RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

Posted in reply to PGStats

11-14-2017 01:32 PM

You could also search SAS Help for "box muller". Hint: it's in there!

--

Paige Miller

Paige Miller

- Mark as New
- Bookmark
- Subscribe
- RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

Posted in reply to trash

11-14-2017 03:22 PM

The Box-Mueller transformation is a way to generate a random normal variates from two uniform variates.

1. Learn how to generate uniform random variates in SAS in the DATA step.

2. Use DATA step programming to combine the uniform variates to form a normal variate.

I suggest looking into PROC UNIVARIATE when you are ready to generate descriptive statistics that indicate that the sample statistics for X and Y are close to the parameters in the population.

For the contour plot and surface plot, I suggest you look at PROC KDE, which can produce bivariate plots of density.