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

Topic Options

- Subscribe to 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
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

01-18-2016 06:58 PM

Hello:

Expert does any one now what is wrong with the following code:

I am simulating a truncated distribution that is multivariate in nature with the follow code from Rick's blog, but it not working well:

data TruncNormal(keep=x fa fb);

Fa = cdf('Normal', 30); /* for a = 30 */

Fb = cdf('Normal', 50); /* for b = 50 */

call streaminit(1234);

do i = 1 to 1000; /* sample size = 1000 */

v = Fa + (Fb-Fa)*rand('Uniform'); /* V ~ U(F(a), F(b)) */

x = quantile('Normal', v); /* truncated normal on [a,b] */

output;

end;

run;

ods select histogram;

proc univariate data=TruncNormal;

histogram x / endpoints=30 to 50 by 5;

run;

The aim is to simulate a truncated [a=30,b=50] distribution that is normally distribution. Minimum value is 30 maximum value is 50. The orginal normal distribution has a mean of 38 and standard of 5. Following generation,I like to check to see that the generated distribution is in fact a PDF.

The above case is aimed to generate on one instance of such a truncated distribution, but I want to genereate three of such variable so that I have a multivariate distrunction with column=3 and a with specified covariance. The plan is to generate the truncated distribution thrice and then merge but that can't build the covariance.

I see that one can still use acceptance-rejection, but building covariance/correlation may be challenging.

Thanks for your help.

Accepted Solutions

Solution

01-19-2016
06:16 AM

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

Posted in reply to SWEETSAS

01-18-2016 10:16 PM

You must specify the parameters of the simulated truncated distribution:

```
data TruncNormal(keep=x fa fb);
Fa = cdf('Normal', 30, 38, 5); /* for a = 30 */
Fb = cdf('Normal', 50, 38, 5); /* for b = 50 */
call streaminit(1234);
do i = 1 to 1000; /* sample size = 1000 */
v = Fa + (Fb-Fa)*rand('Uniform'); /* V ~ U(F(a), F(b)) */
x = quantile('Normal', v, 38, 5); /* truncated normal on [a,b] */
output;
end;
run;
ods select histogram;
proc univariate data=TruncNormal;
histogram x / endpoints=28 to 52 by 2;
run;
```

PG

All Replies

Solution

01-19-2016
06:16 AM

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

Posted in reply to SWEETSAS

01-18-2016 10:16 PM

You must specify the parameters of the simulated truncated distribution:

```
data TruncNormal(keep=x fa fb);
Fa = cdf('Normal', 30, 38, 5); /* for a = 30 */
Fb = cdf('Normal', 50, 38, 5); /* for b = 50 */
call streaminit(1234);
do i = 1 to 1000; /* sample size = 1000 */
v = Fa + (Fb-Fa)*rand('Uniform'); /* V ~ U(F(a), F(b)) */
x = quantile('Normal', v, 38, 5); /* truncated normal on [a,b] */
output;
end;
run;
ods select histogram;
proc univariate data=TruncNormal;
histogram x / endpoints=28 to 52 by 2;
run;
```

PG

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

Posted in reply to SWEETSAS

01-19-2016 05:59 AM

Apparently the reference is "The inverse CDF method for simulating from a distribution," which is based on Chapter 7 of *Simulating Data with SAS *(Wicklin 2013)..

See also "Implement the truncated normal distribution in SAS."

If your eventual goal is multivariate correlated, I recommend reading Chapter 9, "Advanced Simulation of Multivariate Data" as well as searching the literature. This looks like a challenging problem!

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

Posted in reply to SWEETSAS

01-19-2016 06:21 AM

Thanks. Yes, multivariate correlated is the goal. And yes, it is a challenging problem.

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

Posted in reply to SWEETSAS

01-19-2016 06:22 AM

Thanks PGstat. The code works for univariate case