Problem Note 4012: Distributions of risk factors following Monte Carlo simulation may not
match the distributions of these factors in the input data set
Monte Carlo simulation may incorrectly result in simulated risk factor
distributions (sample mean, variance, etc.) that significantly differ
from the input data. This problem can occur either when the supplied
covariance matrix is non-positive definite or when Risk Dimensions
computes the covariance matrix automatically from input data which has
missing values.
To circumvent the problem, supply a positive definite covariance matrix.
A Technical Support hot fix for Release 8.1 TSLEVEL TS1M0 for this
issue is available at:
http://www.sas.com/techsup/download/hotfix/81_sbcs_prod_list.html#004012
Operating System and Release Information
| SAS System | SAS Risk Dimensions Enterprise Edition | Solaris | 3.1 | 3.2 | | |
| Microsoft Windows NT Workstation | 3.1 | 3.2 | | |
| Tru64 UNIX | 3.1 | 3.2 | | |
| 64-bit Enabled AIX | 3.1 | 3.2 | | |
| 64-bit Enabled Solaris | 3.1 | 3.2 | | |
| AIX | 3.1 | 3.2 | | |
*
For software releases that are not yet generally available, the Fixed
Release is the software release in which the problem is planned to be
fixed.
| Type: | Problem Note |
| Priority: | alert |
| Date Modified: | 2002-04-29 15:12:47 |
| Date Created: | 2000-12-21 16:24:53 |
