Problem Note 14048: Floating point zero divide error in PROC PSMOOTH with TPM option
If a p-value has a value of exactly zero for a variable in the VAR
statement and the TPM option is used in the PROC PSMOOTH statement, a
floating point zero divide error occurs.
To circumvent the error, change any p-values that are exactly zero to a
very small number (like 1E-15) in the DATA step prior to running PROC
PSMOOTH.
A fix for SAS 9.1.3 (9.1 TS1M3) for this issue is available at:
http://www.sas.com/techsup/download/hotfix/e9_sbcs_prod_list.html#014048
Operating System and Release Information
SAS System | SAS/Genetics | Microsoft® Windows® for 64-Bit Itanium-based Systems | 9.1 TS1M0 | 9.2 TS1M0 |
Microsoft Windows NT Workstation | 9.1 TS1M0 | |
Microsoft Windows Server 2003 Standard Edition | 9.1 TS1M0 | 9.2 TS1M0 |
Microsoft Windows 2000 Server | 9.1 TS1M0 | 9.2 TS1M0 |
Microsoft Windows Server 2003 Datacenter Edition | 9.1 TS1M0 | 9.2 TS1M0 |
Microsoft Windows Server 2003 Enterprise Edition | 9.1 TS1M0 | 9.2 TS1M0 |
Microsoft Windows 2000 Datacenter Server | 9.1 TS1M0 | 9.2 TS1M0 |
Microsoft Windows 2000 Professional | 9.1 TS1M0 | 9.2 TS1M0 |
z/OS | 9.1 TS1M0 | 9.2 TS1M0 |
64-bit Enabled Solaris | 9.1 TS1M0 | 9.2 TS1M0 |
Microsoft Windows 2000 Advanced Server | 9.1 TS1M0 | 9.2 TS1M0 |
64-bit Enabled AIX | 9.1 TS1M0 | |
OpenVMS Alpha | 9.1 TS1M0 | 9.2 TS1M0 |
64-bit Enabled HP-UX | 9.1 TS1M0 | |
HP-UX IPF | 9.1 TS1M0 | 9.2 TS1M0 |
Linux | 9.1 TS1M0 | 9.2 TS1M0 |
Microsoft Windows XP Professional | 9.1 TS1M0 | 9.2 TS1M0 |
Tru64 UNIX | 9.1 TS1M0 | 9.2 TS1M0 |
*
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: | medium |
Topic: | SAS Reference ==> Procedures ==> PSMOOTH Analytics ==> Genetics
|
Date Modified: | 2005-02-03 09:09:30 |
Date Created: | 2004-12-20 09:29:02 |