Problem Note 17503: Incorrect results with RANDOM statement and TYPE=SP() when random effect
involves a continuous effect
If a PROC MIXED model contains a RANDOM statement like
random a*b / type=sp()
and the random effect of A*B involves a covariate (meaning that either
the effect A or B is not on the CLASS statement), then PROC MIXED will
either not converge or converge to the wrong solution.
To circumvent this problem, use PROC GLIMMIX to fit the model.
Select the Hot Fix tab in this note to access the hot fix for this issue.
Operating System and Release Information
| SAS System | SAS/STAT | Microsoft Windows XP Professional | 8.2 TS2M0 | 9.2 TS1M0 |
| Windows Millennium Edition (Me) | 8.2 TS2M0 | |
| Microsoft Windows 95/98 | 8 TS M0 | |
| Microsoft Windows NT Workstation | 8 TS M0 | |
| Microsoft Windows Server 2003 Standard Edition | 8.2 TS2M0 | 9.2 TS1M0 |
| Microsoft® Windows® for 64-Bit Itanium-based Systems | 9 TS M0 | 9.2 TS1M0 |
| Microsoft Windows Server 2003 Enterprise Edition | 8.2 TS2M0 | 9.2 TS1M0 |
| Microsoft Windows Server 2003 Datacenter Edition | 8.2 TS2M0 | 9.2 TS1M0 |
| Microsoft Windows 2000 Datacenter Server | 8 TS M0 | |
| Microsoft Windows 2000 Server | 8 TS M0 | |
| Microsoft Windows 2000 Professional | 8 TS M0 | |
| Microsoft Windows 2000 Advanced Server | 8 TS M0 | |
| OpenVMS VAX | 8 TS M0 | 9.2 TS1M0 |
| Solaris | 8 TS M0 | 9.2 TS1M0 |
| 64-bit Enabled Solaris | 8 TS M0 | 9.2 TS1M0 |
| z/OS | 8 TS M0 | 9.2 TS1M0 |
| IRIX | 8 TS M0 | 9.2 TS1M0 |
| OS/2 | 8 TS M0 | |
| Linux | 8.2 TS2M0 | 9.2 TS1M0 |
| Linux on Itanium | 9.1 TS1M3 | 9.2 TS1M0 |
| ABI+ for Intel Architecture | 8 TS M0 | 9.2 TS1M0 |
| HP-UX | 8 TS M0 | 9.2 TS1M0 |
| 64-bit Enabled HP-UX | 8 TS M0 | 9.2 TS1M0 |
| HP-UX IPF | 9 TS M0 | 9.2 TS1M0 |
| CMS | 8 TS M0 | 9.2 TS1M0 |
| 64-bit Enabled AIX | 9.1 TS1M0 | 9.2 TS1M0 |
| OpenVMS Alpha | 8 TS M0 | 9.2 TS1M0 |
| Tru64 UNIX | 8 TS M0 | 9.2 TS1M0 |
| AIX | 8 TS M0 | 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: | alert |
| Topic: | Analytics ==> Spatial Analysis
Analytics ==> Longitudinal Analysis
Analytics ==> Mixed Models
Analytics ==> Analysis of Variance
SAS Reference ==> Procedures ==> MIXED
Analytics ==> Regression
|
| Date Modified: | 2006-08-17 16:24:43 |
| Date Created: | 2006-04-20 14:11:40 |
