www.sas.com > Service and Support > Technical Support
Technical Support SAS - The power to know(tm)
  TS Home | Intro to Services | News and Info | Contact TS | Site Map | FAQ | Feedback


Release 8.2 Hot Fixes

SAS/STAT
® Software
Hot Fix Bundle 82SX02 for AIX



The following fixes are included in the 82SX02 Bundle for AIX:Introduced
in BUNDLE:
82ST01
SN-004841PROC CALIS produces incorrect results if an INWGT= data set is specified when METHOD=GLS 82SX01
82ST04
SN-005120Incorrect standard errors and parameter tests possible with NOPRINT and LACKFIT options 82SX01
82ST11
SN-005560Incorrect standard errors for repeated, multinomial models 82SX01
SN-006439Incorrect results when BY statement and AGGREGATE= option used together 82SX01
SN-007104Incorrect results with FREQ and/or WEIGHT statement when DIST=NEGBIN 82SX01
SN-007143Weights incorrectly applied when REPEATED statement is used 82SX01
SN-007297Incorrect results possible when the REPEATED statement is used with a FREQ or WEIGHT statement 82SX01
82ST13
SN-007028Incorrect results from IPF estimation if response variable has more than 256 levels 82SX01
SN-007732Abnormal Termination in PROC CATMOD when response effects have long variable names 82SX01
82ST14
SN-005594NLIN may give Error: Could not compute the change vector and fail to converge 82SX01
SN-005692PROC NLIN may give a Floating Point Zero Divide error with a BOUNDS 82SX01
SN-006607PROC NLIN may terminate abnormally if ARRAY variables begin with "der" 82SX01
SN-006626Invalid Operation error possible with BOUNDS and OUTPUT statements in PROC NLIN 82SX01
SN-008501NLIN may terminate with a Floating Point Overflow when a weight is used 82SX01
82ST15
SN-004855NEGBIN Distribution Produces Incorrect Results in PROC NLMIXED 82SX01
SN-008683PROC NLMIXED fails to process all levels of BY variable when a floating point overflow error occurs 82SX01
SN-008759PROC NLMIXED may display incorrect labels for some by-groups 82SX01
82ST16
SN-008764PROC GLM may not compute the correct error sums of squares when solving the Expected Mean Squares for RANDOM effects 82SX01
82ST17
SN-010513Out of memory error may occur when running PROC CLUSTER with a large distance matrix as input 82SX02 *
82ST18
SN-005135PROC MIXED Produces Incorrect Satterthwaite or KR Degrees of Freedom with TYPE=FA0(2) on RANDOM Statement and a singular G matrix 82SX01
SN-005132PROC MIXED May Report Wrong Satterthwaite or KR Degrees of Freedom with Heterogeneous Covariance Structures on the RANDOM statement 82SX01
SN-005780The DDFM=SATTERTHWAITE option can cause incorrect results when used in the presence of both a RANDOM and a REPEATED statement 82SX01
SN-011543The HTYPE=2 option on the MODEL statement in PROC MIXED produces incorrect results 82SX02 *
SN-011541Incorrect Parameter Estimates When Same Variable List Used on Random Statement and Model Statement 82SX02 *
SN-011540ASYCOV Matrix May Be Computed Incorrectly When Scoring Does Not Stop 82SX02 *
SN-011542Incorrect Covariance Parameter Estimates When LOCAL Option Used with Kronecker Product Structures on REPEATED Statement 82SX02 *

82SX02 * Indicates fixes that are appearing in a bundle for the first time.




Back to the Main Hot Fix Downloads Page


PLEASE CAREFULLY READ THE TERMS AND CONDITIONS OF THIS LICENSE AGREEMENT ("AGREEMENT") BEFORE DOWNLOADING MATERIALS FROM THIS SITE. BY DOWNLOADING ANY MATERIALS FROM THIS SITE, YOU ARE AGREEING TO THESE TERMS.

You are downloading software code ("Code") which will become part of a product ("Software") you currently have licensed from SAS Institute Inc. or one of its subsidiaries ("the Institute"). this Code is designed to either correct an error in the Software or to add functionality to the Software. The code is governed by the same agreement which governs the Software. If you do not have an existing agreement with the Institute governing the Software, you may not download the Code.

SAS and all other SAS Institute Inc. product or service names are registered trademarks or trademarks of SAS Institute Inc. in the USA and other countries. ® indicates USA registration. Other brand and product names are registered tradema rks or trademarks of their respective companies.


Copyright (c) 2002 SAS Institute Inc. All Rights Reserved.
Terms of Use & Legal Information | Privacy Statement