Provide details on the problem: number of cases and variables, variable types (continuous, dichotomous, >2 categorys. Do any variables have 'problem distributions', such as extreme skew or kurtosis, low cell frequencies?
It seems that you've ran the problem multiple times and have gotten different error messages. Is this true? Is what you have reported the full text of the error message? If not, post the full text(s) of the message(s). Other people may well need these details to make useful suggestions.
Gene Maguin
-----Original Message-----
From: SPSSX(r) Discussion [mailto:
[hidden email]] On Behalf Of marlies
Sent: Tuesday, May 21, 2013 4:13 AM
To:
[hidden email]
Subject: computational error during multiple imputation
LS,
I´m trying to run a multiple imputation. It starts, but after a few minutes it gives or:
- communication with the SPSS processor is stopped, sorry for the inconvenience, or:
- the model cannot be build because a computational error has occurred during the estimation. Not output will be displayed.
Last year the multiple imputation worked, with a very comparable syntax, but in SPSS 18 instead of 20 or 21 (I tried both).
What can I do now to fix the problem?
Thank you.
Marlies
--
View this message in context:
http://spssx-discussion.1045642.n5.nabble.com/computational-error-during-multiple-imputation-tp5720339.htmlSent from the SPSSX Discussion mailing list archive at Nabble.com.
=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD
=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Locked
