Dear SPSSX-L
I wondered if someone could let me know if there is a simple solution to my problem.
I am running a two level-linear model in SPSS version 20. Using the MIXED and GEMLIN mixed options I get two slightly different answers. Same estimates, different p-values. It appears this is due to differing methods of calculating the
degrees of freedom. I am able to change the default setting in GENLINMIXED but I can’t see how to do it in MIXED syntax. Does anyone know if it can be done?
Thanks
Becky
Dr Rebecca Playle
Head of Statistics
South East Wales Trials Unit
Cardiff University School of Medicine
Neuadd Meirionnydd
Heath Park, Cardiff
Senior Lecturer in Medical Statistics
Cardiff University School of Dentistry
Heath Park, Cardiff, CF14 4XN
Please note my days of work are Monday / Tuesday (Dental) and Thursday / Friday (SEWTU)
[hidden email]
Tel 02920 744821 (mon/tues)
Tel 02920 687516 (thur/fri)
=====================
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
