b or beta in GEE?

[Sytske]

Dear all,

Does SPSS give a B or beta in the output with GEE?

I am confused as to whether SPSS gives a b or a beta in the output for GEE. It is called B, so you
would think it is a B. But GEE also has the option to show the odds ratio, listed as the exponential of B
exp(B). However, I always thought that the odds ratio was the exponential of beta, since the odds
ratio is a standardized value, just as beta is. So, my second question is: is the odds ratio exp(B) or
exp(beta)?

I have been looking in many different places and find contradictory answers, so I hope someone can
help me!

Thank you in advance for your replies!

Sytske

=====================
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

[Bruce Weaver]

GENLIN output gives you the unstandardized coefficient (B), and in a logit model,  Exp(B) = OR.

Sytske wrote

Dear all,

Does SPSS give a B or beta in the output with GEE?

I am confused as to whether SPSS gives a b or a beta in the output for GEE. It is called B, so you
would think it is a B. But GEE also has the option to show the odds ratio, listed as the exponential of B
exp(B). However, I always thought that the odds ratio was the exponential of beta, since the odds
ratio is a standardized value, just as beta is. So, my second question is: is the odds ratio exp(B) or
exp(beta)?

I have been looking in many different places and find contradictory answers, so I hope someone can
help me!

Thank you in advance for your replies!

Sytske

=====================
To manage your subscription to SPSSX-L, send a message to
[e-mail] (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