Hi,
I have 2 variables with the same 5 level ordinal rating of suicidality.
I have the variable derived from a survey of visitors to a psychiatric
emergency clinic and another variable derived from the psychiatrist's
clinical note after they evaluated the study participant. I know that
the survey results and the psychiatrist's notes are not independent
since they are rating the same entity-the study participant.
I am using a combination of methods to examine agreement including:
looking at the crosstabs for patterns, calculating proportion of
agreement, ICC, and McNemar.
I understand that modeling (specifically conditional logistic
regression) can be used and thus potential confounders can be examined.
I don't understand what would actually be entered into a conditional LR
model?
Here is an example of a crosstabs for the total sample (n=377)
Participant rating MD rating
No SI Passive SI Active SI
Plan Plan prep
No SI 177 50 21
31 18
Passive SI 1 6 3
9 2
Active SI 0 1 9
11 5
Plan 0 0
0 9 9
Plan prep 0 0 1
2 12
Thanks for any help,
Jan
=====================
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
