Hi:
Just in case anyone is interested (some months ago someone at the list
asked for it, but I was too busy/lazy? then to modify them) I have
modified my Bland&Altman limits of agreement macro (BALOA 2.0), and also
added a new one that computes LOA with repeated data (BALOAREP), as
described in their papers:
- The 1986 Lancet paper:
http://www-users.york.ac.uk/~mb55/meas/ba.htm(it can be downloaded from that link)
- Bland JM, Altman DG. Measuring agreement in method comparison studies.
Statistical Methods in Medical Research 1999; 8: 135-160 (not free,
needs subscription)
I haven't updated the web page yet (long story:since my husband meddled
in the affair I can't modify it without his help, my HTML knowledge is
close to 0, and used word to write while he used frontpage), and the
link to the new macro can't be found in it, so here it goes:
http://gjyp.nl/marta/BALOAREP.SPSWhat's new in BALOA:
- It now computes 95% confidence intervals for the bias and the limits
of agreement (following formulas from Bland&Altman 1999)
- It automatically checks the assumptions (error not proportional to the
mean and approximate normality of differences)
- Some problems with the graph have been corrected (LOA not always
showing, for instance)
HTH,
Marta García-Granero
--
For miscellaneous statistical stuff, visit:
http://gjyp.nl/marta/=====================
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
