95% limit of agreement

[Luke01]

Hi community,

I cant seem to find the best command to generate a 95% level of agreement for a bland-altman plot.

I originally calculated by for example in general terms: lower 95% limit of agreement = mean difference - (1.96*std difference)

And vice versa for the upper limit.

This has got me what I needed BUT what is the best command for SAS to generate this? As i would rather not do it by hand and generate opportunities for error.

[Jagadishkatam]

Please refer to the below paper pages 8 and 9 explained the code

https://www.sas.com/content/dam/SAS/support/en/sas-global-forum-proceedings/2018/1815-2018.pdf

[Luke01]

I did see this, but again they just use lldiffm1m22=mdiffm1m2-(2*sddiffm1m2) rather then 1.96, so unfortunately that ref does not clarify