BookmarkSubscribeRSS Feed
Quartz | Level 8

I have 4 different ways of measuring a continuous "normally enough" distributed variable, all of which are compared to a gold standard.


These are repeated 5 times in the same individuals.

Have calculated the differences between them, but two of these ways of measuring the value have some missing ness (54 values measured compared to 90).


Is proc genmod with a REPEATED statement appropriate to account for the repeated measures ?

Is the link function "identity=link"?

What correlation structure should be chosen? 

I have a basic understanding of the types of correlation matrixes that are available.


Initially I planned on just comparing the actual measures, but since we are comparing ways of measuring, the precision of these are possible bias, then I'm assuming that the analyses should be done on the differences  compared to the gold standard rather than the actual values.


Don't miss out on SAS Innovate - Register now for the FREE Livestream!

Can't make it to Vegas? No problem! Watch our general sessions LIVE or on-demand starting April 17th. Hear from SAS execs, best-selling author Adam Grant, Hot Ones host Sean Evans, top tech journalist Kara Swisher, AI expert Cassie Kozyrkov, and the mind-blowing dance crew iLuminate! Plus, get access to over 20 breakout sessions.


Register now!

What is ANOVA?

ANOVA, or Analysis Of Variance, is used to compare the averages or means of two or more populations to better understand how they differ. Watch this tutorial for more.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 0 replies
  • 1 in conversation