Missing values error without missings in the data?
Posted on
nastjuscha
Joined: 06/28/2016
Forums
Dear Mike,
I'm afraid I have to ask you for help again.
I receive a following new error warning every time I try to run an FEM regardless of the constellation of variables from my dataset:
> summary(fixed1)
Error in if (pchisq(chi.squared, df = df, ncp = 0) >= upper) { :
missing value where TRUE/FALSE needed
Even if I try to run it only with first three variables (there are 146 full matrices without any missings) I have the same problem.
I appreciate any idea you can provide.
Regards,
Nastja
Dear Nastja, The issue is
Dear Nastja,
The issue is that the lengths of dt and nDT are different (146 vs. 147). tssem1() fails to detect it in this case. I have fixed it in the developmental version in github. It will throw an error. When I drop the last element in nDT, it works fine.
By the way, the fixed-effects model takes a long time to run as there are 146 groups. Moreover, there is a large degree of heterogeneity on the correlation matrices. The random-effects model seems to be better. It only takes a few seconds to run.
Best,
Mike
Log in or register to post comments
In reply to Dear Nastja, The issue is by Mike Cheung
Hi Mike, such a silly
Hi Mike,
such a silly mistake! Thank you very much!
Regards,
Nastja
Log in or register to post comments