Page 1 of 1

2-level multilevel model issues

Posted: Thu Aug 01, 2019 2:48 pm
by vortexxx
I am a beginner with MLwin and I am using version 3.04.

When I fit a 2-level model, it says "explanatory variables are different lengths (offset 2)". When I looked it up online, I learned that the n of all my variables should be the same. Then I saw that the issue stemmed from a new variable generated by the system. This variable is called "cons", with the value of "1" for only one participant. Hence the n of cons is 1.

I then tried to start from the beginning and attempted the practice on LEMMA. I started from the chapter 5.1 Comparing groups using multilevel modelling. Using the data for MLwin practice 5.1, I got the same issues:
question.png (17.17 KiB) Viewed 3871 times
I received the same error message and saw that a cons with n = 1 was created.
Also, seems like not all cases were in use (1 of 33988 cases in use, and for the level 2 variable, schooolid, only 1 of 508 was in use.

I think I am missing something very basic. Can anyone kindly offer any advice?

Thank you!