1
$\begingroup$

I conducted an experiment in which students rated sentences and I would like to fit a mixed effects model using lme4. My response variable is RATING (i.e. the judgements given by the students), the two predictors (SENTENCE_TYPE (3 levels) and WORD_ORDER (2 levels)) are categorical variables. In addition, I would like to fit random intercepts for SUBJECT and VERB to account for idiosyncratic preferences of individual students and lexical effects of individual verbs. However, as shown in the following example, the variable VERB only applies to two levels of SENTENCE_TYPE and cannot be coded for tokens that belong to the third level (level C in the following example). enter image description here

Is it nevertheless possible to include VERB as a random effect and to get reliable estimates for the intercept adjustments?

Improve this question
$\endgroup$
4
  • $\begingroup$ How many subjects and how many verbs do you have? $\endgroup$
    – Shawn Hemelstrand
    Commented Jun 20, 2023 at 7:49
  • $\begingroup$ I have 240 subjects and 24 verbs. In total, each student rated 36 sentences. $\endgroup$
    – max22
    Commented Jun 20, 2023 at 8:32
  • $\begingroup$ That seems usable then. What does the statement "However, the variable VERB only applies to two levels of SENTENCE_TYPE and cannot be coded for tokens that belong to the third level" mean? $\endgroup$
    – Shawn Hemelstrand
    Commented Jun 20, 2023 at 8:57
  • $\begingroup$ I edited the questions and added an example. As you can see, VERB is not coded for the C level of SENTENCE_TYPE. $\endgroup$
    – max22
    Commented Jun 20, 2023 at 11:56

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.