Exercise

# Analyzing and interpreting the school data

What predicts a student's increase in math skills (`mathgain`

)? Does student's `sex`

, teacher's preparation, `mathprep`

, or teacher's knowledge, `mathknow`

? Also, students learn within classrooms, `classid`

, and schools, `schoolid`

.

With this model, coefficients have 3 outcomes:

- If it is positive and significantly different from zero, the variable predicts an increase in students' math gain.
- If it is negative and significantly different from zero, the variable predicts a decrease in students' math gain.
- If it is not significantly different than zero, the variable likely does not predict a change.

The DataCamp course, Foundations of Inference, covers models interpretation in greater detail.

Instructions 1/2

**undefined XP**

- Build a
`lmer()`

predicting`mathgain`

with`sex`

,`mathprep`

, and`mathknow`

as fixed-effects and`classid`

and`schoolid`

as random-effects using the data.frame`studentData`

. Make sure you use the variables in this order to pass DataCamp's correctness test. - Look at the
`summary()`

outputs of the model.