A random effects model is a statistical model in which effects associated with sampled groups or units are random variables. In a random-intercept model,
 |
the group effects 
have expectation value 0 and variance 
. Observations in the same group
are correlated because they share the same random effect.
The variance 
is a variance component. A model can contain
both fixed effects and random effects. Whether an effect is treated as fixed or random
depends on the sampling scheme and inferential goal, not merely on the symbols used
in the model.
