Commonlyidentified as the effects due to variables representing experimentalmanipulations (i.e., differences in outcomes under different experimentalconditions) or to variables representing stimulus, participant or higher-levelsampling unit attributes (i.e., differences in outcomes correlated with differentvalues of some attributes). In practice, the distinction between random effectsand fixed effects is difficult to motivate consistently (Gelman & Hill,2007).
Gelman, A.,& Hill, J. (2007). Data analysis usingregression and multilevel/hierarchical models. New York, NY: CambridgeUniversity Press.
See Crossed random effects, Random effects