A design where each participant is measured under all a> 2 treatment conditions, with treatments presented in random order
within-subjects factor
The independent variable in a within-subjects experiment
carryover effect
occurs when the effect of one treatment persistsduring exposure to a second treatment
derived score
where a = the number of levels and number of scores that participant i has.
mixed two-factor design (split plot design)
a design which has one between-subjects factor and one within-subjects factor
repeated factor
a factor in which participants are measured on two or more occasions
compound symmetry assumption
assumes that the population variances of the dependent variables are equal across the levels of the within-subjectsfactor(s) and that the population covariances between each pair of within-subjectmeasurements are equal for all pairs
quasi-experimental design
include two or more treatment conditions but do not involve random assignment of participants to treatment conditions
nonequivalent pretest-posttest design
a sample of participants will self-select into, or will be nonrandomly assigned to, two different groups. All participants are measured on the dependent variable prior to receiving treatment. One group receives treatment 1 and the other group receives treatment 2. All participants are measured on the dependent variable at a later point in time.
history effect
when one group is exposed to certain events that occurred between the pretest and posttest in addition to the specified treatment and this poses a threat to the internal validity of the study
regression towards the mean
the tendency of extreme scoring participants' scores to fall closer to the mean when measured again
differential maturation
occurs in studies where, in the absence of any treatment effect, the type of participant in one group will mature or naturally change over time, at a different rate than the type of participant in the other group