quantitative- quasi experimental designs Flashcards
Definition of quasi-experimental design
Quasi-experimental designs are those in which participants cannot be randomly assigned to conditions
Or
A quasi-experiment exists whenever causal conclusions cannot be drawn because there is less than complete control over the variables in the study
Threats to internal validity
all third variables -in a quasi experiment you can't randomly assign which means you are especially vulnerable to: history maturation selection bias regression to the mean
so you match
What are the advantages of quasi-design?
-increased external validity because you are working with real-world conditions
2 types of quasi design
- nonequivalent control group designs
2. interrupted times series design
Nonequivalent control group deign
purpose: evaluate effectiveness of a treatment programme
Experimental group: observation 1 -> treatment -> observation 2
control group:
observation 1 -> observation 2
best outcome for treatment effectiveness
the control group stays level and the experimental group improves
how to rule out regression to the mean
if the line of the experimental group is heading to the control group line then it could be regression but if it is moving away then it is not regression
Interrupted time series design
Observation 1, O2, O3, O4, Treatment, O5, O6, O7, O8
iatrogenic
when the treatment causes the problem