Strategies in random assignment Flashcards
What is the purpose of random assignment?
- randomisation is one way of controlling for confounds
- random variation: variations in people that aren’t of interest to the experiment
What is random assignment?
- placing subjects in different treatment and control groups for purpose of equivalence
- designed to level the playing field
- gives confidence in experiment
What is selection bias?
when the subjects of the study do not accurately reflect the population to whom the results of the study will be applied
How can random assignment reduce confounds?
- accounts for unexpected confounds
- can eliminate need for pre-tests that can threaten validity
What does random mean?
- Every subject must have an equal chance of being assigned to treatment or control groups
- True randomisation means neither researcher nor subject has any say in group they’re assigned
What is blind assignment?
subjects not knowing their assigned group and reason they were assigned
What are 4 threats to internal validity?
- diffusion of treatment
- compensatory equalisation
- compensatory rivalry
- resentful demoralisation
What is diffusion of treatment?
Communication between subjects belonging to different groups
What is compensatory equalisation?
Those providing the treatment attempt to give some of the advantages to the group group or vice-versa
What is compensatory rivalry?
when members of the control group try to gain some of the benefits of the treatment group or vice-versa
What is resentful demoralisation?
Control group subjects underperforming because they resent being denied the treatment or vice-versa
How are survey experiments randomised?
- managed, distributed and conducted online with tools like Qualtrics and SurveyMonkey
- Can be problematic for internal validity given that subjects online can be surrounded by potential confounds
