Research Design Flashcards
Types of research design and their notation.
One-shot case study
One group is studied one time, after some type of treatment. The notation is X O
One-group pre-test/post-test design
you have a single group, you test them for some level of functioning (pretest), you give some type of treatment and then you test them again on the same type of functioning (post test). Stanley and Campbell note that this type of research is widely used, but suffers from many different threats to validity. O X O
The static group comparison
This is where one group is compared against another group, but they are not randomized and there is no pretest, it is just a post test.
Pretest / post-test control group design
This is simply the same design as #2, but you add in a control group
Post-test only control group design
This is essentially design one with a control group and randomization
the non-equivalent control group design
In this design, both groups are given a pre-test and a post-test, but the two groups are not randomized(non-equivalent).
The separate sample pre-test/post-test design
For large populations, such as cities, factories, schools, and military units, it may often happen that although one cannot randomly segregate subgroups for differential experimental treatments, one can exercise something like full experimental control over the when and to whom of the O
Design 12
The separate sample pre-test/post-test control group (Design 13)
The same thing as the seperate sample pre-test/post-test but with the addition of a control group.
It is expected that Design 12 will be used in those settings in which the X, if presented at all, must be presented to the group as a whole. If there are comparable (if not equivalent) groups from which X can be withheld, then a control group can be added to Design 12, creating Design 13
The recurrent institutional cycle design (Design 15)
Air Force Academy Example
Done when there are institutional patterns that allow for systematic evaluation (ie cohorts in school). Is basically a mash up of two other designs, static group and single group pretest/posttest.
One group is studied one time, after some type of treatment. The notation is X O
One-shot case study
you have a single group, you test them for some level of functioning (pretest), you give some type of treatment and then you test them again on the same type of functioning (post test). Stanley and Campbell note that this type of research is widely used, but suffers from many different threats to validity. O X O
One-group pre-test/post-test design
This is where one group is compared against another group, but they are not randomized and there is no pretest, it is just a post test.
The static group comparison
This is simply the same design as #2, but you add in a control group
Pretest / post-test control group design
This is essentially design one with a control group and randomization
Post-test only control group design
In this design, both groups are given a pre-test and a post-test, but the two groups are not randomized(non-equivalent).
the non-equivalent control group design
For large populations, such as cities, factories, schools, and military units, it may often happen that although one cannot randomly segregate subgroups for differential experimental treatments, one can exercise something like full experimental control over the when and to whom of the O
The separate sample pre-test/post-test design
It is expected that Design 12 will be used in those settings in which the X, if presented at all, must be presented to the group as a whole. If there are comparable (if not equivalent) groups from which X can be withheld, then a control group can be added to Design 12, creating Design 13
The separate sample pre-test/post-test control group
Air Force Academy Example
The recurrent institutional cycle design