Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
9 Cards in this Set
- Front
- Back
|
Classic Design
O X O O O |
A pretest is given to both the experimental group and the control group. After the test the independent variable is administered only to the experimental group then followed by a post test from both groups. |
|
|
Post test Design
X O O |
This design eliminates the threat of the pretest affecting the results. The independent variable is applied to the experimental group only then the post test is given to both control and experimental groups. |
|
|
Solomon 4 Goup
O X O O O X O O |
This Design accounts for both classic design and post test design. There are 4 groups total, 2 experimental and 2 control groups. One experimental group and one control group gets a pretest. Then the independent variable is given to both experimental groups. All groups are given a post test. |
|
|
Non Equivalent Control Group
O X O O O |
A comparison group is selected to be as comparable as possible to the treatment group. One way is individual matching, this is matching individuals with similar cases or aggregate matching, which is matching individuals by similar identifiers such as age and sex. This design follows the classic design without following the rules of causality. It also allows you to determine whether an association exists between the presumed cause and effect. |
|
|
Before and After Design
O X O O X O O X O
|
There is no comparison group in this design. All cases are exposed to pretest, treatment, and post test. Later a comparison between pretest and post test is done. If there are multiple groups then this design is called Multiple group before and after. |
|
|
Time Series Design
OOO X OOO |
In this design, there is a one group trend study. There are 3 pretests, the independent variable is given, then 3 post tests are given. The reduces the impact of statistical regression. |
|
|
Quasi designs are relevant because? |
They provide generalizability |
|
|
How does internal validity reduce threats? |
By randomly assigning 2 comparable groups you establish that the independent variable was responsible for the change in the dependent variable. By randomly assigning both groups you are also controlling any threats to the validity. Any extraneous variables would affect both control and experimental groups evenly since the groups are randomly assigned therefore the outcome would be the same |
|
|
Which designs are the best? |
The true experimental designs are best because they have the highest internal validity. |
