Flashcards in KL Ch. 19 Inadequate Designs and Design Criteria Deck (13)
What is the defining feature of Experimental Design?
The investigator manipulates at least one independent variable.
What is the defining feature of Non-experimental Research?
One cannot manipulate variables or assign participants or treatment at random because the nature of the variable is such that it precludes manipulation.
How do Experimental and non-experimental designs differ?
What is the main reason for the preeminence of the controlled experiment?
Researchers can have more confidence that relations they study are the relations they think they are.
One Group: (One Shot Case Study) maps
a) X Y (experimental)
b) (X) Y (non-experimental)
Limitations of One Group: (One Shot Case Study)
- In above study there is no control
- The variables could be confounded, and when two or more variables cannot be separated, the results are difficult to interpret.
- The minimum useful scientific information requires one formal comparison.
One Group, Before-After (Pretest, Posttest) maps
a) Yb X Ya (experimental)
b) Yb (X) Ya (non-experimental)
One Group, Before-After (Pretest, Posttest) characteristics
- The group is compared to itself
- The variables are confounded
What are Measurement, History, Maturation effects?
- Measuring participants changes them (reactive measure)
- Tests such as memory, are reactive because it changes subjects memory on topic covered by test.
- History and maturation – The longer the period of time, the greater the chance of extraneous variables affecting the participants and Ya measure.
When does the regression effect operate?
Whenever there is time between pre and post tests
One can account for regression effects with...
What is Variable Representation?
Are the variables of the research representative?
--i.e. is anxiety induced by verbal instruction the same as anxiety induced by electric shock?