Ch 8: Quasi-Experimental research designs

Question 1

What is a quasi-experimental design?

Answer 1

A quasi-experimental design is one in which the researchers have only partial control over an independent variable. One or more of the variables cannot be randomly assigned.

^{<u>Example:</u> Gender, smoking, and depressin are all things that cannot be randomly assigned}

Question 2

What is a person-by-treatment quasi-experiment?

Answer 2

A person-by-treatment quasi-experiment is a design in which the researcher measures at least one independent variable and manipulated at least one other independent variable.

^{Example: A researcher finds people that are either depressed or non-depressed (measured variable) and for the study puts them in either a positive or negative mood (manipulated variable).}

Question 3

What is prescreening?

Answer 3

Prescreening is often done before the laboratory study in order to measure a large group of people on an individual-difference dimension (or attitude)

Question 4

What is the difference between extreme groups and median split?

Answer 4

1. Extreme groups is when you take only the highest and lowest groups of people on a scale and throw out the middle
2. Median split is when you take only the ones in the middle and throw out the extremes.

Question 5

What are natural experiments?

Answer 5

Natural experiments involve naturally occoring “manipulations.” These often random life events were caused by facotrs that had nothing to do with the people who experienced them.

^{<u>Example:</u> Someone having their house destroyed by a natural disaster.}

Question 6

What is a nature-by-treatment study?

Answer 6

A nature-by-treatment study is one that combines natural events with laboratory manipulations, or that assesses individual differences among people and then waits for them to experience truly arbitrary natural events.

Question 7

What is a patched-up design?

Answer 7

A patched-up design occurs when a researcher adds new conditions to a study to help establish the side of a quasi-experimental effect, to test for the influence of conceivable confounds, or both.

Question 8

What are some of the threats to internal validity in designs that study one group before and after the quasi-independent variable?

Answer 8

1. History
2. Maturation
3. Regression to the mean
4. Pretest sensitization - Because they have taken the rpetest, the subjects may be more sensitive to the treatment. Had they not taken a pretest, the treatment would not have worked.