Quiz 4 Flashcards
(27 cards)
What is the goal of experimental research? What does it allow us to say about our results?
- to find a cause-and-effect relationship between two variables
- control allows us to eliminate alternative explanations for the results
Independent and Dependent Variables
- IV is the variable that is manipulated by the researcher by creating a set of treatment conditions
- DV is the variable that is observed/measured for changes to assess the effects of manipulating the IV
What are levels of an Independent Variable?
n
What is an Extraneous Variable?
all other variables in the study other than the IVs and DVs
Third Variable Problem
•when two variables are related there is no guarantee that there is a direct (causal) relationship bc a third (unidentified) variable may be truly responsible for the observed relationship
-ex. there is a correlation b/t ice-cream consumption and crime rate and the third variable is temperature
Directionality Problem
•results may show a relationship between two variables
-does not always explain the direction of the relationship
-which variable is the cause and which is the effect?
1. The “cause” must happen before the “effect” occurs
•value of the IV is followed by a change in the DV
2. Must show that one specific variable is responsible for changes in another variable
•must rule out the possibility that differences are caused by extraneous variables
Why do we manipulate an independent variable?
to determine the direction of the relationship and control for third variables (experimental control)
Confounding Variables. What are they and why do we need to prevent them?
- Extraneous variable is a confound only if it influences the DV
•if totally unrelated to the DV, is not a threat
•previous example: crime rate is not related to ice cream consumption - Confounding variable must vary systematically with the IV
•if variable changes randomly, with no relation to the IV, is not a threat
•previous example: crime rate does vary systematically with changes in temperature
Methods to prevent a Confound (randomization, matching, holding constant). What are each and what are the advantages/disadvantages of each?
n
What are the benefits of randomly assigning participants to treatment conditions
n
Control Groups. What are they and why do we use them?
n
Between-Subjects and Within-Subjects Designs. What are they and how do they differ? How many scores do we record for participants in each type?
n
Advantages of a Between-Subjects Designs.
n
Why do we need to worry about individual differences for participants in Between-Subjects designs?
n
Between-Treatments and Within-Treatments Variance. For a Between-Subjects Design what do we want for each?
n
Compensatory Equalization
n
Differential Attrition
n
What statistical analysis do we use for a single-factor two-group design?
n
What statistical analysis do we use for a single-factor multiple-group design?
n
Primary limitation of a two-group design?
n
Threats to internal validity for within-subjects design (History, Maturation, Instrumentation, Regression Toward the Mean, Order Effects). What influence does practice, fatigue, and carry-over effects play?
n
Participant Attrition
n
If we are trying to prevent threats to internal validity, how does it help to increase the time between treatments for a within-subjects experiment? When might we want to switch to a between-subjects design?
n
Counterbalancing. What is the point of it? What does it do to the threats to internal validity?
n
