Lecture 3 Flashcards
What is the experimental method?
One (or more) variables is manipulated to determine if it influences other variables
What makes it so we can determine cause and effect?
Manipulation
What are the steps of doing an experiment?
1) Manipulate one or more variables
2) Measure the effect on other variables
3) control extraneous factors
What is the control group?
The baseline level of the Iv-receives no treatment
What is a between-subjects design?
Different groups of participants are assigned to each “level” of the IV.
What is a within-subjects design?
Each participant is exposed to all levels of the IV
What is a problem with between-subjects designs?
Need to ensure groups are equivalent
What is the solution to the problem with between-subjects designs?
Random assignment-each participant has an equal change to be in either group. Balances differences.
Why is random assignment better than matching?
Because with random assignment, people will be roughly evenly split (even variables not considered will be roughly evenly split)
What are some problems with a within-group design?
Sometimes the order of the conditions can make a difference
What is the practice effect?
The person getting better at a task overtime
What is a solution to the problem with within-group designs?
Counter-balancing- order of conditions is varied between people-random assignment to vary the orders
What does multiple IV’s allow for you to do?
See an interaction
What are inferential statistics?
Allows us to determine whether differences between groups are “real” and “big enough”
What is statistical significance?
The result that would happen by chance in less than 5 in 100 experiments
What are the 4 key concepts in psych testing?
1) Reliability
2) Validity
3) Sampling
4) Standardization
What is reliability?
How consistent a measurment is
What is validity?
How well a test measures what it’s supposed to measure
What is sampling?
The procedures used to choose who takes the test and how well this matches our goal for generalizing
What is standardization?
Define controlled testing procedures and developing norms
What is test-retest reliability?
Are scores stable overtime?
What is inter-judge reliability?
Would different people agree on the same scores for the same test?
What is internal consistecy?
Do all different types of questions measure the same things (ex: Word problems don’t correlate as strongly with other math questions)
What is construct validity?
Does the test measure the thing that it’s supposed to measure? (ex: IQ- might anything other than intelligence affect scores? Some are more about trivia knowledge)