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;
26 Cards in this Set
- Front
- Back
David Hume
|
- "Principle of Association"
- human habit of causal inference |
|
Oskar Pfungst
|
- Hero of "Clever Hans" horse story
- Showed correlation does NOT imply causation |
|
Goals of Scientific Method
|
- describe (phenomenon)
- explain (what's happening, mechanism) - predict (go beyond given) - control (intervene, better outcomes) |
|
Data Collection Methods
|
- self-report
- observation |
|
Research Settings
|
- lab
- field |
|
Descriptive Research Design
|
- case study
- survey - naturalistic observation |
|
Correlational Research Design
|
- positive relationship
- negative relationship - no relationship - correlation does NOT imply causation |
|
Operationalization
|
manipulate the IV
|
|
Independent Variable
|
(IV) what is changed in experimental research, what you manipulate in the experiment
|
|
Dependent Variable
|
(DV) what depends on the IV, the outcome from the experiment, what you observe
|
|
Control of Extraneous Factors, Randomization
|
necessary for experimental research
|
|
Sample Representativeness
|
adequate #? appropriate? assesses theoretical framework? adequate procedures?
*critiquing a study* |
|
reliability
|
consistent?
*critiquing a study* |
|
validity
|
tests what it is supposed to measure?
*critiquing a study* |
|
central tendency
|
??
|
|
mode
|
most common
|
|
median
|
middle point
|
|
mean
|
arithmetic mean, average
|
|
range
|
highest-lowest #s
|
|
variability
|
(stdev) average distance from mean
|
|
normal curve
|
when the mean - mode
|
|
null hypothesis
|
- H0
- means are from the same curve - differences are due to chance |
|
alternative hypothesis
|
- H1
- means are from different curves - differences are significant |
|
p value
|
- probability that H0 is true, data comes from the same population
- when p< .05, reject H0, accept H1 |
|
Inferential Statistics
|
necessary because nothing is ever 100% testable, one must always go beyond the given data
|
|
When Critiquing a Study:
|
- don't announce hypothesis to subjects
- large sample # - exactly same environment - examine the data / conclusions - consider meaningfulness of study - evaluate ethics of study |