Glossary of Psych 303

Start Studying! Add Cards ↓

Created by chmchan

Deck Info



Recent Users

epistemology in psychological science
epistemology: the way of knowing
1. observation
2. logic
3. intuition
4. authority

4 canons of science
1. determinism
2. empiricism
3. parsimony
4. testability

- the universe is orderly, mechanistic, and understandable
- event are caused
- explain causal relationships with laws and theories

- making obv of the world

- simplicity
- preference for simple explanations for phenomenons
- any notion must be testable
- the notion must be falsifiable as well

1. situational variables
2. response variables
3. participant variables
4. mediating variables

concrete definition that can be used to measure abstract ideas
i.e. stress measured by number of nightmare episodes
Independent variable
manipulated variable
dependent variable
measured variable
response variable
internal validity
extent to which research findings provide compelling evidence for causality
high internal validity
temporal sequence
eliminations of confounds

external validity
extent to which research findings can generalize to other samples, situations, and settings
high external validity
findings would hold truth across samples, situations, and /or settings
potential problems for experiments
can't manipulate IV
artificiality of the controlled situation (low external validity)
correlational studies
variables are measures, not manipulated
eg surveys
naturalistic - high external vaidity

potential problems for correlational studies
different results depending on subtle differences
need larger sample to have sig effect
can't est. causality (low internal validity)

construct validity
are the measures measuring what the study claims to measure?
conclusion validity
do the results support the claim?
consistency or stability of a measure
test-retest reliability
consistency over time
interrater reliability
extent to which two or more raters agree in their ratings
face validity
are the measures appear to measure what they are supposed to measure?
content validity
the measure spans the universe of content defining a construct
criterion-related validity
predictive validity
concurrent validity
convergent validity
discriminant validity

predictive validity
use the measures to predict the future
concurrent validity
use the measures to differentiate known groups
convergent validity
correlate the measures with different operationalizations of the same construct
- measures used to measure SHOULD correlate
divergent validity
showing that a measure is not related to measures with which it should NOT be
reliability and validity
Can be reliable and not valid, but NOT vice versa (ie not reliable but valid)
levels of measurement

categories with no values
eg gender, race political party

categories for which values communicate only order
numeric values are meaningful, but not the ratio; no fixed 0
eg SAT starts from 200

with true 0 pt
ratios are meaninful
eg reaction time

Add Cards

You must Login or Register to add cards