View
- Term
- Definition
- Both Sides
Study
- All (48)
Shortcut Show
Next
Prev
Flip
PSYC 204: EXAM 1
methods of acquiring knowledge |
science
tenacity (superstitions)
common sense
intuition
mysticism (altered state of consciousness)
authority
|
science is based on a set of assumptions which are |
realism
rationality
regularity
causality or determination
discoverability |
realism |
objects exist outside of the mind |
rationality |
reasoning and logic are the basis for solving problems |
regularity |
phenomena exists in recurring patterns |
causality or determination |
all events happen because of preceding events |
discoverability |
it is possible to learn solutions to questions, our only limitations are time and resources |
characteristics of scientific approach |
control
operational definition
empirical
objective
replication
self-correcting
progressive
tentative
parsimonious
concerned with theory |
validity |
appropriateness of inferences drawn from data |
research validity types |
internal
external
statistical conclusion
construct |
test and measurement validity types |
criterion-related
content-related
construct-related |
research validity |
conclusion based on a research study is valid when it corresponds to the actual or true state of the world |
internal validity |
we can infer that a relationship between two variables is causal or that the absence of a relationship implies absence of cause |
extraneous variable |
any variable other than the IV that influences the DV |
confounding |
an extraneous variable that systematically varies with the IV |
threats to internal validity |
history
maturation
testing
attrition or mortality
selection
regression effects |
how to correct for threats to internal validity |
random assignment |
external validity |
causal relationships can be generalized to the general population |
threats to external validity |
population validity (other participants)
ecological validity (other settings)
temporal validity (other times) |
how to correct threats to external validity
|
random sampling |
statistical conclusion validity |
appropriateness of inferences made from data. Are IV and DV statistically related? |
threats to statistical conclusion validity |
low statistical power
violated assumptions of statistical tests
reliability of measures' scores |
construct validity |
correct labeling. Do our results support the theory underlying the research |
threats to construct validity |
loose connection between theory and study
changes in research participants' behaviors that result from their tendency to alter their behavior because they are being studied |
how to correct threats to construct validity |
double-blind procedures
single-blind procedures
deception |
ex of artificial discrete variable |
young/old |
ex of natural discrete variable |
male/female |
list of worst to best ways to create artificial discrete variables |
mean split
median split
extreme groups |
pearson's correlation |
both variables are continuous |
point-biserial |
one variable is true dichotomy, cannot assume normal distribution |
biserial |
one variable is artificial dichotomy, we can assume normal distribution |
phi coefficient |
both variables are dichotomies |
categorical variable |
qualitative |
labels |
the use of numbers that cannot be mathematically analyzed (ex. UIN) |
nominal scale |
grouping objects and giving them a number (men 1, women 2) |
ordinal scale |
ordered from most to least (ex. top five contestants) |
interval scale |
most common
tells how far apart objects are from one another but not the absolute magnitude
(1=do not like, 5=really like) |
ratio scale |
preceding 4 levels of measurement in addition to a true zero (ex. speed) |
correlation coefficients are a characteristic of |
reliability |
correlation coefficient range |
-1 to +1 |
criterion-related validity |
effectiveness of a test in predicting an individual's behavior in specific situations
|
concurrent
predictive
postdictive |
criterion-related validity |
content-related validity |
the degree to which a predictor convers a representative sample of the behavior being assessed
|
construct-related validity |
extent to which the test may be said to measure theoretical construct or trait |
convergent validity |
construct-related validity
different measures of the same construct should be correlated to each other |
discriminant validity |
construct-related validity
different constructs should not be correlated to each other
|
multi-trait/multi-method matrix |
most common approach to assessing the construct-related validity |
a test's scores cannot be |
valid but not reliable |