- Shuffle
Toggle OnToggle Off
- Alphabetize
Toggle OnToggle Off
- Front First
Toggle OnToggle Off
- Both Sides
Toggle OnToggle Off
Front
How to study your flashcards.
Right/Left arrow keys: Navigate between flashcards.right arrow keyleft arrow key
Up/Down arrow keys: Flip the card between the front and back.down keyup key
H key: Show hint (3rd side).h key
PLAY BUTTON
PLAY BUTTON
41 Cards in this Set
- Front
- Back
|
why does correlation not equal causation?
|
experimenter does not have control over variables (no internal validity)
|
|
types of correlations
|
pearson- 2 continuous
point biserial- 1 continuous & 1 dichotomous phi- 2 dichotomous spearman rho- 2 rank |
|
coefficient of determination
|
shared variance (r squared)
|
|
2 characteristic of psychological test
|
standardized and objective
|
|
3 types of tests
|
speed, power, mastery
|
|
4 types of reliability ...
|
test retest, alternate forms, internal consistenty, interrater
|
|
3 types of internal consistency
|
split half, KR-20, cronbach
|
|
interrater measured by..
what is it affected by.. |
kappa coefficient
observer drift |
|
most strict form of reliability is..
|
alternate forms
|
|
which form of reliability overestimates..
|
internal consistency
|
|
reliablity tells accuracy of.. SEM tells accuracy of..
|
obtained scores
an individual score |
|
4 things that affect reliability
|
test length, homogenity of examinees, ability to guess, & difficulty level
|
|
3 types of validity
|
content, construct, criterion related
|
|
2 incorrect decisions that result from using predictors in decision making
|
false positive- pass predictor, fail criterion
false negative- fail predictor, pass criterion |
|
most common standard score
|
z score
|
|
criterion contamination
|
overestimates validity
|
|
ceiling effect is...
floor effect is... |
hard to discriminate among high scorers
hard to discriminate among low scorers |
|
personality tests have a reliability of
|
.70
|
|
industrial setting selection test
|
.90
|
|
spearman brown formula used to
|
correct split half reliability
|
|
2 types of tests good for speeded testing?
|
test retest & alternate forms
|
|
formula for standard error of measurement (SEM)
SEM means... |
std dev * (sqrt of 1-reliability)
likelihood obtained score = true score |
|
1 SEM=
2 SEM= 3 SEM= |
68%, 95%, 99%
|
|
correlation of GRE & GPA correlation of GRE & faculty ratings
|
.33, .41
|
|
Standard error of measurement(SEM):Standard error of estimate (SEst)
|
reliability:validity
|
|
reduce false positives by but which easier to manipulate
|
increasing predictor cutoff or reducing criterion cutoff -predictor cutoff
|
|
shrinkage is..
|
validity coefficient decreases when result cross validated
|
|
explain true positive, false positive, true negative, false negative
|
valid acceptance, false acceptance, valid rejection, invalid rejection
|
|
monotrait-heteromethod.. heterotrait-monomethod..
|
high= convergent validity
low= discriminant validity |
|
cluster analysis used to
|
develop a classification system
|
|
reliability does what to validity?
|
sets upper limit for validity
|
|
validity equal to or less than
|
sqrt of reliability
|
|
correction for attenuation
|
tells what validity would be if predictor & criterion perfectly reliable
|
|
best test difficulty level?
|
.50 (moderate)
|
|
Item characteristic curves graph.. slope of the curve tells.. so less steep curves..
|
how difficult item was
how well item discriminates discriminate best |
|
2 types of developmental norms are
|
mental age scores & grade equivalents
|
|
2 limitations of developmental norms
|
does not allow different age comparison or different test comparison
|
|
2 types of within group norms are
|
%tile rank and standard score
|
|
limitation of %tile rank
|
only for ordinal data so doesn't allow interpretation of absolute difference
|
|
4 types of standard scores
|
z score, T score, stanine, deviation IQ
|
|
z score formula
|
(score - mean)/std dev.
|
