exam one Flashcards
standardization
a comparison tool: how does ones score compare to others
reliability
are the results consistent
validity
are the results accurate, measured accurately
magnitude
is the scale measuring a relative amount, are the numbers representing labels
equal intervals
is the difference between two points on a scale consistent across the scale
absolute zero
is there a point at which the scale can truly detect a nothingness
nominal
categorizes (qualitative)
ordinal
categorizes, ranks in order (qualitative)
interval
equal intervals (quantitative)
ratio
has a true zero
central limit theorem
if the sample size is large enough, the sampling distribution will be normal
criterion referenced tests
assesses performance based off standards
norm referenced tests
standard deviation
shows variation in a data set
z-score
deviation of a score from the mean in SD units, (individual score-mean score/SD)
why do we need standardization?
to give raw data meaning
mccall’s t (t-score)
used for personality testing, mean is set at 50, SD is 10
dichotomous scaling method
offers two choices for each question
polytomous scaling method
multiple choice test
likert scaling method
pick which one represents their response
category scaling method
similar to likert but with more choices
reliability coefficient
measures the inter-item correlations in the connect of the number of items
what is the correlation coefficient called?
cronbachs alpha
test retest reliability
test once and come back to retest
alternate forms reliability
different versions of a test
interrater reliability
multiple people observing, making sure they’re consistent
internal consistency
making sure items are internally consistent on measure
what are the sources of measurement error?
item selection, test administration, subjective scoring, systematic measurement error (poor validity)
validity
is it accurate
content validity
test items are a representative sample from a population
criterion (outcome) related validity
test demonstrate the ability to effectively estimate performance based on an outcome measure
concurrent validity
criterion (outcome) is measured at the same time as the test scores
predictive validity
test scores predict a later criterion (outcome)
what is validity determined through?
correlation, validity coefficient, Pearson
construct validity
theoretical, pertains to psychological tests, measured through convergent and discriminant validity
convergent validity
use other tests of similar constructs and show strong correlations
discriminant validity
use tests for unrelated constructs and show weak correlations
what statistic do we look at to test the standardization of our measure?
z-score
what statistic did we use to test reliability?
cronbachs alpha
what type of reliability did we test in our survey?
internal consistency
how do we determine if an assessment has construct validity?
convergent and discriminant validity
what other type of validity helps demonstrate construct validity?
content validity
what do we use SPSS for?
use stats to help us know how good our items are at measuring the construct, gives stats for validity and reliability to see how good our measure is
types of psychological assessments
- intelligence test
- personality test
- psychometric tests
- neuropsychological tests
- projective tests
- behavioral assessment
- interview
- achievement tests
- emotional intelligence tests
