General flash cards 2
Kuder-Richardson Formula 20
a variation of coefficient alpha; used when test items scored
dichotomously
the test length, the _______ the test’s reliability
coefficien
larger
The Spearman-Brown formula tends to _________ a test’s
true reliabilit
overestimate
reliability coefficient
the proportion of variability in a set of test scores taht is
attributable to true score variabilit
standard error of measurement
s used to construct a confidence interval around a
measured score
content validity
a test adequately samples the content or behavior that is it is
designed to measure
construct validity
when the test measures the hypothetical trait (construct) it is
intended to measure
convergent validity
high correlation with measures of the same trait
discriminent(divergent) validity:
low correlations with measures of unrelated characteristic
multitrait-mulitmetnod matrix:
used to systematically organize the data collected when
assessing a test’s convergetn and discriminant validity
monotrait-monomethod coefficients:
reliability coefficients: they indicate the correlation btw/ a
measure and inself; they should be large in order for the
matrix to provide useful info
monotrait-heteromethod coefficient:
indicate the correlation btw/ different measures of the same
trait;when large-provide evidence of convergent validity
heterotrait-monomethod coefficient:
show correlation btw/ different traits that have been
measured by the same method: when small,show
discriminant validity
heterotrait-heteromethod coefficient
ndicate the correlation btw/ different traits that have been
measured by different methods; also show discriminant
validity when sma
factor analysis
conducted to identify the min. number of common factors
required to account for the intercorrelations among a set of
tests,subtests, or test items
factor loadings:
correlation coefficients that indicate the degree of association
btw/ each test and each facto
communality
common variance-the ammount of variability in test scores
taht is due to the factors taht the test shares in common with
other tests included in the analysis
orthogonal rotation
the resulting factors are uncorrelated
oblique rotation
the resulting factors are correlated; the attributes measured
by the factors are not independent
criterion-related validity:
used whenever test scores are to be used to draw conclusions
about an examinee’s likely standing or performance on
another measure
concurrent validity:
when criterion data are collected prior to ar at the same time
as the data on the predictor/type of criterion-related validity
predictive validity:
when criterion is measured some time after the predictor is
administered; better for predicting future job performance
standard error of the estimate:
used to construct a confidence interval around a predicted
criterion score
incremental validity
the increase in correct decisions that can be expected if the
predictor is used as a decision making tool
incremental validity =
positive hit rate-base rat
base rate
he proportion of people who were seleted without the use of
the predictor and who are currently considered successful on
the criterion
base rate=
true pos + false neg/total # of people
positive hit rate
he proposrtion of people who would have been selected ont
he basis of their predictor scores and who are successful on
the criterion
positive hit rate =
true positives/total positives
The predictor’s criterion-related validity coefficient cannot
exceed:
the square roote of its reliability coefficient
correction for attentuation formula
o estimate what a predictor’s validity coefficient wouldbe if
the predictor and/or the criterion were perfectly reliable
A shortcoming of the correction for attentuation formula:
it tends to overestimate the actual validity coefficient that
can be achieved
the best way to avoid criterion contamination
is to make sure that the individual who is rating/scoring
people on the criterion measure is nto familiar with their
performance on the predictor
Percentile ranks have a flat distribution because
they are evenly distributed thoughout the range of scores
Percentile ranks
nonlinear transformation bc/ their distribution is always flat
regardless of the shape of the raw score distribution
z-score distribution properties
The mean of the distribution is 0; the SD is 1; all raw scores
below the mean are neg and all above the mean are pos;
unless it is normalized, the distribution has the same shape as
the raw score distribution
T-score distribution
has mean of 50 and SD of 10
genotype
a person’s genetic inheritence
phenotype
his/her observed characteristics; attributable to a
combination of heredity and environment
3 stages of prenatal development:
germinal, embryonic, fetal
translocation
germinal, embryonic, feta
translocation
the transfer of a chormosome segment to another
chromosome