FINAL Flashcards
- a measurement device or technique used to quantify behavior or aid in the understanding and prediction of behavior
- devices we use to translate observations into numbers
test
a specific stimulus to which a person responds overtly; this response can be scored or evaluated
item
a set of items designed to measure characteristics of human beings that pertain to behavior
psychological test
overt behavior
observable activity
covert behavior
occurs within a person and cannot be directly observed (thoughts and feelings)
relate raw scores on test items to some defined theoretical or empirical distribution
scales
traits
enduring characteristics or tendencies
states
specific conditions or status
scores on tests may be related to
traits and states
individual tests
given to one person at a time
group tests
can be administered to more than one person at a time by a single test administrator
test administrator
person who gives the test
scored in terms of speed, accuracy, or both
ability test
measures previous learning
achievement test
measures potential for learning or acquiring a specific skill
aptitude
measures a person’s general potential to solve problems, adapt to changes in circumstances, think abstractly, and profit from experience
intelligence
measures typical behavior related to overt and covert dispositions of an in
personality
provide a statement and require the subject to choose between two or more alternative responses
- self-report
- true false
structured/objective tests
the stimulus, the response, or both are ambiguous
- Rorschach
- TAT
projective tests
all possible uses, applications, and underlying concepts of psychological and educational tests
psychological testing
Main uses
evaluate differences or variations among individuals
- abilities
- personality
- assume actual differences
- accuracy, dependability, consistency, or repeatability of test results
- greater reliability = less error
reliability
meaning or usefulness of test results
degree to which a certain inference or interpretation based on the test is appropriate
validity
method of gathering information through verbal interaction
interview
who “invented” standardized testing, when, and what for?
Chinese
4,000 years ago
Proficiency - reading, writing, math, etc.
two or more tests used in conjunction
test batteries
Individual differences
Darwin
experimented to show difference in sensory and motor functioning
Galton
- coined the term ‘mental test’
- established first psychology lab in U.S.
- individual differences and reaction time
James McKeen Cattell
used math models as a basis for educational theories
Herbart
attempted to demonstrate the existence of a psychological threshold; minimum stimulus needed for sensory activation
Weber
devised law that strength of a sensation grows as the log of stimulus intensity
Fechner
- founded the first psychology lab
- believe that people are more the same than different
- trained the first experimental psychologists
Wundt
Why did tests become necessary?
need to identify and classify mentally and emotionally handicapped people
Binet-Simon
- first intelligence test
- based on cognitive processes
Binet-Simon was supposed to differentiate between
capable, mentally limited, those who were capable but still didn’t learn
sample with individuals similar to those for whom the test is to be used
representative sample
a measurement of a child’s performance on a test relative to other children in the same age group
mental age
standardized the Binet-Simon and created a test manual
Lewis Terman
- created a nonverbal intelligence test for incoming immigrants
- eugenics
- controversial
- didn’t account for SES or education
Goddard at Ellis Island
World War I
Schools, colleges, industries, the military
multiple choice questions that are standardized on a large sample
achievement tests
measure presumably stable characteristics or traits that, theoretically, underlie behavior
personality tests
-developed during WWI to screen recruits
First-Woodworth Personal Data Sheet
method of finding the minimum number of dimensions, called factors, to account for a large number of variables
factor analysis
- personality test
- Cattell
- well-structured
- uses factor analysis
16PF
methods used to provide a concise description of a collection of quantitative information
descriptive
methods used to make inferences from observations of a sample to the population
inferential
application of rules for assigning numbers to objects
measurement
specific procedures used to transform qualities of attributes into numbers
rules
“moreness”; when a particular instance of the attribute represents more, less, or equal amounts of the given quantity than does another instance
magnitude
when the difference between two points at any place on the scale has the same meaning as the difference between two other points that differ by the same number of scale units
equal intervals
when nothing of the property being measured exists
absolute zero
to name objects; for qualitative info
nominal
has magnitude; allows for rank, but does not have equal intervals
ordinal
magnitude and equal intervals - no true zero
interval
magnitude, equal intervals, and absolute zero
ratio
summarizes scores for a group of individuals
distribution
- displays scores on a variable or a measure to reflect how frequently each value was obtained
- defines all possible scores
frequency distribution
-mean 50, SD 10
McCall’s T
interquartile range
Q3-Q1
- any set of numbers into a transformed scale
- range from 1-9
stanine system
the performances of defined groups on particular tests
-used to give information about performance relative to what has been observed in a standardization sample
norms
ways to express norms
- z-scores
- percentiles
- means
compares each person with a norm
norm-referenced test
describes the specific types of skills, tasks, or knowledge the test taker can demonstrate
criterion-referenced test
two scores for each individual
bivariate distribution
visual display of the relationships between variables
scatter diagram
determining whether two variables covary
correlation
mathematical index that describes the direction and magnitude of the relationship
correlational coefficient
technique used to make prediction about scores on one variable based on knowledge of scores on another variable
regression
- the best-fitting straight line through a set of points in a scatter diagram; the running mean or line of least squares, which minimizes the squared deviation around the regression line
- the mean will always be the point of least squares
regression line
shows the best linear relationship between X and Y
regression equation (slope formula)
the difference between the observed and the predicted Y values
residual
ratio used to determine the degree of variation in one variable that can be estimated from knowledge about variation in the other variable
Pearson product moment correlation coefficient
pictures showing the relationship between variables
regression plots
using information gained from representative groups and making an educated guess about an individual, typically that they will be at lease average
normative
- method for finding the association between two sets of ranks; coefficient (r)
- rank but not actual scores
Spearman’s rho
expresses the relationship between a continuous variable and an artificial dichotomous variable
biserial correlation
reflect an underlying continuous scale forced into a dichotomy
artificial dichotomous
one true dichotomous variable is used
point biserial correlatoin
both dichotomous, one true
phi coefficient
both artificially dichotomous
tetrachoric correlation
- squared correlation coefficient; tells us the proportion of the total variation in Y that is a function of X
- determines how much fo the variance in Y is a function of X
coefficient of determination
- measure of nonassociation between two variables
- determines how much variance is left over that is not accounted for by X
coefficient of alienation
- the amount of decrease observed when a regression equation is created for one population and then applied to another
- tend to overestimate the relationship in small samples
shrinkage
a process to ensure proper references are being made
- use regression equation to predict performance in one sample, other than the one the equation was applied to
- standard error of estimate can then be calculated for the relationship between the values predicted by the equation and the observed values
cross validation
correlation and regression use variability for explanations and predictions; if variability is restricted, significant correlations will be hard to find
restricted range
considers the relationship among combinations of three or more variables and one possible outcome
multivariate analysis
a weight composite of the original variables
linear combinations
goal is to find the linear combination of the three variables that provides the best prediction for the outcome
multiple regression
the correlation between the original items and the factors
factor loadings
put the ideas of sampling error and Pearson’s r together
Reliability theory
uses computer technology to advance psychological measurement
Item response theory
-on average, how much a score varies from the true score
-
Standard Error of Measurement
- using a limited number of items to test a larger construct
- more items = greater reliability
domain sampling
focuses on range of item difficulty that assesses an individual’s ability (test gets harder if you get more questions right)
item response theory
the will always be some inaccuracy in measurement
error
Standard Error of the difference
Tells you if two scores are significantly different enough
ratio of variance of the true scores on a test to the variance of observed scores
reliability coefficient
-test administered on two different occaisions
test-retest/stability
first testing session influences the second
carryover/practice effects
two equivalent forms of a test measure the same attribute
parallel/alternate forms/equivalent
item/scale homogeneity
do all the items measure the same thing?
best reliability estimate
internal consistency
tells you how many items are needed to reach a certain power
Spearman Brown
used for dichotomous scoring (true/false, multi, y or n)
Kudan-Richardson KR20
used for tests that are not dichotomous
Coefficient alpha
the agreement between a test score measure and the quality it is believed to measure
validity
judgement of items sampling intended domain
content validity
compare test in question to already established standard
criterion related validity
- concurrent
- predictive
tests administered at the same time
concurrent validity
test is being evaluated on how well it can predict scores on the criterion
predictive validity
give test to different groups and compare
-EFA and CFA
construct validity
a statistical analysis to predict a categorical dependent variable (called a grouping variable) by one or more continuous or binary independent variables (called predictor variables).
discriminant function analysis
comparison of true positive rate to false positive rate
Receiver-Operator-Characteristic (ROC curve)
Test development is made up of..(5)
- conceptualization
- construction
- tryout
- analysis
- revision
-who? what? why? of testing
conceptualization
scaling, scoring, adminstration
construction
pilot study
tryout
the capacity to find and maintain a definite direction or purpose, to make necessary strategy adjustments to achieve that purpose, and to engage in self-criticism
intelligence
Binet’s principles of intelligence
age differentiation & general mental ability
differentiating older children from younger children by their differing abilities
age differentiation
the total product of the various separate and distinct elements of intelligence
general mental ability
intelligence consists of one general factor (g) plus a large number of specific factors
Spearman’s Model of General Mental Ability
when a set of diverse ability tests are administered to large unbiased samples, almost all correlations are positive
positive manifold
ratio score of a subject’s mental age in conjunction with chronological age (IQ = MA/CA x 100)
Intelligence quotient (IQ)
standard score with M=100 and SD=15
deviation IQ
reflects learning and realization of original potential through experience
crystallized abilities
original potential, or basic capabilities that an individual uses to acquire crystallized abilities
fluid-analytic abilities
Wechsler vs. Binet
W had point scale - B had age scale
W had non-verbal performance scale
individual receives a specific amount of credit for each item passed, making it easy to group items of a particular content together
point scale
scale that provides a measure of nonverbal intelligence
performance scale
the relatively stable and distinct patterns of behavior that characterize an individual and his/her reactions to the environment
personality
nonintellective aspects of human behavior, typically distinguished from mental abilities
personality characteristics
relatively enduring dispositions; tendencies to act think or feel in a certain manner in any given circumstance and that distinguished one person from another
personality traits
general descriptions of people
personality type