Psychometrics
study of psychological measurement, including the measurement and assessment of IQ, specific abilities, knowledge in a given area,
... [Show More] personality traits, behaviors, attitudes, symptoms, and educational or vocational progress
Binet-Simon Scale (1905)
-first intelligence test
-problems occurred in order of difficulty
-easy to administer, objective, good test criterion validity evidence
assessment in clinical and counseling psych
tests that define and characterize patterns of adaption and functioning, to classify or diagnose
personality, mood and behavior functions, current functioning, adaptive capacity
referenced to range of function spanning development, capture degree of symptoms or traits influence/interfere with functioning
assessment in school psych
measure and characterize learning
IQ, academics, language, visual and motor processing, and behavior
assessment in neuropsychology
incorporates knowledge of brain functioning and brain-behavior relationship
neurocognitive strengths and weaknesses to determine if neurological/organic or function of nature
vocational and rehabilitation assessment
how well an individual meets demands for independence across development; goal of increasing success at work and learning as primary focus
behavioral assessment
an exploratory hypothesis-testing process to understand specific intervention strategies
assumption that behavior is produce of interaction of individual and environment
FBA - understanding the function of a behavior
ecological assessment
uses primarily observation methods to understand physical and psychological variable that impact behavior
Hiltonsmith and Keller 3 components of ecological assessment
1. setting appearance and contents: observable physical aspects of setting
2. setting operation: interaction and communication patterns within environment and how setting is being used
3. setting opportunities: opportunities within the environment that support development of cognition, language, and social-emotional growth
norm-referenced tests
standardized measures that compared performance to a specific population (usually age)
also evaluate change in performance over time
criterion-referenced test
where person stands on a particular criterion, or domain of skills, status, or functioning
assess an individual knowledge or skill in hierarchical fashion, consistent with expectations for learning
often used in educational or vocational settings to assess progress or mastery of skill or subject
EX driving test, licensure exam,
self-report measures
symptom-based questionnaires and surveys
broad-based: symptoms acorss a number of diagnoistic criteria (symptoms checklist, broad personality inventory)
narrow measure: symptoms of specific diagnosis (like Conners for ADHD)
informant reports: most used when wrking with kids, often parents and teachers; always consider bias
interviews
unstructured: outside standardized format, often open-ended; not good as only information for diagnosis
semistructured/structured: have good psychometrics; commonly used in research setting
observation
in natural setting allows understanding of antecedent and consequences
can check accuracy of informant reports
systematic observations/FBA's can be used to see effectiveness of behavior or psychological interventions
Narrative Recording
running record throughout observation
interval recording AKA time sampling
must operationally define target behaviors-record if behavior occurred during interval
good for frequent behavior or no clear beginning or end
event sampling
frequency of behavior during observation
rating recordings
examiner rates intensity or during using Likert scale
FBA
problematic behavior to create intervention plan; A-B-C; derived from operant conditioning model
-used to look at the function of a behavior
Assessment centers (I/O)
setting where standardized evaluation of behavior can occur based on multiple inputs
evaluate behavior and skills specific to job content; norm-referenced test for cognitive/personality/criterion for job knowledge
work sample to assess job potential
9 components of assessment centers
job analysis/competency modeling, behavior classification, assessment techniques, multiple assessments, simulations, assessor training, recording behavior and scoring, and data integration
classical test theory
Spearman (1904): an individual observed score on a test is the sum of a true score plus an independent measure of error
generalizability theory
identified sources of measurement error, separates the influence of each source, then estimates the individual sources of measurements error
reliability of measurement is evaluated by conducting a generalizability study (G study) to identify sources of measurement error
potential sources of measurement error
characteristics of the measure like test forms, test items, circumstance under which the test way given, the rater, and other related sources
Item Response Theory (IRT) - 3 parts
construct being measure and individual test items examine on multiple levels
1. item difficulty (% who get correct)
2. item discrimination (discriminate between high and low scores)
3. probability of a correct guess
Item Characteristic Curve (ICC)
IRT theory
mathematical function to show increasing proportion of correct answers for an item at higher levels of ability or trait being measured by the given assessment
Reliability
consistency of measurement
G theory: degree free from measurement error
CTT: reflect true score as well as error
test-retest reliability
the stability of measurements across time
alternate forms reliability
using different varieties of the test to measure consistency between them
internal consistency reliability
Reliability assessed with data collected at one point in time with multiple measures of a psychological construct. A measure is reliable when the multiple measures provide similar results.
split-half reliability
A measure of reliability in which a test is split into two parts and an individual's scores on both halves are compared.
use Spearman-brown
Interitem Consistency
Measure of internal consistency that compares item responses with each other and the total test score
good for homogeneous test items
Kuder-Richardson (KR-20) alternate approach for split half of a homogeneous test
inter-rater reliability
measure of agreement among observers on how they record and classify a particular event [Show Less]