Ch. 5 Measurement Concepts Flashcards
four scales of measurement
nominal, ordinal, interval, and ratio
Standard deviation is an example of which: nominal, ordinal, interval, or ratio scales of
measurement?
(interval)
What is a general definition of reliability?
extent to which a measure is free from measurement error
Measurement error is …
the positive or negative bias within an observed score.
The score a person receives on a test is made up of two elements:
the person’s true score and an error score that may add to or subtract from the true score.
because error originates from the individual, test, and/or testing condition, _____ is impossible
no measurement error
A test with perfect reliability would equate to …
no measurement error.
A ____ score is never known.
true
Each correlation coefficient contains 2 bits of information. What are these 2 bits of
information?
- direction (+ or -) of the relationship
- size of the relationship
The _________ correlation coefficient (r) is the most common type of correlation
coefficient
Pearson product-moment
three types of reliability:
Test-retest reliability
Interitem consistency
interrater reliability
T or F: Reliability is a precursor to validity but not sufficient by itself.
(True)
content validity
extent to which the content of an assessment represents the construct being measured
two types criterion-related validity:
concurrent and predictive
_____ validity is measured at the time of the initial assessment, while _______ validity is assessed after the initial assessment
concurrent; predictive
criterion-related validity
extent to which an assessment correlates with the actual presence of the characteristic being measured
Sensitivity
the power of a test to avoid false negatives and identify the trait/construct it intends to identify
specificity
the power of a test to avoid false positives and identify the lack of a trait or construct being measured.
___ validity refers to the correlation between a test and other tests measuring the same construct; while ____ validity refers to the lack of correlation between the test and measures of constructs purported to be different.
convergent; discriminant
factor analysis
form of validity analysis that can determine whether the test items fall together in different factors the way that the theory suggests they should
treatment validity
the extent to which a measure has a clinically useful effect on client outcomes
validity scales
tools used to determine response distortions
three types of response distortions:
faking bad, faking good, and random response
