Psych Prep - Chapter 9: Test Construction
TEST BANK Practice Questions with correct answers
Chamberlain College of Nursing
Define reliability The amount of consistency, repeatability, and
dependability in scores obtained on a given test
or measure
What is the classical test theory? X (obtained score) = T (true score) + E (error)
When scores range on the EPPP - What is an true score variability - genuine differences in the
example of true score variability? What is an ability and knowledge among the test-takers
example of error variability?
error variability - chance factors
what is the relability co-efficient range? What is 0.0 to 1.0
the minimum acceptable value for the reliability
coefficient ? .80
What are the four types of reliability? 1. Test-Retest reliability: one group takes the
same test at two points in time
2. Parallel forms reliability: one group takes two 3. Internal consistency reliability: One group takes
versions of the test at two points in time one test at one point in time
, Methods include split-half reliability (comparing 4. Interrater reliability: subjective; one test at one
two halves of the test) or Cronbach's coefficient point in tiem with different raters
alpha (average of every possible split-half of the
test)
Methods include Pearson r (the correlation What is the difference between a power test and
between the scores assigned to each ratee by two a speed test?
different raters, Cohen's kappa statistic (ranges
from 0.0 to 1.0
Power test: assesses a person's level of mastery Speed test: assesses how many items a person
of a particular topic when there is little or not can complete in a predetermined time block. Easy
time pressure. Difficult questions are asked. questions are asked.
What are the four factors that affect reliability? 1. the number of items: greater number of times
the more reliable the test will be
2. Homogeneity of items: the more homogeneous 3. range of scores: The greater heterogeneity of
the test items, the more reliable the test will be subjects on the measured dimension, the wider
the range of scores will be. A full range of scores
maximizes reliability
4. Ability to guess: tests that allow for easier What is a standard error of measurement (SEM)?
guessing (ie, true or false) generally have lower
reliability then other tests because scores will be
more affected by chance guessing
the average amount of measurement error in What do confidence intervals indicate? What is
each subject's score on any given test required to calculate it?
TEST BANK Practice Questions with correct answers
Chamberlain College of Nursing
Define reliability The amount of consistency, repeatability, and
dependability in scores obtained on a given test
or measure
What is the classical test theory? X (obtained score) = T (true score) + E (error)
When scores range on the EPPP - What is an true score variability - genuine differences in the
example of true score variability? What is an ability and knowledge among the test-takers
example of error variability?
error variability - chance factors
what is the relability co-efficient range? What is 0.0 to 1.0
the minimum acceptable value for the reliability
coefficient ? .80
What are the four types of reliability? 1. Test-Retest reliability: one group takes the
same test at two points in time
2. Parallel forms reliability: one group takes two 3. Internal consistency reliability: One group takes
versions of the test at two points in time one test at one point in time
, Methods include split-half reliability (comparing 4. Interrater reliability: subjective; one test at one
two halves of the test) or Cronbach's coefficient point in tiem with different raters
alpha (average of every possible split-half of the
test)
Methods include Pearson r (the correlation What is the difference between a power test and
between the scores assigned to each ratee by two a speed test?
different raters, Cohen's kappa statistic (ranges
from 0.0 to 1.0
Power test: assesses a person's level of mastery Speed test: assesses how many items a person
of a particular topic when there is little or not can complete in a predetermined time block. Easy
time pressure. Difficult questions are asked. questions are asked.
What are the four factors that affect reliability? 1. the number of items: greater number of times
the more reliable the test will be
2. Homogeneity of items: the more homogeneous 3. range of scores: The greater heterogeneity of
the test items, the more reliable the test will be subjects on the measured dimension, the wider
the range of scores will be. A full range of scores
maximizes reliability
4. Ability to guess: tests that allow for easier What is a standard error of measurement (SEM)?
guessing (ie, true or false) generally have lower
reliability then other tests because scores will be
more affected by chance guessing
the average amount of measurement error in What do confidence intervals indicate? What is
each subject's score on any given test required to calculate it?
