Validity
Reliability
Segment Statistics
Item Analysis Techniques
Hodgpodge
100
This is the type of validty that a job analysis can provide evidence for.
What is Content Validity?
100
This is the equation used to identify Classical Test Theory.
What is O = T + E?
100
It tells you how much the scores deviate from the mean (on average)
What is the standard deviation?
100
This is the percentage of candidates who answered the item correctly.
What is Item Difficulty?
100
This was the song played during the first exercise.
What is Man-Eater. BONUS - The artist of this song is.....
200
This document, endorsed by several federal agencies, provides three methods to validiate selection examinations.
What is the uniform guidelines of employee selection procedures?
200
Health, Fatigue, Testwiseness; these are all examples of this.
What is error variance?
200
This is what an adequate standard deviation would be for an employment exam.
What is 10% of the test segement length?
200
Generally this is the range we want for item difficulty.
What is between .40 and .60 (unadjusted for guessing)
300
This type of validity is in evidence when the exam looks like what is required on the job.
What is face validity?
300
This type of reliability is achieved when the same test is administered at two points in time.
What is Test-Retest?
300
This referes to the average item difficulty of the exam segment.
What is the Mean Item Difficulty?
300
This is a measure of the difference between the proportion of high scorers answering the item correctly, and the proportion of low scorers answering the item correctly.
What is Item Discrimination Index?
300
This tends to increase with the homogeneity of items.
What is Reliability?
400
Providing a statistical relationship between job performance and a score on an exam is an example of this type of validity.
What is criterion referenced?
400
This type of reliability is achieved when two different but equivalent forms of the test are administered at two separate points in time to the same group of examinees.
What is Parallel Forms?
400
This refers to the reliability of the exam section.
What is Segment R?
400
This is something an Item Discrimination Index should never be.
What is a negative number?
400
This type of correlation coefficient indicates that candidates who scored well on the subtest also did well on the item.
What is a positive correlation?
500
When both convergent and divergent validity are present, it is used for evidence of this form of validity endorsed by the Uniform Guidelines.
What is construct validity?
500
This type of reliability focuses on estimating the consistency of different items on the same test.
What is internal consistency?
500
This is an estimate of error to use in interpreting an individual’s test score. A test score is an estimate of a person’s “true” test performance.
What is the Standard Error of Measurment?
500
This is similar to the discrimination index, but is not based on fixed upper and lower groups. For each item, it compares the mean score of students who chose the correct answer to the mean score of students who chose the wrong answer.
What is the Point-Biseral Correlation?
500
These are two procedures used to provide an estimate of the internal consistency of test scores.
What are Kuder Richardson (KR 20) and Cronbach’s alpha
M
e
n
u