CTT 4

Norm

• Total

• certain groups

Comparability

• parallel test forms

Economy

• time

• material

• group test

• scoring

Utility

• no other test could do the job better

Suppose that a student, twenty years old, received a raw score of 60 on the on the Wechsler‘s Intelligence Scale

Does this mean that his/her mental abilities are in the average range?

Impossible to tell since there is no clearly defined and uniform frame of reference (i.e., standardized scale)

The purpose of standard scores (e.g., Z-scores, IQ scores, T-scores) is to transform individual raw scores into a standard form that provides a more meaningful description of the individual scores within the distribution

This is because standard scores have a known mean and standard deviation enabling us to compare individual test results with the test performance of the standardization sample

Very simple way of categorizing test performances into top, middle and bottom percentages

Very imprecise way to categorize anything

• Everyone in the same stanine receives the same score

• Example: Someone at the bottom of the 5 th is almost 20 percentage points below the person at the top of the 5th (40% vs. 60%)

Only useful when a test is unreliable (rtt < .75) because it is an imprecise measure anyway