How do test items become a raw score?
An IQ test turns answers to reasoning items into a raw score. The test's scoring rules determine how much credit each answer earns, and the points add up to that score.
The raw score belongs to that test and its particular items. By itself, it does not show how the result compares with other people. Test makers use a norm sample for that comparison. Learn more about the abilities assessed in what IQ tests measure.
Why is the norm sample matched by age?
The norm sample shows how people in the test-taker's age group performed on the same test. The raw score is interpreted against those results, making age part of the comparison.
Each age group's average is 100. A resulting IQ score describes a person's standing relative to people of the same age; it is not a count of correct answers or a direct measure of every ability.
How does a raw score become an IQ score?
Test makers use the norm sample to convert a raw score to a standard score. Wechsler IQ scores use a mean of 100 and SD 15, so the number shows how a result compares with the relevant norm group.
The common scale makes results easier to interpret, but tests can use different questions, scoring rules, and norms. A Wechsler IQ test is one example of a full test with its own materials and administration rules.
Why do IQ tests have a floor and ceiling?
Full-scale scores on the WAIS-IV and Stanford-Binet 5 have a standard range of 40-160. These are the lower and upper limits for reporting scores on those scales.
Near either limit, the test gives less detail about differences beyond the boundary. A score also has a margin of error, so a report may give a range instead of presenting one number as exact.
Who gives full tests, and why use new items on a retest?
A qualified examiner gives a full IQ test one to one and follows the test's instructions. The Wechsler publisher limits access to the WAIS to users with Qualification Level C.
Retaking a similar test tends to raise scores a little. Familiarity with the task types or remembered items can affect a later result, so a retest should use different items. The new result still depends on suitable norms and proper administration.