Norms
What are norms?
Distribution of scores obtained from a specific sample (norm group)
What are raw scores?
What is the normal curve?
A symmetrical, bell-shaped curve that describes the distribution of probabilities
Total area under curve = 1
Extends infinitely in both directions approaching 0
Most scores cluster in centre
Similarity of scores of the same people on different administrations.
Test is administered to the same group on two different occasions.
What is the classical test theory?
- Observed score (X) = true score (T) + random error (E)
How are norms obtained?
By administering the test to a sample of people (presumably representative of the population)
What do measures of central tendency do?
Describes the middle of the distribution and provides information on the mean, median, and mode.
What does it mean if scores are negatively skewed?
The majority of scores are to the right of the distribution (items are too easy)
What is inter-rater reliability?
-Used when scoring involves some level of subjectivity
-Errors are random
-The true score will not change with repeated measurement
-The distribution of errors will be the same for everyone
What are norms used for?
To estimate a person's standing relative to similar others, and to provide standards for interpreting scores.
What are the methods for making sense of raw scores?
Using descriptive statistics (central tendency, range and standard deviation, frequency distributions), normal distribution (bell curve), skewness, and standard scores.
What does it mean if scores are positively skewed?
The majority of scores are to the left of the distribution (items are too difficult)
What is parellel-forms reliability?
Focuses on whether different forms of the same measurement instrument, when measuring the same subject, will produce similar results.
What are random errors?
What are the forms norms can take?
1. % rank
2. Age equivalents
3. Grade equivalents
4. Standard score
What do measures of variability do?
Describe the spread in the distribution and provide information on the range (high score minus low score), variance (average squared distance from the mean), and standard deviation (average distance from mean).
What are standard scores?
Universally understood units in testing.
What is internal consistency?
A measure of reliability; the degree to which a test yields similar scores across its different parts, such as an odd versus even items.
What are sources of random error?
1. Test itself
2. Test administration
3. Test scoring
4. Test takers
5. Stability of construct
What does percentile describe?
The % of people who score below a particular score.