Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
26 Cards in this Set
- Front
- Back
What is the theoretical definition of reliability?
|
The proportion of score variance that is caused by systematic variation in the population of test-takers.
|
|
What is reliability?
|
A measure of consistency in the scores produced from an instrument
|
|
How is reliability correlated with random error?
|
An indicator of the absence of random error when the test is administered.
When random error is minimal, scores can be expected to be more consistent. |
|
What is important to remember about reliability?
|
It is important to remember that reliability is a property of scores and NOT of tests.
|
|
What is reliability dependent on?
|
Variances.
|
|
Where does variance come from?
|
-From the test items.
-From the individuals taking the test. |
|
Who contributes to variablity in scores?
|
-Both the test and the individuals contribute to variability scores.
Individuals do not contribute to variability in tests, but individuals do contribute to variability. |
|
How does measurement error occur?
|
Think of a tape measure.
Each time we use the tape measure, we get approximately the same answer. Sometimes we may be off by a few millimeters. Measurement Error |
|
What does reliability tell us?
|
Reliability tells us how accurate and trustworthy a test score is.
|
|
Theories of reliability suggest that the accuracy of any psychological measure is influenced by what 2 main factors?
|
-Factors that contribute to test consistency:
-Factors that contribute to test inconsistency: |
|
What are Factors that contribute to test consistency?
|
Stable characteristics of the person or of the attribute one is trying to measure.
|
|
What are Factors that contribute to inconsistency?
|
These are error.
|
|
What are some sources of Variablity?
|
-The test taker
-The test itself -The test administration -Scoring of the test |
|
What is our goal in developing tests that produce reliable scores?
|
To minimize the sources of systematic error.
|
|
What is X=T+e
|
Observed score = True score + Error
|
|
What does the formula X=T+e suggest?
|
This formula suggests that the scores you gather on psychological tests are not in fact ‘true’ or ‘real’ scores
|
|
What do the scores you obtain represent, if not real scores?
|
A combination of many factors.
|
|
The ultimate goals of reliability theory are to:?
|
-Estimate errors in psychological measurement
-Devise techniques to improve testing so errors are reduced |
|
What is the central assumption of reliability theory?
|
That measurement errors, pertaining to large groups of people, are random.
|
|
If errors are random, then it is reasonable to assume:
|
-Mean error = 0 (errors are equally + and -)
-True test scores and errors are not correlated. -Errors on different measures are not correlated |
|
Because of the assumptions of errors?
|
The variance in observed scores consists of 2 elements:
-Variability in true scores -Variability in error scores |
|
When we talk about reliability, we are interested in what?
|
the consistency of observed scores obtained.
|
|
What is signal to noise radio?
|
Comparison of the amount of variance due to true and error scores in observed scores
|
|
What is reliability index?
|
Comparison of the amount of variance due to true scores with total variance in observed scores.
|
|
What is the reliability coefficient?
|
The square of the reliability index (when using correlation to calculate it)
|
|
When is the reliability index generally used?
|
In CTT.
|