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;
12 Cards in this Set
- Front
- Back
Which of the four scales of measurement has a true zero?
|
Ratio
|
|
What is the difference between interval and ratio scales?
|
Both scales are continuous and use equal units of measurement, but ratio scales have a true zero and ratio data can be compared in terms of proportions. Interval scales use an arbitrary zero - examples are IQ scores and Celsius temperature
|
|
What type of data are class rankings?
|
Ordinal
|
|
Which of the four scales of measurement do not involve equal units?
|
Nominal and Ordinal
|
|
What is a construct?
|
A hypothetical factor that is inferred from behavior, but cannot be observed directly
|
|
What is an operational definition?
|
A way of attaching a system of measurement to a construct:
* Must be replicable * Must be a faithful proxy of the construct |
|
What are the characteristics of a reliable measure?
|
Yields results that are consistent and repeatable, and include minimal measurement error
|
|
Define validity
|
The extent to which a measure of a construct truly measures that construct and not something else
|
|
What is Classical Test Theory?
|
a theory of reliability
|
|
What are 4 assumptions of classical test theory?
|
1. True scores are constant
2. Error is random 3. Correlation between true scores and error is 0 4. Correlation between errors on different measurement occasions is 0 In other words, true scores reflect systematic differences, while error is unsystematic (random). |
|
What is Generalizability Theory?
|
A special case of classical test theory in which error is divided up into factors
For example, error may result from testing conditions, the subject's well-being, characteristics of the test, etc etc |
|
What are the four main components of validity, from easiest to obtain to hardest?
|
1. Face
2. Content 3. Criterion 4. Construct |