Validity and Reliability
No description yet. This curated deck is ready for daily study.
Card preview (24)
Define validity
• The degree to which the test or instrument measures what it is supposed to measure
What are the 4 types of validity
Logical or face Content Criterion Concurrent
Define logical or face validity
• Degree to which a measure involves the performance being measured • Not objective, hence not useful for research
Define content validity
• Usually applies to education settings - Degree to which the sample of items or questions on a test are representative of some defined content
Define criterion validity
• Degree to which scores on a test are related to some recognised standard or criterion
Define concurrent validity
• Type of criterion validity in which the scores from a measurement instrument are correlated with a criterion measure that is administered at the same time
Define reliability
• Relates to the consistency or repeatability of an observation
What is validity dependent on
Reliability and relevance
TO be valid a test must be what
reliable
A test can be x but not y
x = reliable y = valid
What is the reliability and classical test theory
• Test reliability is sometimes discussed in terms of observed score, true score, and error score
reliability and classical test theory equation
• Observed score = True score + Error score
How can reliability been expressed
• Can be expressed by a correlation coefficient, ranging from -1.00 to 1.00
Define interrater reliability
inter-rater reliability is the degree of agreement among raters.
What correlation do u use for two measures, and what for more than two
Pearson r = two Intraclass correlation = for more then two
what correlation is used for interrater reliability
Kappa
What is the correlation range
• 1.00 to 1.00
What does the Pearson r tell us
It gives information about the magnitude of the association, or correlation, as well as the direction of the relationship between variables.
Explain the correlation ranges from 0 to + 1
.80 - 1: Very strong positive .60 - 79: Strong positive .40 - 59: Moderate positive .20 - 39: Weak positive .0 - 19: Very weak positive
Explain the correlation ranges from 0 to - 1
• 1.00 to - 0.80: Very strong negative • 0.79 to - 0.60: strong negative • 0.59 to - 0.40: moderate negative • 0.39 to - 0.20: weak negative • 0.19 to -0.01: very weak negative
Define internal consistency reliability
nternal consistency reliability is a way to gauge how well a test or survey is actually measuring what you want it to measure.
What does test-rest measure
It reflects the variation in measurements taken by an instrument on the same subject under the same conditions
Threats to external validity
Hawthorne effect Demand characteristics
Threats to internal validity
• Maturation • History • Statistical regression: An initial extreme score is likely to be followed by less extreme subsequent scores • Instrumentation e.g. Uncalibrated equipment • Selection Bias, e.g. Groups not randomly assigned