Validity and Reliability Flashcards Preview

EPHE 444 > Validity and Reliability > Flashcards

Flashcards in Validity and Reliability Deck (25):

what is validity?
what is it dependant on?

the ability of a test to measure accurately, the degree to which a test measures what it purports to measure
--> dependant on reliability, relevance and appropriateness of scores


what is reliability

the consistency or repeatability of an observation, the degree to which repeated measurements of a trait are reproducible under the same conditions


4 common types of validity evidence

1. construct validity
2. logical validity
3. criterion validity
4. convergent validity


all types of validity can be estimated either _______ or _______

logically, statistically


the test effectively measures the desired construct

construct validity


the measures obviously involves the performance being measured
- no statistical evidence is required

logical/face validity


degree to which scores on a test are related to recognize standard or criterion (gold standard)

criterion validity


AKA statistical or correlation validity

criterion validity


how is criterion validity obtained?

by determining the correlation/ validity coefficient (r) between scores for a test and the criterion measure


The criterion is measured at approximately the same time as the alternate measure and the scores are compared
- ex?

concurrent validity

ex, skin folds and hydrostatic weighing


the criterion is measured in the future (week, months, years later)
- ex?

predictive validity

ex, the pre selection test battery score and the selection success


2 or more measurements are conducted to collect data and establish that a test (battery) is measuring what is purports to measure

convergent validity


the consistency of repeatability of an observation
- the degree to which repeated measurements of a trait are reproducible under the same conditions



how do calculate reliability

rest retest scores to calculate reliability coefficient
eg. r= 0.99 to sit and reach (very high reliability)


3 types of reliability

1. stability reliability
2. internal - consistency reliability
3. objectivity


what is stability reliability ?

when scores do not change across days
--> look at the relationship b/w multiple trials across multiple days


3 factors that contribute to low stability

1. the people tested may perform differently
2. the measuring instruments may operate or be applied differently
3. the person administering the measurement may change


what is internal consistency reliability ?

evaluator gives at least 2 trials of the test within a single day


the internal consistency reliability coefficient is not comparable to stability reliability coefficient, the I-C coefficient is almost always?



what is objectivity reliability

rater/judge reliability
- inter-tester reliability


2 factors affecting objectivity

1. the clarity of the score system
2. the degree to which the 'judge' can assign a score accurately


9 considerations for reducing measurement error

1. validity and reliable test
2. instructions
3. test complexity
4. warm up and test trials (learning effect - may need 5 trials)
5. equipment quality and preparation (e.g calibration)
6. testing environment
7. scoring accuracy
8. experience and state of mind of person conducting the test
9. state of mind of person being tested


Why calibrate?
How calibrate?

important to confirm accuracy of what equipment is telling you
- requires comparison between measurements (one of known magnitude and one of unknown magnitude that need sot be confirmed)
- check equipment is up to date and proper functioning


how often do you calibrate?

at least every 6 months, or according to manufacturer's guidelines


reliability can be expected when ? (3)

1. the testing environment is favorable to good performance
2. ppl are motivated , ready to be tested and familiar
3. the person administering the test is trained and competent