final exam review Flashcards
measurement:
administer test for purpose of obtaining score and collecting info
evaluation:
interpret score, place a value judgement on the measurement, and making decision about results
stages of testing:
- test selection
- preparation
- administration
- data processing
- decision making and feedback
*prescreening doc
can a test be valid but not reliable?
no
*can be reliable but not valid
how would you say a test is valid (include which components?)
this test can be used to make decisions about (underlying construct being measured) in (intended population) for (intended purpose and situation) because (provide evidence of validity)
test selection:
what we are testing and why
consider:
are scores repeatable?
are we remaining objective?
are we measuring actual construct?
sensitivity
practicality
participant burden
preparation:
obtain consent forms
calibrate equipment
consider sources of measurement error
administration:
testing sequence - consider motivation, safety, preparation
data processing:
interpreting results requires using an appropriate statistics protocol
decision making and feedback
a criterion score (needs to be gold standard for test) indicates a person’s ability - pass/fail
typical testing sequence (8):
- screening
- non fatiguing tests (flexibility, jump, body comp)
- agility
- max power/ strength
- sprint
- muscle endurance
- anaerobic capacity
- aerobic capacity (performed on different day)
4 sources of measurement error:
- test
- test administrators
- test subjects
- environment
what is validity? what 3 characteristics does it rely on?
how well a test measures what it is supposed to
1. reliability
2. relevant (does is accurately measure desired outcome)
3. scores - do they make sense & are interpretable?
objectivity
depends on:
consistency b/n 2 judgements of performance - test is objective when eliminate scorer’s bias/ personal opinion
depends on:
- Competency of judges
- Clarity of scoring system
- Degree to which judge can assign scores
accurately
logical validity:
content validity - does tested movement mimic real life situation?
determined by experts opinion
construct validity:
examines the degree to which a test measures hypothetical, subjective constructs and abstract skills
criterion validity
the relationship between scores from a test against the gold standard for criterion measurement
R greater or equal to 0.80 and an R closer to 1 suggests strong validity
types of criterion validity:
predictive
concurrent
predictive validity
criterion measured in the future (weeks, months, years later) to generate predictions on performance for a given construct
concurrent validity
extent of to which agreement between two measures taken at approximately the same time. It compares a new assessment with one that has already been tested and proven to be valid.
(Negative R value suggests inverse relationship between two measurements)
intra-rater reliability
measure w same instrument on 2 separate occasion to observe the level of agreement b/n trials
inter-rater reliability
measure of consistency - used to evaluate extent to which different judges agree in their assessment decisions
How to reduce measurement error/ reliability be impacted by adjusting:
- Valid and reliable tests
- Instructions - standardized
- Test complexity - straightforward?
- Warm up and test trials
- Equipment quality and preparation -
calibrated?