click below
click below
Normal Size Small Size show me how
EBP Review
Review of EBP terms, stats tests
Term | Definition |
---|---|
Independent Variable vs. Dependent Variable | IV: factor believes to bring about a change in the DV; DV: Change believed to result from intervention |
Data Types: Nominal, Ordinal, Interval, Ratio | Nominal: variables into 2 or more categories (M vs F) Ordinal: classifies and ranks variables based on degree (MMT, GPA) Interval: classifies at predetermined equal interval (0-200, temperature) Ratio: True zero, precise level of measurement |
Effect Size | the size (magnitude, quantity) of the difference between sample means; allows a stat test to find a difference when one exists |
Internal Validity | the degree to which the observed differences on the dependent variable are from direct manipulation of IV |
External Validity | Generalizability of the results outside study |
Face validity | the assumption of validity based on the appearance of an instrument as a reasonable measure |
Content validity | the degree to which an instrument measures an intended area (expert judgement) |
Concurrent Validity | the degreee to which the scores on one test relate to scores on another criterion test (comparison to gold standard) |
Predictive Validity | the degree a test can predict future performance |
construct validity | the degree in which a test measures intended hypothetical abstract concept (non observable) |
Interrater reliability | 2 independent raters find the same result |
intrarater reliability | one rater multiple trials |
test-retest reliability | scores on a test are stable over time |
split-half reliability | reliability of first half of test compared to second (internal consistency) |
Sensitivity | test's ability to correctly identify individuals who have the dx |
Specificity | test's ability to identify individuals who do not have dx. |
Predictive value | test's ability to estimate likelihood of + or - test |
Cohort Study | prospective following a group of participants for a period of time compared to matched group without condition |
Case-control study | retrospective; group with condition compared to group without |
Range (Measures of Variability) | difference between highest score and lowest score |
Standard deviation | determination of variability of scores from the mean |
Normal distribution | symmetrical bell curve, 68% of scores fall within 1 SD |
Alpha level | preselected level of statistical significance (set at .05, .01, expressed as a value of P) |
Type I Error | Null was rejected when it was true |
Type II Error | null was not rejected when it was false |