PT526 - Week 3
Order by
44 terms
Terms | Definitions |
|---|---|
 PICO(T) | population intervention comparison outcome (TIME) |
| The role of the Independent variable | predictor, antecedent |
| The role of the DEPENDENT variable | outcome, consequent |
| Research hypothesis | expresses researcher true expectation of results |
| Statistical or Null hypothesis | implies no change |
| Validity | degree to which a useful (meaningful) interpretation can be inferred from a measurement |
| Construct Validity | conceptual (theoretical) basis for using a measurement to make an inferred interpretation; evidence for construct validity is through logical argumentation based on theoretical and research evidence |
| Content validity | a form of validity that deals with the extent to which a measurement is judged to reflect the meaningful elements of a construct and not any extraneous elements |
| The three forms of Criterion-based (criterion-related) validity | concurrent validity, predictive validity, and prescriptive validity |
| The common element of the three forms of criterion-based validity | with each form, correctness of an inferred interpretation can be tested by comparing a measurement with either a different measurement or data obtained by other forms of testing |
| Concurrent validity | form of criterion based validity in which an inferred interpretation is justified by comparing a measurement with supporting evidence that was obtained at approximately the same time as the measurement being validated |
| Predictive validity | form of criterion based validity in which an inferred interpretation is justified by comparing a measurement with supporting evidence that was obtained at a later point in time; examines the justification of using a measurement to say something about future events or conditions |
| Prescriptive validity | a form of criterion based validity in which the inferred interpretation of a measurement is the determination of the form of treatment a person is to receive; is justified based on the successful outcome of the chosen treatment |
| Face validity | assumption of validity of a measurement instrument based on its appearance as a reasonable measure of a given variable |
| If valid... | must be reliable |
| If reliable... | may or may not be valid |
| Evidence in support of construct validity | 1. Known groups method 2. Multi-trait multi-method matrix (trait and method) 3. Factor analysis |
| Convergent validity | scores of similar people will be similar |
| Divergent validity | scores of different people will be different |
| Whats very important for functional assessment tools? | content validity for example: SF36 assessment of Health-Related Quality of Life Usually determined by a panel of experts |
| Content validity is inextricably linked to | construct validity |
| what differentiates concurrent validity from predictive? | two measurements are taken at the same time |
| the gold standard in measurement parlance | measurement beyond reproach - one that everyone agrees is valid, and against which other measures can be validated |
| With predictive validity, measuring something now will | predict an outcome later |
| PT Example of predictive validity | screening tests |
| Prescriptive validity is similar to.. | predictive but now guides intervention ex: sensory organization test |
| Issues related to criterion based validity | norm vs criterion referencing |
| Problems with norm referencing | 1. no one person is normal 2. how big a deviation from normal is clinically relevant? |
| Whats criterion referencing and whats the problem? | choose an absolute, against which all are measured; Problem: who chose the criterion? |
| Sensitivity | ability of a test to obtain a positive test when the condition is present; a sensitive test rarely misses a positive diagnosis (if they got it, they test positive) |
| Specificity | ability of a test to obtain a negative test when the condition is absent; a specific test rarely misses a negative diagnosis (if they dont got it, they test negative) |
| Sensitivity equation = | Number of people with true positives / number of people who should be positive a / (a + c) |
| Specificity | Number of people with true negatives / number of people who should be negative d / (b + d) |
| predictive value of a positive test = | number of people with true positives / number of people who test positive |
| predictive value of a negative test = | number of people with true negatives / number of people who test negative |
| predictive values are dependent on | prevalence of the disease; if disease is more prevalent, you will get a higher positive predictive value |
| sensitivity and specificity are not affected as much by | prevalence |
| Receiver operating characteristics allows you to | choose the best operating point; the best balance |
| Change Score | difference between the outcome (after) score and the initial (before) score |
| Four issues affecting the validity of change scores | 1. level of measurement 2. reliability 3. stability 4. linearity |
| Level of measurement | ordinal scales- for evaluation and talk about improvement ratio data - interval is usually considered pretty good as well |
| Linearity | refers to the fact that the difference between 60 and 70% isnt the same as the difference between 88 and 98% but both are increases by 10. Ceiling and floor effects come into play here as well |
| Ceiling effects example | Berg - those old people with no balance |
| Floor effects examples | SAT scores |
First Time Here?
Welcome to Quizlet, a fun, free place to study. Try these flashcards, find others to study, or make your own.