Methodological Research Flashcards
How is the reliability affected in an experiment 3 things effect it
The reliability of a measurement is influenced by:
The sources of variability studied.
The participants selected.
The range of scores exhibited by the sample
Things that can affect Validity 4 things
Instrument
Intra-rater (intra-tester)
Inter-rater (inter-tester)
Intra-subject
Examples of Instrument, Intra-rater, Inter-rater, intra-subject issues
Instrument Loose axis (slips during measurement) Tight axis (too difficulty to move precisely) Interinstrument differences Intra-rater (intra-tester) Variations in participant positioning Inconsistent identification of landmarks Variable end-range pressure Inconsistent stabilization Reading errors Inter-rater
Levels of Standardization:
Nonstandrized. Highly Standardized, Partially Standarized approach. Explain each term.
Nonstandardized approach: No control of any sources listed. Low reliability.
Highly standardized approach: Control of the all possible sources. High reliability.
Partially standardized approach: Standardized a few sources of variability.
Range of Scores
What does restricted range of scores lead to.
what about having an extremely heterogenous group of people?
Reliability may vary at various places of measurement. For example the use of measure swelling might accurate at the knee x amount of times. However measuring swelling at the ankle maybe low reliability cause some might use the figure eight method while others may measure around the malleoi.
Restricted range of scores leads to low reliability coefficients. The use of normal participants can restrict the rage of scores within a study.
Using extremely heterogeneous group would overestimate the reliability of the measure for clinical use.
Reliability may vary at different places in the range scores because of difficulties unique to taking measurements at particular points in the range.
Levels of Realiabilty
if realiability is
below .5 = represents what level of reliability
between .5-.75 = what level of reliability
Above .75 = what level of reliability
Many reliability coefficients are based on measures of correlation.
Reliability coefficients are interpreted on the basis of their proximity to a value of 1.00.
Below .50= poor reliability
Between .50-.75= moderate reliability
Above .75= good reliability
For most clinical measurements, reliability should exceed .90 to ensure valid interpretations of findings.
A measure has a high internal consistency reliability when:
Each of the items correlates with other items in the measure.
Participants score at the high end of the scale every time they complete the measure.
Multiple observes obtain the same score every time they use the measure.
Multiple observes make the same ratings using the measure
Answer: Each of the items correlates with the other items in the measure.
Internal consistency occurs when all items are intercorrelated.
Cronbach’s coefficient alpha is often used for statistical documentation of internal consistency.
Measurement reliability refers to the: Dependency of the scores Consistency of the scores Comprehensiveness of the scores Accuracy of the scores
If the measure is consistent over multiple occasions, it has…………………….
Answer: consistency of the scores
A study to establish reliability of Mini Mental-State Examination reported that Cronbach’s α measure of reliability was 0.91. This finding refers to the A. Equivalency Reliability B. Stability Reliability C. Internal Consistency D. Interrater Reliability
???????
What is construct validity
Reflects the ability of an instrument to measure an abstract concept, or construct.
Strength, function, pain…etc.
FOR STRENGTH: Manual muscle testing, the number of times that particular weight can be lifted, handheld dynamometers, and a multitude of isokinetic tests.
FOR FUNCTION: Self dressing, transfers, housekeeping, recreational skills,…
What is content validity??
Reflects the ability of an instrument to measure an abstract concept, or construct.
Strength, function, pain…etc.
FOR STRENGTH: Manual muscle testing, the number of times that particular weight can be lifted, handheld dynamometers, and a multitude of isokinetic tests.
FOR FUNCTION: Self dressing, transfers, housekeeping, recreational skills,…
Determination of content validity is a subjective process. The validation is made by the panel of experts.
Example: A test of gross motor skills should not include items that assess fine motor skills, nor should it be influenced by the patient’s anxiety level or ability to read.
What range of activities are representative of “function” ?
Should a functional status questionnaire include questions related to physical, cognitive, social, and emotional status?
Criterion-related validation
Is determined by comparing it with an accepted (GOLD) standards of measurement. It is the most practical approach to validity and the most objective.
It is based on the ability of one test to predict results obtained on another test.
Criterion is based on what 3 concepts
Selecting the criterion: Instrument accuracy Concurrent criterion Predictive criterion When two test are administered to one group of subjects. If the correlation is high (CC is close to 1.00), the target test is considered a valid predictor of criterion score.
The validity of a measure refers to:
Comprehensiveness with which it measures the construct
Consistency of the measurement
Accuracy with which it measures the construct
Particular type of construct specification
Accuracy with which it measures the construct
A researcher developed a measure of shyness and is now asking whether this measure does in fact measure a person's true state of shyness. This is a question of: Reliability Construct validity Criterion validity Concurrent validity
Criterion validity
