Reliability and Validity PDF

Measurement Reliability and Validity Dr. Latifah Alenezi Assistant Professor Measurement Reliability Reliability: The degree of consistency with which an instrument or rater measures a variable. Reliability Coefficient  < 0.5 poor  0.5 to 0.75 moderate  > 0.75 good Reliability Types of Reli...

Measurement Reliability and Validity Dr. Latifah Alenezi Assistant Professor Measurement Reliability Reliability: The degree of consistency with which an instrument or rater measures a variable. Reliability Coefficient  < 0.5 poor  0.5 to 0.75 moderate  > 0.75 good Reliability Types of Reliability I. Test-Retest reliability II. Rater Reliability III. Alternate reliability IV. Internal consistency Reliability I. Test-Retest Reliability The degree to which an instrument is stable, based on repeated administration of the test to the same individuals over a specific time interval Things to consider  Carryover ex. Dexterity test  Testing effects ex. ROM test  Test-retest interval  Stability of response  Test’s intended purpose Reliability II. Rater Reliability Intra-rater Inter-rater The degree to which one rater can obtain The degree to which two or more raters the same ratings on multiple occasions of can obtain the same ratings for a given measuring the same variable variable Things to consider Rater bias ex. Memory of 1st score Reliability III. Alternate Forms The reliability of two equivalent forms of measuring instrument Example: 3 brands of dynamometers Reliability IV. Internal consistency or homogeneity The degree to which a set of items in an instrument all measure the same characteristics Example: physical function scale Measurement Validity Validity: The degree to which an instrument measures what it is intended to measure Example: pain scale vs. leg length as measure of LBP Types of Validity I. Face validity II. Content validity III. Criterion-related validity IV. Construct validity I. Face validity Indicates that an instrument appears to test what it is supposed to test Validity Validity II. Content validity The degree to which the items in an instrument adequately reflect the content domain being measured Example: pain scale vs. McCill Pain Questionnaire -pain location, time, intensity Validity Concurrent III. Criterion-related validity The degree to which the outcomes of one test correlate with outcomes on a criterion test (GOLD STANDARD) Predictive The degree to which the Instrument is used to outcomes of one test correlate predict some future with outcomes on a criterion performance test, when both tests are given Example: Observational gait vs. motion at relatively the same time analysis system (Leg length using x-rays vs. tape) Validity IV. Construct validity The degree to which a theoretical construct is measured by an instrument Relationship between Validity and Reliability The relationship is unidirectional A. Reliable B. Neither reliable nor valid C. Reliability improved D. Reliable and valid Slide Preparation  Dr. Hesham Alrowayeh  Dr. Latifah Alenezi