Validity and Reliability

• Validity and Reliability

Validity

• Denotes the extent to which an instrument measures what it is supposed to measure

Content Validity

• This is whether the test items represent what you want to assess

Face Validity

• It is also known as logical validity
• Involves analyzing whether the instrument uses a vaild scale
• The researcher determines this by looking at the instrument's features
• This includes font size/typeface, spacing, paper size, and other details to avoid respondent distraction

Construct Validity

• This is the extent to which a test measures a theoretical construct or concept

Criterion-Related Validity

• A method to assess validity by comparing instrument scores with a criterion already known to measure the same trait/skill

Concurrent Validity

• The extent to which test/measurement results align with an established test conducted at the same time

Predictive Validity

• The extent a procedure allows accurate predictions about a subject's future behavior

Reliability

• This is the consistency of measurements
• A reliable test produces similar scores across various conditions, situations, different evaluators, and testing environments

Test-Retest Reliability

• Subjects tend to achieve the same score when tested at different times

Split-Half Reliability

• Sometimes referred to as internal consistency
• Subject scores on some trials consistently match their scores on other trials

Interrater Reliability

• Two raters independently observe and record specified behaviors during the same time period
• Target behavior refers to a specific behavior the observer records

Alternate Forms Reliability

• Also known as parallel-forms reliability
• Obtained by giving two equivalent tests to the same group
• Items are matched for difficulty on each test
• The time frame between giving the two forms should be as short as possible