skip navigation
Welcome! Orthopedics Resources Neurology Resources #PTDOS Physical Therapy Pulse Contributors Store

Statistics Overview and Definitions

Statistics Definitions


Standard Error of Measurement (SEM): Expected measurement error or difference of observed score from the true score  

Minimal Clinically Important Difference (MCID): The smallest amount of change in an outcome measure that is specifically meaningful to the patient

Minimal Detectable Change (MDC): The smallest amount of change in an outcome measure that represents a true change in the variable being tested (rather than measurement error)

Interrater Reliability: The degree of consistency of measurements taken between different testers 

Intrarater Reliability: The degree of consistency of measurements taken by a single tester across multiple trials 

Test/Retest Reliability: The consistency of the results of a test taken multiple times; measure of repeatability

Construct Validity: A measure of overall validity; the ability of a test to accurately assess what is actually being tested 

Content Validity: The ability of a test to assess all of the components or sub-categories of the construct being tested

Concurrent Validity: A measure of how well a certain test correlates with other tests that measure the same construct

Convergent Validity: A measure of how well a test compares to the current "gold standard" measure of the construct

Face Validity: The subjective validity of a test; a measure of the validity from the point of view of the patients/subjects

Predictive Validity: A measure of how well a test is able to predict future performance of the construct 

Sensitivity: The ability of a test to correctly rule in the condition being assessed (true positive rate)

Specificity: The ability of a test to correctly rule out  the condition being assessed (true negative rate)