Medical 2

• Reliability


  How consistently a method measures something
• Validity


  How accurately a method measures what it is intended to measure
• High reliability


  One indicator that a measurement is valid
• Inter-rater Reliability


  • Consistency of ratings or judgments made by different raters or observers
• Parallel Reliability


  • Consistency of results obtained from different but equivalent versions of the same test or measurement tool
• Test-Retest Reliability


  • Consistency of results obtained when the same test is administered to the same individuals on two different occasions
• Internal Consistency


  • Extent to which items within a measurement tool or scale are correlated with each other
• Cronbach's Alpha


  A measure of internal consistency reliability, which assesses how closely related a set of items are as a group
• Split-half reliability


  A measure of internal consistency that assesses the reliability of a scale or questionnaire by dividing it into two halves and comparing the scores obtained from each half
• Inter-item correlation


  The degree of association or relationship between different items or variables within a measurement instrument or scale
• Item-total correlations


  The relationship between individual items of a scale or questionnaire and the total score of the scale, evaluating the extent to which each item contributes to the overall measurement of the construct
• Face validity


  • How valid the results seem based on what they look like, the least scientific method of validity
• Content validity


  • Whether the measure used in the research covers all of the content in the underlying construct
• Criterion-related validity


  • A measure of the quality of your measurement methods, demonstrated by comparing it with a measure that is already known to be valid
• Predictive validity


  • The extent to which a measurement or test can predict future outcomes or behavior
• Concurrent validity


  • The degree of correlation between a new measurement or test and an established measurement or test that measures the same construct, administered at the same time
• Convergent validity


  • The degree to which scores on a measurement tool correlate with scores on other measures of the same construct
• Discriminant validity


  • The degree to which scores on the measurement tool do not correlate with scores on measures of unrelated constructs
• Internal validity


  • The degree to which the results of a study accurately reflect the effects of the independent variable(s) being manipulated or studied, involving controlling for extraneous variables
• External validity


  • The generalizability of the results of a study to other populations, settings, or conditions
• Pretest or Pilot Study


  A study conducted before a large-scale study to evaluate the feasibility of the research methods, identify potential problems, and refine the study protocol