Karteikarten
Reliability and Validity
Karten in diesem Stapel (18)
- 1Reliability and ValidityTechniques for evaluating the relationship between measured and conceptual variables
- 2Reliability =Consistency
- 3Validity =accuracy in measuring
- 4Random Error and ReliabilityChance fluctuations in measured variables
Not Systematic - 5Some sources of random error:Misreading or misunderstanding of the questions
Measurement of individuals on different days or in different places
Experimenter misprints the questions or makes errors recording responses
Individuals mark answers incorrectly - 6Systematic Error and Validitythe measured variable is influenced by other conceptual variables that are not part of the conceptual variable of interest
systematically increase or decrease the scores on the measured variable
Occurs throughout study or on regular basis - 7ReliabilityThe extent to which a measure is free from random error
Cronbach’s Alpha Reliability Coefficient (α) - 8Approaches to assessing reliabilityTest-retest reliability
Equivalent-forms reliability
Interrater reliability
Intrarater reliability - 9Test-Retest ReliabilityExtent to which scores on the same measure correlate with each other
High correlation = high reliability
administered at two different times - 10Test-Retest Reliability: ConcernsRetesting effects
responses on the second administration may be influenced by the measure having been taken the first time - 11Equivalent-forms ReliabilityEquivalent-forms reliability
Extent to which scores on similar, but not identical, measures, administered at two different times, correlate with each other - 12Interrater reliabilityExtent to which the ratings of more than one examiners correlate with each other
- 13Intrarater reliabilityExtent to which the ratings of one examiner correlate over time
- 14Construct validityExtent to which a measured variable actually measures the conceptual variable it is designed to assess
- 15Types of Construct validity:Face validity
Content validity
Convergent validity
Discriminant validity - 16Face ValidityExtent to which the measured variable appears to be an adequate measure of the conceptual variable
Does it make sense? - 17Content ValidityDegree to which the measured variable appears to have adequately sampled from the potential domain of questions that might relate to the conceptual variable of interest
Looks at the conceptual variable in its entirety? - 18Improving Reliability and ValidityPilot testing
Use multiple measures
Write good items
Attempt to get respondents to take questions seriously
Attempt to make items nonreactive
Consider face and content validity
When possible, use existing measures
Cronbach Alpha!