measurement concepts © 2012 the mcgraw-hill companies, inc
TRANSCRIPT
MEASUREMENT CONCEPTS
© 2012 The McGraw-Hill Companies, Inc.
Define reliability of a measure of behavior and describe the difference between test-retest, internal consistency, and interrater reliability
Discuss ways to establish construct validity, including predictive validity, concurrent validity, convergent validity, and discriminant validity
© 2012 The McGraw-Hill Companies, Inc.
Describe the problem of reactivity of a measure of behavior and discuss ways to minimize reactivity
Describe the properties of the four scales of measurement: nominal, ordinal, interval, and ratio
© 2012 The McGraw-Hill Companies, Inc.
Consistency or Stability of a Measure of Behavior
True Score Measurement Error Pearson Product-Moment Correlation
Coefficient
© 2012 The McGraw-Hill Companies, Inc.
- 1.00 + 1.000.00
Variables covary in opposite directions
Variables covary in the same
direction
© 2012 The McGraw-Hill Companies, Inc.
Test-Retest Reliability Assessed by measuring the same individuals two points
in time Vulnerable to artificiality Vulnerable to maturation
Internal Consistency Reliability Split-half reliability Cronbach’s alpha
Correlation of each item on the measure all other items on the measure
Item-total correlations© 2012 The McGraw-Hill Companies, Inc.
Interrater Reliability Correlation between the observations of raters
Reliability and Accuracy of Measures Reliability indexes do not indicate whether a
particular measure is an accurate measure of the variable of interest
A measure can be highly reliable but not accurate
© 2012 The McGraw-Hill Companies, Inc.
Less error
© 2012 The McGraw-Hill Companies, Inc.
Indicators of Construct Validity Face validity Content validity
Predictive validity Concurrent validity Convergent validity Discriminant validity
© 2012 The McGraw-Hill Companies, Inc.
Face Validity The content of the measure appears to reflect the construct being measured
Content validity The content of the measure is linked to the universe of content that defines the construct
Predictive validity Scores on the measure predict behavior on a criterion measured at a time in the future
Concurrent validity Scores on the measure are related to a criterion measured at the same time (concurrently)
Convergent validity Scores on the measure are related to other measures of the same construct
Discriminant validity Scores on the measure are not related to other measures that are theoretically different
© 2012 The McGraw-Hill Companies, Inc.
Systematic and detailed research on validity is most often carried out on measures of personality and individual differences
Should use measures of personality that have demonstrable validity and reliability Example: Mental Measurement Yearbook
© 2012 The McGraw-Hill Companies, Inc.
Measure is reactive if awareness of being measured changes an individual’s behavior
Measures of behavior vary in terms of their potential reactivity
© 2012 The McGraw-Hill Companies, Inc.
Nominal Scales Ordinal Scales Interval and Ratio Scales The Importance of the Measurement Scales
© 2012 The McGraw-Hill Companies, Inc.
© 2012 The McGraw-Hill Companies, Inc.
Scale Description Example Distinction
Nominal Categories with no numeric scales
Males / femalesIntroverts / extroverts
Impossible to define any quantitative values
Ordinal Rank orderingnumeric values limited
2-, 3-, and 4-star restaurantsRanking TV programs by popularity
Intervals between items is unknown
Interval Numeric properties are literalAssume equal intervals between values
IntelligenceAptitude test scoresTemperature (Fahrenheit and Celsius)
No true zero point
Ratio Zero indicates absence of variable measured
Reaction timeWeightAge Frequency of behavior
Can form ratios (someone weighs twice as much as another)