RM Ch. 3 Notes

• Variables


  Characteristics or conditions that change or have different values for different individuals
• Two important aspects of measurement:


  1. No one-to-one relationship between the variable measured and the measurements obtained

  2. Different methods to measure the same variable lead to different findings
• Nominal


  Label and categorize observations with no quantitative distinctions

  [Colors, political party, college major]
• Ordinal


  Categories organized in an ordered sequence in terms of size or magnitude

  [Year in school, placing in a race]
• Interval


  Ordered categories that are all intervals of the same size, arbitrary zero

  [Fahrenheit temperature (0 is not the absence of temp. and can be lower)]
• Ratio


  Interval scale with an absolute zero point (absence of variable), meaningful ratios

  [Height, weight, time]
• Construct


  Hypothetical attributes or mechanisms that help explain and predict behavior in a theory (cannot be directly observed or measured)
• The Operational Definition


  A method for measuring and defining a construct, Specifies a measurement procedure (a set of operations) for measuring an external, observable behavior
• The Operational Definition LIMITS


  Easily oversimplified, Often influenced by extraneous, unknown factors

  Check previous research for a "standard method
• Fixed-format


  Likert scale

  Semantic Differential

  Guttman Scale
• 3 Modalities of measurement


  self-report, physiological, behavioral
• self-report measure


  use questionnaire/interview. more direct way to assess construct
• Physiological Measure


  Measure the physiological manifestations of the construct (PET scanning, MRI)
• Physiological Measure LIMTIS


  Extremely objective, but expensive/unavailable equipment, unnatural settings
• self-report measure LIMTITS


  easy to distort
• Behavioral measures


  Measure the ways a construct reveals itself in observable

  behaviors

  (Frequency, duration, latency, intensity)
• Behavioral measures LIMITS


  measures may only be temporary or situational indicator of construct
• Reliability


  The stability or consistency of the measurement

  (Does it measure it consistently over time?)
• Validity


  The degree to which the measurement process measures the variable it claims to measure (Does this measure what it claims to be measuring?_
• Operationalization


  procedure for measuring and defining construct a researcher identifies behavior associated with construct, behavior is measured and resulting measurements used as definition and measure of the construct
• When is Reliability achieved?

  Achieved if the same individuals measured under the same conditions produce nearly identical measurements
• Inter-rater reliability


  Degree of agreement between two observers simultaneously recording measurements
• Internal consistency


  Degree of consistency between similar groups of items
• Split-half reliability


  Split items in a questionnaire in half, score each half, then calculate the consistency between two scores for a group of participants
• Test-retest reliability


  Measure the same individuals twice and calculate correlation between scores
• Parallel-forms reliability


  Alternate versions of the same measurement instrument
• Types of Reliability


  Inter-rater, Test-retest, Internal Consistency, Parallel Forms
• Face Validity


  Whether a measure superficially appears to measure what it claims to measure
• Concurrent validity


  Scores obtained from a new measure
• Predictive validity


  Scores obtained from a measure accurately predict behavior according to a theory
• Construct validity


  Scores obtained from a measurement behave exactly the same as the variable itself
• Convergent validity


  Strong relationship between the scores obtained from two (or more) different methods of measuring the same construct
• Divergent validity


  Showing little or no relationship between the measurements of two different constructs (discriminant validity)
• Sources of (Measurement) Error


  Observer error, Environmental changes, Participant changes
• Observer error


  The individual making the measurements can introduce simple human error (Use of stopwatches, forgetting to note something, etc.)
• Environmental changes


  Small changes to the environment that differ from one measurement to another (Time of day, lighting, temperature, etc.)
• Participant changes


  Characteristics of the participant that change between