Research methods in clinical psychology: An introduction for students and practitioners Chris Barker

1
Research methods in clinical psychologyAn
introduction for students and practitionersChris
Barker, Nancy Pistrang, and Robert Elliott

• CHAPTER 4
• Foundations of quantitative measurement

2
Operationalisation

• Construct Measure(s)
• Construct is latent
• (it can never be directly observed)
• Complications
• Theory dependence of measurement
• Reactivity of measurement

3
Examples of measures by source and approach
4
Quantitative methodsoverview

• General background
• positivism
• Psychometric theory
• reliability
• validity
• generalisability
• item response theory
• utility

5
Advantages of quantitative measures

• Precision
• Theory of reliability and validity
• Established statistical methods for data
  analysis
• Facilitates comparison
• Fits in well with hypothetico-deductive
  approaches

6
Positivism

• (August Comte)
• Restrict scientific attention to observables
• Apply the methods of the physical sciences to the
  social sciences
• Science is objective and value free

7
Psychometric theory

• How good is this measure?
• Theory of measurement

8
Scales of measurement

• Nominal
• unordered categories
• Ordinal
• order property only
• Interval
• ordinal plus equal intervals
• Ratio
• interval plus actual zero

9
Type of measure

• Nomothetic
• Compares across people, e.g., WAIS, BDI
• Idiographic
• Measures within the person, e.g., Q-sort,
  personal questionnaire

10
Classical test theory

• Classical test theory measurement model
• observed score true score error
• Underpins the concepts of reliability and
  validity

11
Reliability

• Reproducibility of the measurement
• do you obtain the same results each time?
• Equivalent to the proportion of error in the
  measurement

12
Types of reliability

• Test-retest reliability
• Equivalent forms reliability
• Split-half reliability
• no longer used
• Internal consistency
• assumes parallel items
• (Cronbachs alpha)
• Inter-rater reliability
• (Cohens kappa intraclass correlation)

13
Validity

• Meaning of the measure
• Whether the measure measures what it is supposed
  to measure.

14
Validity types 1

• Content validity
• consistency with definition of construct
• Face validity
• does it look right?
• Criterion validity
• compare to gold standard
• concurrent validity (present)
• predictive validity (future)
• sensitivity and specificity

15
Validity types 2Construct validity

• Cronbach Meehl (1955)
• validity is theory based
• Campbell Fiske (1959)
• convergent validity
• discriminant validity
• method variance
• multitrait-multimethod matrix

16
Suggested standards

• Reliability Validity
• Good .80 .50
• Acceptable .70 .30
• Marginal .60 .20
• Poor .50 .10

17
Alternative approaches

• Item response theory
• uses item characteristic curves
• e.g., Rasch Scaling
• Generalisability theory
• Cronbach
• uses an ANOVA framework

18
Utility

• General user friendliness
• e.g., length and layout
• Incremental utility
• what does the measure add?
• Cost-effectiveness