The Analysis of Qualitative Data

1
REAL WORLD RESEARCHSECOND EDITION

• Chapter 14
• The Analysis of Qualitative Data

Robson, C.(2002) Real World Research

2nd edn. Oxford
Blackwell
2
Approaches to qualitative analysis

• Quasi-statistical approachesUse word or phrase
  frequencies and inter-correlations as key methods
  of determining the relative importance of terms
  and concepts typified by content analysis.
• Template approachesKey codes are determined
  either on an a priori basis or from an initial
  read of the data. These codes then serve as a
  template for data analysis typified by matrix
  analysis.

continued...
3
Approaches to qualitative analysis
(cont.)

• Editing approachesMore interpretive and flexible
  than the above, with no (or few) a priori codes
  typified by grounded theory approaches.
• Immersion approachesLeast structured and most
  interpretive, emphasizing researcher insight,
  intuition and creativity.

4
Deficiencies of the human as analyst

• Data overload
• First impressions
• Information availability
• Positive instances
• Internal consistency
• Uneven reliability

continued...
5
Deficiencies of the human as analyst
(cont.)

• Missing information
• Revision of hypotheses
• Fictional base
• Confidence in judgement
• Co-occurrence
• Inconsistency
• (from Sadler, 1981, pp.27-30)

6
Advantages of specialist QDA programmes

• They
• provide an organized single location storage
  system for all stored material.
• give quick and easy access to material (e.g.
  codes) without using cut and paste techniques.
• can handle large amounts of data very quickly.
• force detailed consideration of ALL text in the
  database on a line-by-line (or similar) basis.
• help the development of consistent coding
  schemes.
• (from Cresswell, 1998 pp.155-6)

7
Disadvantages of specialist QDA programmes

• Proficiency in their use takes time and effort.
• There may be difficulties in changing, or
  reluctance to change, categories of information
  once they have been established.
• Particular programmes tend to impose specific
  approaches to data analysis.
• (from Cresswell, 1998 pp.155-6)

8
Different types of matrix

• Checklist matrix
• Time-ordered matrix (a commonly used version is
  event listing)
• Role-ordered matrix
• Conceptually clustered matrix
• Effects matrix
• Case dynamics matrix

9
Different types of networks

• Context charts
• Event flow networks
• Activity records
• Decision modelling
• Conceptually ordered tree diagrams
• Cognitive map
• Causal network

10
Assessing data quality

• Checking for representativeness
• Checking for researcher effects
• Triangulation
• Weighting the evidence
• (from Miles and Huberman, 1994)

11
Testing patterns

• Checking the meaning of outliers
• Using extreme cases
• Following up surprises
• Looking for negative evidence
• (from Miles and Huberman, 1994)

12
Testing explanations

• Making if-then tests
• Ruling out spurious relationships
• Replicating a finding
• Checking out rival explanations
• Getting feedback from informants
• (from Miles and Huberman, 1994)