The Nature of Quantitative Research

1
The Nature of Quantitative Research

• Chapter 3

2
Overview

• Stages of quantitative research
• Conceptualization and measurement
• Reliability
• Validity
• Main preoccupations of quantitative researchers

3

• Criticisms of quantitative research
• Gap between the ideal and the actual

4
The Stages of Quantitative Research

• Theory/hypothesis
• Research design
• Devise measures of concepts
• Select site and sample
• Collect data
• Code and analyze data
• Write up

5
A basket of concepts

• Femininity/Masculinity

Body image
Household division of labour
Sexual harassment
Women and Girls
Glass ceiling
Patriarchy
Feminism
Gender Inequality
Gender
Boys and Men
6
Concepts and Conceptualization

• Concepts categories for the organisation of
  ideas and observations (Bulmer, 1984 43)
• May provide explanations of social phenomena
• May represent things we want to explain
• Conceptualization the process of specifying
  what is meant by a term

7
Measurements. . .

• delineate fine differences between people/cases.
• are consistent and reliable.
• are more precise estimates of the degree of
  relatedness between concepts.

8
Indicators of Concepts

• Produced by the operational definition of a
  concept and are less directly quantifiable than
  measures
• Common-sense understandings of the form a concept
  might take
• Multiple-indicator measures
• concept may have different dimensions
• example commitment to work

9

• How to measure the concept of Keeping up in a
  course?
• Direct measures?
• Indicators?
• Dimensions?
• Can we research a concept without using any
  measures or indicators?
• (e.g. poverty, body image, intelligence, etc.)

10
Reliability

• Stability over time
• test-retest method (correlation between measure
  on different occasions)
• Internal reliability
• split-half method (correlation between measures
  on two halves of a scale)
• Cronbachs alpha

11

• Inter-observer consistency
• agreement between different researchers

12
Measurement Validity

• Face validity
• Concurrent validity
• Construct validity
• Convergent validity
• Validity presupposes reliability (but not vice
  versa). Why is this?

13
Main Preoccupations of Quantitative Researchers

• 1. Measurement
• Can a concept be quantified?
• Comparisons between measures
• Changes in a variable over time
• 2. Causality
• Explanations of social phenomena
• Causal relationships between independent and
  dependent variables
• Inference only in cross-sectional designs

14

• 3. Generalization
• Can the results be applied to individuals beyond
  the sample?
• Aims to generalize to target population
• Requires representative sample (random,
  probability sample)

15

• 4. Replication
• Detailed description of procedures allows other
  researchers to replicate study
• Low incidence of published replications

16
Criticisms of Quantitative Research

• Failure to distinguish between objects in the
  natural world and social phenomena
• Artificial and false sense of precision and
  accuracy
• presumed connection between concepts and measures
• respondents make different interpretations of
  questions and other research tools

17

• Lack of external validity
• reliance on instruments and measurements
• little relevance to participants everyday lives
• variation in the meaning of concepts to each
  individual

18

• Static view of social life
• reduced to relationships between variables
• ignores processes of human definition and
  interpretation (Blumer, 1956)

19
The Gap Between the Ideal and the Actual

• Quantitative research design is an ideal-typical
  approach
• Useful as a guide to good practice but there is a
  discrepancy between ideal type and actual
  practice of social research
• Pragmatic concerns mean that researchers may not
  adhere rigidly to these principles

20
How does quantitative research sometimes depart
from the principles of good practice?

• Three examples

21
1. Reverse operationalism

• Quantitative research is usually deductive
  (operational definition of concepts), but
  measurements can sometimes lead to inductive
  theorizing (Bryman, 1988)
• example factor analysis
• groups of indicators cluster together and suggest
  a common factor
• e.g. personality trait research

22
2. Reliability and validity testing

• Published accounts of quantitative research
  rarely report evidence of reliability and
  validity (Podsakoff Dalton, 1987)
• Researchers are primarily interested in the
  substantive content and findings of their
  research
• Tests of reliability and validity are often
  neglected

23
3. Sampling

• Good practice in quantitative research calls for
  probability sampling
• Sometimes it may not be possible to obtain a
  probability sample due to lack of time, lack of
  resources, or the nature of the population.

24

• Despite the inevitable shortcomings of actual
  projects peer review helps ensure that
  quantitative researchers remain committed to the
  principles of good practice.