Summary Chapter 18 Bryman

Chapter 18
Sampling in qualitative research


Introduction
What is a sample:

 A subset of the population, selected by either probability or nonprobability methods

Criteria for probability sampling:

1. If it is highly significant or NB for the qualitative researcher to be able to generalize to a
wider population – probability sampling more compelling approach
2. If the research questions don’t suggest that particular categories of people should be
sampled- there may be a case for sampling randomly

Why qualitative researchers generally don’t use random sampling:

 They want to ensure that they gain access to a wide range of individuals relevant to
their research questions
 So that many different perspectives & ranges of activity are the focus of attention

What can be sampled:

 People / individuals
 Time (when will you be ‘observing’ – vary this)
 Space (where…?)
 Readings / ideas from formal literature
 Discourse (segments: words / paragraphs)
 Objects / artefacts /media
 Events



Levels of sampling
Two levels of sampling:

1. Sampling of context
2. Sampling of participants



1

,Purposive sampling
What is purposive sampling:

 Non-probability form of sampling
 Researcher doesn’t seek to sample research participants on a random basis
 Goal = to sample cases/participants in a strategic way, so that those sampled are
relevant to the research questions that are being posed
 To ensure that there is a good deal of variety in the resulting sample
 Because it is a non-probability approach generalization is not possible

Purposive sampling approaches:

1. Extreme or deviant case sampling
 Sampling cases are unusual
2. Typical case sampling
 Sampling a case because it exemplifies a dimension of interest
3. Critical case sampling
 Sampling a crucial case that permits a logical inference about the phenomenon
of interest
4. Maximum variation sampling
 Sampling to ensure as wide a variation as possible i.t.o the dimension of interest
5. Criterion sampling
 Sampling all units that meet a particular criterion
6. Theoretical sampling
 The process of data collection for generating theory whereby the analyst jointly
collects, codes & analyses his data & decides what data to collect next & where
to find them in order to develop his theory as it emerges
 Emphasizes theoretical saturation as a criterion for deciding when to cease
collecting new data on a particular theoretical idea & to move on to the
investigation of some ramification of the emerging theory
 Theoretical saturation
o Key idea is that you carry on sampling theoretically until a category has
been saturated with data
o Until no new or relevant data seem to be emerging regarding a category
o The category is well developed i.t.o its properties & dimensions
demonstration variation
o The relationships among categories are well established & validated

2

, 7. Snowball sampling
 The researcher samples initially a small group of people relevant to the research
questions
 These sampled participants propose other participants who have had the
experience/ characteristics relevant to the research
8. Opportunistic sampling
 Capitalizing on opportunities to collect data from certain individuals, contact
with whom is largely unforeseen but who may provide data relevant to the
research question
9. Stratified purposive sampling
 Sampling of usually typical cases or individuals within subgroups of interest


Generic purposive sampling:

 Relatively open ended & emphasizes the generation of concepts & theories but doesn’t
entail the iterative style of grounded theory
 Sampling is conducted purposively but not necessarily with regard to the generation of
theory & theoretical categories
 The researcher establishes criteria concerning the kinds of cases needed to address the
research questions, identifies appropriate cases & then samples from those cases that
have been identified

3