HTHSCI 3C04 Lecture Notes - Lecture 7: Nonprobability Sampling, Snowball Sampling, Qualitative Property
28 Apr 2018
School
Department
Course
Professor
UNIT VII/VIII: Critical Appraisal of Qualitative Research Designs
Qualitative research
Sampling, data collection and data analysis
- Basic decision is use of: existing data (records, historical data) or new data, collected specifically for research purposes
(interviews, observation)
- Most common data collection techniques are interviewing and participant observation
o Unstructured interviews are used when the researcher knows little about the topic
o Semi-structured interviews are used when the researcher has some idea of the questions to ask about a topic
o Participant observation is used to observe research participants in as natural a setting as possible; techniques
differ in the extent to which the researcher is visible and involved in the setting
Sampling in qualitative research
- Good qualitative enquiry leads to theoretical generalizability rather than statistical inference
- Sampling is driven by a set of concerns very different from those that drive quantitative designs; the purpose of
sampling is not to establish a random or representative sample drawn from a population but rather to identify specific
groups of people who either possess characteristics or live in circumstances relevant to the social phenomenon being
studied
- Informants are identified because they will enable exploration of a particular aspect of behaviour relevant to the
research
Non-probability sampling: a method of sampling that does not use a random selection; hallmark feature of qualitative research
- Purposeful sampling: selecting information rich cases, participants and settings
- Convenience or opportunistic sampling: involves choosing individuals who are easiest to access
- Homogenous sampling: select participants who can provide similar stories or narratives on phenomenon; selection may
be based on shared demographic or theoretical characteristics
- Heterogeneous or maximum variation sampling: researchers decide at the outset to select participants who can provide
different narratives or accounts of experiencing a phenomenon; often, selection is based on different demography or
theoretical characteristics
- Snowball sampling: used when no sampling frame exists or access to individuals in a frame might be difficult because
of cultural or social reasons; initial respondent is asked if they know of any other potential participants
- Theoretical sampling: aims to seek out data that challenge, and therefore develop, emerging ideas and hypotheses
revealed by previous data collection. Initial cases are sampled based on shared characteristics to gain a broad
understanding of the phenomenon under investigation. Then, individuals are sought who may prove exceptions to the
arguments being developed. When it is no longer possible to advance the arguments further (i.e. theoretical avenues of
inquiry are exhausted), a state of theoretical saturation is said to have been achieved
Tasks in qualitative data management and organization
- Transcribing the data; proof audio with transcription
- Developing a categorization scheme
- Coding qualitative data; researchers independently code, then compare to ensure they perceive the same codes
- Organizing qualitative data; manual methods or computerized methods
General analytic overview
- Coding (reduce the data into meaning units)
- Reassemble meaning units to understand the whole
- Identify themes or regularities
- Search for patterns among themes, variations in the data
- Validate themes, patterns
- Integrate thematic pieces
Qualitative data
- Analysis focuses on codes, themes and patterns in the data; use computer software programs to assist with coding and
analysis
- Research reports often contain direct quotes from participants that provide rich illustrations of themes; allows
researchers to generalize to a theoretical understanding of the phenomenon being examined
- Meta-study involves the analysis and synthesis of qualitative findings, methods, and theories of frame-works from
different studies to develop overarching or more conclusive ways of thinking about phenomena
Types of qualitative research: ethnography, phenomenology, grounded theory, life history, and case study
Phenomenology: seeks to unravel human experience and to examine the essential structures of phenomena; reduce the
phenomenon to its core essence; asks, what is the essence of a phenomenon and what does it mean?; 4 aspects of experience:
find more resources at oneclass.com
find more resources at oneclass.com
Document Summary
Unit vii/viii: critical appraisal of qualitative research designs. Basic decision is use of: existing data (records, historical data) or new data, collected specifically for research purposes (interviews, observation) Most common data collection techniques are interviewing and participant observation: unstructured interviews are used when the researcher knows little about the topic. Semi-structured interviews are used when the researcher has some idea of the questions to ask about a topic. Participant observation is used to observe research participants in as natural a setting as possible; techniques differ in the extent to which the researcher is visible and involved in the setting. Good qualitative enquiry leads to theoretical generalizability rather than statistical inference. Informants are identified because they will enable exploration of a particular aspect of behaviour relevant to the research. Non-probability sampling: a method of sampling that does not use a random selection; hallmark feature of qualitative research. Purposeful sampling: selecting information rich cases, participants and settings.
