![6Sampling[1].ppt 6Sampling[1].ppt 6Sampling[1].ppt](https://image.slidesharecdn.com/6sampling1-250127151710-704b8b7a/85/6Sampling-1-ppt-6Sampling-1-ppt-6Sampling-1-ppt-11-320.jpg)
6Sampling[1].ppt 6Sampling[1].ppt 6Sampling[1].ppt
- 1. Sampling in Qualitative Sampling in Qualitative Research Research Sampling: Bounding the Collection of Data
- 2. Key features Key features Qualitative researchers usually work with small samples of people, nested in their context and studied in-depth. Tend to be purposive rather than random. Conceptually-driven sequential sampling- usually not wholly pre-specified, but can evolve once fieldwork begins.
- 3. Key features of qualitative sampling Key features of qualitative sampling Rich informative cases not representative Deep understanding not prediction
- 4. Typology of sampling strategies Typology of sampling strategies (Kuzel 1992; Patton 1990) (Kuzel 1992; Patton 1990) Types Purpose Maximum variation Homogeneous Critical case Theory-based Typical case sampling Document diverse variations and identifies important common pattern Focuses, reduces, simplifies, facilitates group interview Permit logical generalization and maximum application of information of other cases Finding example To illustrate, or highlights what is typical, normal, average
- 5. Typology of sampling strategies Typology of sampling strategies (Kuzel 1992; Patton 1990) (Kuzel 1992; Patton 1990) Types Purpose snowball or chain sampling (locate one or key indiv. and ask them to name other likely informants) Convenience sampling (selecting who ever easiest, closest) To facilitate the identification of cases of interest To save time, money, and effort, but information collected has very low creditability
- 6. How many is enough? How many is enough? Representation is the issue that most people concern. Criteria: – Research questions The bigger (question) the larger (number of samples) The more within-difference of the study site, the wider /more number of samples – Practicalability Money, time and resource available
- 7. How many and when is enough? How many and when is enough? No hard and fast rules for sample sizes in qualitative research. Sample size depends on – Purpose of the research – Specific questions to be addressed – What will be useful – What will have creditability – What can be done
- 8. How many and when is enough? How many and when is enough? In non-probabilistic sampling, the selection of informants continues to the point of redundancy- when no new information is being discovered. The no formulas for conducting sample size does not mean unsystematic. All decisions concerning sampling strategies and sample sizes should be clearly defined.
- 9. When is enough? When is enough? Nature of the phenomenon studied – How many households, families, social groups belief patterns exist in the community? Practicalability – Money, time and resource available
- 10. (the point of redundancy Saturation)
Editor's Notes
- #2: Unlike quantitative researchers, who aim for larger numbers of context-stripped cases and seek statistical significance. 2.Purposive rather than random. That tendency is partly because the initial definition of the universe is more limited (e.g., arrest-making in an urban precinct), and partly because social processes have a logic and a coherence that random sampling can reduce to uninterpretable sawdust. 3. Initial choices of informants lead you to similar and different ones; observing one class of events invites comparison with another; and understanding one key relationship in the setting reveals facets to be studied in others. This is conceptually-drien sequential sampling.
- #4: Sampling may look easy. Many qualitative research examines a single “case”, some phenomenon embedded in a single social setting. But settings have subsettings (schools have classrooms, classrooms have cliques, cliques have individuals), so deciding where to look is not easy. Within any case, social phenomena profilerate (science lessons, teacher questioning techniques, student unruliness, use of innovations); they too must be sampled. And the questions of multiple-case sampling add another layer of complexity. How to manage it all? Max vari: involves looking for outlier cases to see whether main patterns still hold. 2. Critical case: is the instances that “proves” or exemplifies the main findings