"qualitative inquiry is inductive and often iterative in that the evaluator may go through repeated cycles of data collection and analysis to generate hypotheses inductively from the data. These hypotheses, in turn, need to be tested by further data collection and analysis. The researcher starts with a broad research question, such as 'What effects will information systems engendered by reforms in the UK’s National Health Service have on relative power and status among clinical and administrative staff in a teaching hospital?' .The researcher narrows the study by continually posing increasingly specific questions and attempting to answer them through data already collected and through new data collected for that purpose. These questions cannot all be anticipated in advance. As the evaluator starts to see patterns, or discovers behavior that seems difficult to understand, new questions arise. The process is one of generating hypotheses and explanations from the data, testing them, and modifying them accordingly. New hypotheses may require new data, and, consequently, potential changes in the research design."
(Bonnie Kaplan and Joseph A. Maxwell, p.38, 2005)
Kaplan, B. and J. Maxwell (2005). Qualitative Research Methods for Evaluating Computer Information Systems. Evaluating the Organizational Impact of Healthcare Information Systems. J. Anderson and C. Aydin. New York, Springer: 30-55.
"To say you will engage in purposive sampling signifies that you see sampling as a series of strategic choices about with whom, where and how to do your research. Two things are implicit in that statement. First is that the way that you sample has to be tied to your objectives. Second is an implication that follows from the first, i.e., that there is no one “best” sampling strategy because which is “best” will depend on the context in which you are working and the nature of your research objective(s).
Purposive sampling is virtually synonymous with qualitative research. However, because there are many objectives that qualitative researchers might have, the list of “purposive” strategies that you might follow is virtually endless, and any given list will reflect only the range of situations the author of that list has considered."
(Ted Palys, 2008)
Palys, T. (2008). "Purposive Sampling". The SAGE Encyclopedia of Qualitative Research Methods. Lisa M. Given. London, SAGE Publications, Inc. 1&2.
"This article defines and describes the rich variety of research designs found in librarianship and informatics practice. Familiarity with the range of methods and the ability to make distinctions between those specific methods can enable authors to label their research reports correctly. The author has compiled an inventory of methods from a variety of disciplines, but with attention to the relevant applications of a methodology to the field of librarianship. Each entry in the inventory includes a definition and description for the particular research method. Some entries include references to resource material and examples."
(Jonathan D. Eldredge, 2004, Journal of the Medical Library Association)
"What are your beliefs about how valid knowledge can be obtained? This will influence your approach to your research. If you are a positivist, for example, (who believes that valid knowledge can be obtained through a scientific approach), you are likely to choose a quantitative research method that begins with a theory and tests that theory. If you favour the social constructivist view that meaning is subjective, gained through interactions with others, you would be more likely to choose qualitative research methods that explores themes. Qualitative research is about generating theory and finding patterns of meaning."
(Centre for Academic Development and Quality, Nottingham Trent University)
"qualitative research first involves studying the meaning of people’s lives, under real-world conditions. People will be performing in their everyday roles or have expressed themselves through their own diaries, journals, writing, and even photography - entirely independent of any research inquiry. Social interactions will occur with minimal intrusion by artificial research procedures, and people will be saying what they want to say, not, for example, limited to responding to a researcher’s preestablished questionnaire. Likewise, people will not be inhibited by the confines of a laboratory or any laboratory-like setting. And they will not be represented by such statistical averages as the average American family having 3.18 persons (as of 2006) - which at once may represent accurately an entire population but in fact by definition does not speak to any single, real-life family.
Second, qualitative research differs because of its ability to represent the views and perspectives of the participants in a study. Capturing their perspectives may be a major purpose of a qualitative study. Thus, the events and ideas emerging from qualitative research can represent the meanings given to real-life events by the people who live them, not the values, preconceptions, or meanings held by researchers.
Third, qualitative research covers contextual conditions - the social, institutional, and environmental conditions within which people’s lives take place. In many ways, these contextual conditions may strongly influence all human events. However, the other social science methods (except for history) have difficulty in addressing these conditions.
Experiments, for instance, 'control out' these conditions (hence the artificiality of laboratory experiments). Quasi-experiments admit such conditions but by design nevertheless focus only on a limited set of 'variables,' which may or may not fully appreciate the contextual conditions. Similarly, surveys are constrained by the need to manage carefully the degrees of freedom required to analyze the responses to a set of survey questions; surveys are therefore limited in the number of questions devoted to any contextual conditions. History does address contextual conditions, but in its conventional form studies the 'dead past,' not ongoing events as in qualitative research (refer again to footnote 1 about oral history).
Fourth, qualitative research is not just a diary or chronicle of everyday life. Such a function would be a rather mundane version of real-world events. On the contrary, qualitative research is driven by a desire to explain these events, through existing or emerging concepts. For instance, one existing concept is Goffman’s (1963) stigma management. In his original work, stigma management largely pertained to adaptations by individual people. However, a contemporary qualitative study applied his typology and framework to a collective group, thereby offering new insights into how the actions of nation-states also might try to overcome their own historically stigmatizing events"
(Robert K. Yin, p.8,9)
1). Robert K. Yin (2011). "Qualitative Research from Start to Finish", The Guilford Press.