1. Communication Arts Research CA3011(2/2014)
A. Parichart W.

2. Data Analysis in Qualitative Research

3. Outlines The Tool for qualitative data analysis
The phases of qualitative data analysis

4. Tools for Analysis 1. Manual Methods
Instruments used in the study(e.g. interview guides)
Summary information about the sample of cases (e.g. demographic information of participants)
Codebook
In-process memos
Theoretical memos
Coded texts (which may be subdivided into sections based type of data—fieldnotes, interview transcription, documents, etc.)

5. Tools for Analysis
2. Computer-Assisted Qualitative Data Analysis Software (CAQDAS)
Nvivo  see example on youtube

6. Before you begin, you should carefully interpret your data.
Interpretation
It involves the translation of an object of analysis from one frame of meaning into another.
Two boys contract the eyelids of their right eyes.
Winking = sorts winks from twitches
A sign of conspiracy = mimicking another person’s wink

7. The Phases of Qualitative Data Analysis by Miles and Huberman (1994)

8. Step 1 and Step 2

9. Preparing the Data: 1)Reduction and 2) Display
The researcher generally first organizes the info. Along a temporal dimension. In other words, the data are arranged in chronological order according to the sequence of events that occurred during the investigation.
Multiple photocopies and computer files of the notes, transcripts, and other documents should be made.
The data are then organized into a preliminary category system. These categories might arise form the data themselves, or they might be suggested by prior research or theory. When the process is finished, a preliminary category system may have emerged from the data.
Many researchers prefer to do a preliminary run-through of the data and jot possible category assignment.

10. Preparing the Data: 1)Reduction and 2) Display
Other researchers prefer to make multiple copies of the data, cut them into coherent units of analysis, and physically sort them into as many categories as might be relevant.
Finally, some of the toil in qualitative data analysis can be made easier by commercial software programs e.g. NVIVO
Finally, the researcher is the main instrument in qualitative data collection and analysis and therefore must prepare before beginning the task of investigation.

11. Step 3

12. 3) Data Analysis: Conclusion Drawing
Qualitative data can be analyzed with many different techniques. This section discusses two of the best known:
The constant comparative technique ( was first articulated by Glaser and Strauss (Lincoln & Guba, 1985). The process consists of FOUR steps:
Comparative assignment of incidents to categories
Elaboration and 1967) and has subsequently been refined (refinement to of categories)
Searching for relationships and themes among categories
Simplifying and integrating data into a coherent theoretical structure
An explanation is derived as the result of the research

13. Conclusion Drawing: 1. Comparative assignment of incidents to categories
The researcher places each unit of analysis into a set of provisional categories.
As each new unit is examined, it is compared to the other units previously assigned to that category to see whether its inclusion is appropriate.
It is possible that some initial categories may have only one or two incidents assigned to them while others may have a large number.
If some units of analysis do not fit any preexisting category, new classifications may have to be created.
Units that fit into more than one category should be copied and included where relevant.
The emphasis if on comparing units and finding similarities among the units that fit into the category.

14. Example Qualitative Research: Why individuals join social network such as Facebook
“Keeping in touch with current friends” “Finding out what old high school acquaintances are doing” “Not wanting to be left out”
Categories
Interpersonal connections
Peer Pressure

15. Conclusion Drawing: 2. Elaboration and Refinement of Categories
The researcher writes rules that attempt to describe the underlying meaning that defines the category.
These rules help to focus the study and also allow the researcher to start to explore that theoretical dimensions of the emerging category system.
The ultimate value of these rules, however, is that they reveal what the researcher learns about a chosen topic and help determine the research outcome.

16. Example: Rule/proposition
Category “Interpersonal connections” Proposition “People subscribe to social networking websites to expand their circle of casual friends.”

17. Conclusion Drawing: 3. Searching for Relationships and Themes among categories
The phase involves searching for relationships and common patterns across categories.
The researcher examines the propositional statements and looks for meaningful connections.
Some propositions are probably strong enough to stand alone; others might be related in several important ways.
The goal of this phase is to generate assertions that can explain and further clarify the phenomenon under study.

18. Example
The researcher might note that several propositions refer to the notion of expansion.
The analyst then generalizes that the expansion of one’s social and cultural space is an essential reason for joining.
People use the social network sites to expand their circle of friends.
People use the social network sites to expand their sources of music.
People use the social network sites to expand the no. of groups to which they belong.

19. Conclusion Drawing: 4) Simplifying and Integrating data into a coherent theoretical structure
In the final phase, the researcher writes a report that summarizes the research.
All the results of the foregoing analyses are integrated into some coherent explanation of the phenomenon.
The researcher attempts to write a brief explanation, but in sufficient detail to convey an idea of the scope of the project.
The goal of this phase of the project is to arrive at an understanding of the people and events being studied.

20. Analytic Induction Strategy (in conclusion drawing)

21. The Analytic Induction Strategy
It blends hypothesis construction and data analysis. It consists of the following steps (adapted from Stainback & Stainback 1988):
1. Define a topic of interest and develop a hypothesis.
2. Study a case to see if the hypothesis works. If it doesn’t work, reformulate it.
3. Study other cases until the hypothesis is in refined form.
4. Look for “negative cases” that might disprove the hypothesis. Reformulate again.
5. Continue until the hypothesis is adequately tested.
This process can be exhausting, and it can be difficult for the researcher to determine an exact stopping point (til no more case can be support the revised hypothesis..

22. Example Why do people watch home-shopping channels.
People watch because they want to buy the merchandise. (initial hypothesis)
People watch because to find out about new and unusual products. (from heavy viewer)
People watch because the similar reason and for comparison shopping. (refined hypothesis)
The researcher posits that the home-shopping channels are viewed for practical consumer-related reasons: finding bargains, learning about products, and comparing prices.
The initial hypothesis is modified to take this finding into account. At this point, the researcher tries to find cases that might not fit the new hypothesis.

23. Step 4

24. 4) Verification : Reliability and Validity in Qualitative Data
Qualitative researchers must pay attention to several different concerns that may call the credibility of their research into question.

25. Problems
The first problem concerns if qualitative researchers do a sloppy job taking notes or otherwise recording what was observed, there is a possibility that incorrect interpretations may be drawn from the data.
A second problem concerns selective perception. Qualitative researchers can not simply dismiss data that do not fit a favored interpretation of the data. They must analyze these cases and offer explanations as why the data don’t seem to fit.

26. Problems
The third problem, qualitative research often raises the question of reactivity- when the act of observing some situation changes the situation itself. Would the same things have occurred if researchers were not there?
Reactivity is a difficult problem to overcome, but researchers must try to minimize it whenever possible.

27. Four Factors that help build credibility
Rather than emphasizing reliability and validity, Maykut and Morehouse (1994) address the trustworthiness of a qualitative research project.
Multiple methods of data collection.
The use of interviews along with field observations and analysis of existing documents suggests that the topic was examined from several different perspectives, which helps build confidence in the findings.
It is similar to the notion of triangulation.

28. Four Factors that help build credibility (contd.)
2. Audit Trail. This factor is essentially a permanent record of the original data used for analysis and the researcher’s comments and analysis methods. The audit trail allows others to examine the thought processes involved in the researchers’ work and allows them to assess the accuracy of their conclusions.

29. Four Factors that help build credibility (contd.)
3. Member checks. In this technique, research participants are asked to read a researcher’s notes and conclusions and tell whether the researcher has accurately described what they were told.

30. Four Factors that help build credibility (contd.)
4. Research team. This method assumes that team members keep each other honest and on target when describing and interpreting data. When appropriate, an outside person is asked to observe the process and raise questions of possible bias or misinterpretation.

31. Thank you for your attention