Qualitative data analysis

MICHAEL MUZENDA 20/25 Well articulate. However, a few demits on the topic were a necessity. Data analysis is the process of reducing a large amount of responses or raw data into meaningful data and to make use of it. Qualitative data analysis can be categorised into the following content analysis, discourse analysis, or grounded theory. Qualitative data analysis can be conducted through the following steps: organising the data, finding and organising ideas and concepts, building overarching themes in the data, ensuring reliability and validity in the data analysis and in the findings and finding possible and plausible explanations for findings. However, the principle of reliability and validity must be followed from the beginning of the research up to the end of the research and protecting the identity of the participants during triangulation must be taken into consideration. Qualitative data means non-numeric information such as interview transcripts, notes, video and audio recordings, images and text documents. Qualitative data analysis can be used in situations where the researcher has a large amount on unquantifiable data such as transcripts, interview notes audio recordings or pictures, (Walliman,2017). Walliman, (2017) noted that qualitative data analysis can be divided into the following five categories which are as follows: 1. Content analysis. This refers to a method of categorising verbal or behavioural data to organise, summarise and tabulate the data. 2. Narrative analysis. This technique encompasses the reformulation of stories presented by respondents taking into account context of each case and different experiences of each respondent. In other words, narrative analysis is the revision of primary qualitative data by researcher. 3. Discourse analysis. This denotes to analysis of naturally occurring dialogue and all types of written text. 4. Framework analysis. This is more advanced technique that comprises of numerous phases such as familiarisation, classifying a thematic framework, coding, plotting, mapping and interpretation. 5. Grounded theory. This process of qualitative data analysis starts with an examination of a single case to formulate a theory. Then, additional cases are examined to see if they add to the theory. According to O'Connor and Gibson, (2003), qualitative data analysis can be conducted through the following steps: Step 1: Organizing the Data The first step towards conducting qualitative analysis of collected data is to gather all the comments and feedback to be analysed. This data might be captured in different formats such as on paper or notes or in online forums and surveys, so it is important to get all the content into a single place. O'Connor and Gibson, (2003), noted that data should be organized in a way that is easy to look at, and that allows the researcher to go through each topic to pick out concepts and themes. One way to do this is to organize all the data for example from the transcript and make a chart. One might also consider a master spreadsheet as a place to collect all of these feedbacks. Thus, "valid analysis is immensely aided by data displays that are focused enough to permit viewing of a full data set in one location and are systematically arranged to answer the research question at hand,” (Huberman and Miles, 1994, p. 432). These methods of organising and displaying the data allows the researcher to look at the responses to each topic and specific question individually, in order to make it easier to pick out concepts and tthemes,(Rubin and Rubin, 1995). For example the researcher may carry out a research on the topic effects of Covid 19 among families and communities and ask questions to Covid 19 survivors like whom they told and how they reacted. The interviewees may give the following responses; " I told my boss and my family were worried and scared. They were worried about me and they were worried that they may also get sick. My boss was also worried about him and other employees of getting sick too...” The researcher may use chart as a place to collect all of these feedbacks and it may look like the one bellow: Topics Respondent A Respondent B Notes Effect of Covid 19 to families and communities Personal experiences How do you feel when you first know that you have Covid 19? I was scared what was going to happen to me. I was also scared what others would think and what their reaction would be especially my family and I did not want to make other people sick, so I avoided to go to places where I might give other people Various answers / responses as in respondent A are written here A list of recurring words, ideas, concept, themes eg from this response the main theme is worry Topics Respondent A Respondent B Notes Effect of Covid 19 to families and communities Perception of Covid 19 in the family and community How has having Covid 19 affected your life? It was difficult because I was supposed to leave in my own room and my family were to be careful not to touch anything that I touched to avoid getting sick Various answers / responses as in respondent A are written here A list of recurring words, ideas, concept, themes e.g in this case the main theme is Feeling of being infectious Source: O'Connor and Gibson,( 2003) Once the data are organized, the researcher can move onto the next step of picking out ideas and concepts and organizing them into categories, (O'Connor and Gibson, 2003). Step 2: Finding and Organizing Ideas and Concepts The next step in this process is about coding the ccomments and most importantly reading and making a decision about how each one should be organised. Creswell (2007) and Creswell (2012) defined coding as the process of fragmenting and categorising text to form clarifications and comprehensive themes in the data. Marshall and Ross, 1995, p. 114 noted that “Identifying salient themes, recurring ideas or language, and patterns of belief that link people and settings together is the most intellectually challenging phase of the analysis and one that can integrate the entire endeavor.” when going through different responses the researcher need to take note of recurring specific words or ideas. For example using the previous example of responses; " I told my boss and my family were worried and scared. They were worried about me and they were worried that they may also get sick. My boss was also worried about him and other employees of getting sick too...” the main reaction or theme is worry about the interviewee and the family. The boss is also worried about himself and other employees of contracting the disease. However, different people the researcher for example is interviewing may express themselves differently as the researcher could do. Thus, the way they express themselves can reflect attitudes and behaviours, so the researcher needs to pick words and expressions used frequently that might sound differently than how the researcher and others would express them. O'Connor and Gibson, (2003), noted that this is particularly important when doing cross-cultural interviews because the researcher needs to understand what is meant by certain expression and to understand the underlying implications of those expressions. This is important because every language and culture have different expressions which means different than what the researcher might consider to be the obvious meaning. Once the researcher has identified words or phrases frequently used by the respondents the researcher now has to organise these themes into categories or codes. Using the same example of the topic given above the researcher may categories the data as follows: Question/topic Responses Categories How do you feel when you first know that you have Covid 19? I was scared what was going to happen to me. I was also scared what others would think and what their reaction would be especially my family and I did not want to make other people sick, so I avoided to go to places where I might give other people Concern about not making healthy recovery Concern over other people's reactions How has having Covid 19 affected your life? It was difficult because I was supposed to leave in my own room and my family were to be careful not to touch anything that I touched to avoid getting sick Feeling of being infectious Source: O'Connor and Gibson, (2003) Step 3: Building Over-Arching Themes in the Data After categorising the data, each of the category has one or more associated theme that can give a deeper understanding of the data, so different categories can be collapsed under one main over-arching theme, (O'Connor and Gibson, 2003). For instances from the above examples of responses the over-arching theme is Isolation. The interviewee was forced to stay in his /her room so that he does not infect others, he also avoid to go out to places where people gather and the family members were also avoiding to touch everything he touches before disinfecting them to avoid getting sick too. Step 4: Ensuring Reliability and Validity in the Data Analysis and in the Findings Validity can be defined as the accuracy with which the method measures what it is intended to measure and yield data that really represent reality or the real situation or phenomenon, (Schopper et al., 1993). Validation is an ongoing principle which not needs to be observed only on this stage but throughout the whole research process. Reliability is defined as the consistence of research findings, (Kvale, 1996). The findings are validated through triangulation. Findings can be confirmed to be valid or dependable when they are confirmed from different independent sources. Their validity are also confirmed when they are confirmed by more than one instrument measuring same thing. Triangulation can be done by interviewing different members of the community who can give different perspectives on the same question or topic. Triangulation can be done by using different research method like focus group, interviews and surveys. it can also be done by comparing data found by two different researchers carrying same research, ( O'Connor and Gibson, 2003). After triangulation the researcher may find out that the data obtained is the same which means the data is both reliable and valid. The data can be inconsistence or conflicting and this means that there were things missed in the original data collection process. Sometimes it means that the researcher's assumptions were off base, and that he or she needs to change questions or do more research, (O'Connor and Gibson, 2003). The researcher can also go back to the interviewees with the results to confirm if he or she correctly interpreted the data. Thus, Denzin, (1978), noted that local informants can act as judges evaluating the major findings of the study and this can be done through focus groups. Data can be also validated through comparing the themes and categories the researcher created or extracted with those of other researchers who are carrying out the same research to see if they came up with similar responses, themes and categories. This validation is called external validation,( O'Connor and Gibson, 2003). However, this must be done keeping in mind to protect the identity of participants. After the data have been tested for validity and reliability the next stage is now to find possible and plausible explanation of the findings. Step 5: Finding Possible and Plausible Explanations of the Findings The final stage of qualitative data analysis after the data passed the validity and reliability test is to seek patterns, ideas, associations and explanations within the knowledge provided (Bryman, 2016). The researcher will start by summarising the themes from the findings. O'Connor and Gibson, (2003), noted that the researcher will be asking himself or herself the following questions: are these findings what he or she was expecting, based on the literature? , were there any major surprises in the findings? and how are they different or similar to what is stated in the literature or from other similar studies? O'Connor and Gibson, (2003), also state that the researcher at this stage need to go back to literature review and compare his or her findings. This will help the researcher to come up with explanations for the findings. They also argue that key informant can also help to give obvious answer which they only know as insiders to why certain responses were given by participants. They also further note that observation and personal notes the researcher took during research also help the researcher to get explanation why he or she get such responses. However, "it is important to relate the findings back to the context of the cultural experience within each respective community. This is not only important in terms of finding explanatiions for the results, but also in terms of findings’ implications for that community. The implications of the findings are an important part of the final report", (O'Connor and Gibson, 2003, P.77). In summation, qualitative data analysis can be categorised into the following categories: content analysis, discourse analysis, or grounded theory. Qualitative data analysis can be conducted through the following steps: organizing the data, finding and organizing ideas and concepts, building overarching themes in the data, ensuring reliability and validity in the data analysis and in the findings and finding possible and plausible explanations for findings. However, the researcher needs to constantly relate the findings back to the context of the cultural experience within each respective community. Reference list Bryman, A. (2016). Social research methods: Oxford University Press; 5th edition. Creswell, J. W. (2007). Qualitative Inquiry and Research Design: Choosing Among Fire Traditions (2nd edition ed.). California, U.S.A: SAGE Publications. Creswell, J. W. (2012a). Educational Research: Planning, Conducting, and Evaluating Quantitative and Qualitative Research (4th Edition, International edition ed.): PEARSON Publications. Denzin K.N. and Y.S. Lincoln,(1994). Handbook of Qualitative Research: Sage Publications, Thousand Oaks, California. Kvale, S. (1996). Interviews: Sage Publications, Thousand Oaks California. Marshall, C. and G. Rossman,(1995). Designing Qualitative Research: Sage Publications, Thousand Oaks California. Miles, H.B., and A.M. Huberman,(1994). Qualitative Data Analysis: Sage Publication, Thousand Oaks California O'Connor. H. and Gibson, N, (2003).A Step-By-Step Guide To Qualitative Data Analysis available at https:///www.researchgate.net (accesed 10/06/2021). Rubin, J, H. and S.J. Rubin, (1995). Qualitative Interviewing, the Art of Hearing Data: Sage Publications, Thousand Oaks California Schopper D, Doussantousse S, Orav J. Sexual behaviors relevant to HIV transmission in a rural African population: how much can a KAP survey tell us. Soc Sci Med. 1993;37(3):401–412. 10.1016/0277-9536(93)90270-E. Walliman, N, (2017).Research Methods: The Basics: 2nd edition: Taylor & Francis: Oxford Brookes University FACULTY OF ARTS Department of Development Studies NAME: MUZENDA MICHAEL REG NUMBER: R135676T MODULE NAME: MADS 734 ADVANCED SOCIAL RESEARCH METHODS LECTURER: Dr V.S. NYATHI Question: Using relevant examples, discuss how you would carry your qualitative data analysis collected from the field. Due date: 14 June 2021