You have worked several times with quantitative data and must have used several mathematical tools and methods to perform data analysis on the numbers and data. But there is also something called qualitative data – data which consists of words, texts, observations, and not numbers. Such data usually involve people and their activities, signs, symbols, artifacts and other objects they imbue with meaning. The most common forms of qualitative data are what people have said or done.
As with all data, qualitative data also can be analyzed and interpreted for better understanding. There are no variables and hypotheses in qualitative analysis and there is no one way to analyze this textual data. Qualitative analysis transforms data into findings and there is no fixed formula for the transformation. Some guidance and directions can be laid down, but the final destination and interpretation varies with the inquirer.
Common examples of such qualitative data are explanation and information gathered from these documents:
- Copy of the narration of an interview
- Field notes taken by a student doing a research or finding
- Transcript of video and audio recordings
- Interpretation of images
- Documents which may consist of reports, minutes of meeting, e-mails, and so on
What is Qualitative Data Analysis (QDA)?
Qualitative Data Analysis (QDA) is the range of processes and procedures used on the qualitative data that have been collected to transform them into some form of explanation, understanding or interpretation of the people and situations that are being investigated.
QDA is usually based on an interpretative philosophy. The intention behind qualitative analysis is to answer the ‘why’, ‘what’ and ‘how’ questions, and to examine the meaningful and symbolic content of qualitative data.
For example, students doing research on finding facts about the correlation between age and attitude to comply with dietary regulations may ponder on these questions or perform these actions to answer to their questions:
- Why are some patients with diabetes reluctant to comply with dietary advice?
- Why are older people more compliant to follow dietary advice than younger ones?
- Why obese patients cannot cut down on the intake of fatty foods?
- Is financial status and education related to the attitude of compliance?
- Interview people in more depth about their lifestyles
- Observe and write down their behavior over a period of time
- Find out what problems the participants face while trying to comply with a healthier food habit
The researcher can find quantitative data on some of the above questions. But drawing inferences on the basis of interviews, observations, and analysis of the real life experiences of the sample group will be part of the qualitative analysis process.
Process of QDA
The process of QDA mainly involves the following procedures or steps. But some approaches, such as dialogue analysis may not require identification of themes. But in majority of QDA, finding themes is still carried out. Here are the steps for performing a QDA:
Writing and Coding Them into Themes
The most important or initial step of QDA is writing. It involves writing detailed observations, facts, and approaches of your findings or data you gathered through your study. In many cases your writing may be analytic ideas. In other cases it may be some form of summary of the data, or conclusions from observations.
After writing, to organize your fact findings you need to sort them into themes or coherent categories. Looking for themes involves coding. This involves identifying passages of text, or other meaningful phenomena, such as parts of images, videos and organizing them into certain categories. Then apply descriptive labels to these categories to indicate they are parts of some thematic idea. This enables researchers to quickly retrieve and collect all the text and other data that are associated with a particular thematic idea so that they can be examined together. It also helps to identify the pattern and connections within the different categories. You may discover two or more themes occur consistently in the data or you may identify cause and effect relationships in some of the connections.
As all quantitative data are subject to interpretation, so are qualitative data. Repeatedly reading the textual data, understanding it, and analyzing it for its authenticity and quality are important before proceeding with your interpretation. Review the purpose of your evaluation and identify the questions you want your analysis to answer. Now focus on each question and topic and see how the respondents replied to each set of queries or topics. Make a detailed understanding to explain why things are as you have found them. Jot down a list of key points or findings you found after categorizing or sorting your data. Develop an outline for preparing your final report.
The data sets used in QDA tend to be very large. Though sample size may be quite small compared with those used in quantitative approaches such as surveys, the kinds of meaningful data collected in the form of field notes, video and audio recordings, facts, and interviews, tend to be very lengthy. The facts and data found from the observation require the intensive examination, understanding, and reading that only humans can do. In order not to be overwhelmed by the vast amount of data and analytic writings, you as an analyst need to be organized. Researchers can sort and organize their data in the manual way or can use the computer.
Audio interviews can be transcribed. Sections of the interviews which are important can be noted separately, relevant images can be copied, a summary of a detailed interview or observation can be prepared, and the data can be put under the relevant folders, files, or filing cabinets.
Now with computers around, the process of organization has become much easier. Though smaller data can be handled manually, it may be a good idea to use word processing software to write and annotate texts and use worksheets for analysis. Computers can be also used for data storage and it is much easier to categorize and sort data under different folders and retrieving of data becomes much easier. Thus many researchers have replaced physical files and cabinets with computer based directories. Different kinds of computer software are also available in the market, which are good at analyzing qualitative data. Many analysts now use dedicated computer assisted qualitative data analysis (CAQDAS) packages that not only make the coding and retrieval of text easy, but also make data search much faster than what humans can do. The software has advanced features of analyzing audio and video data also.
Methodologies for Qualitative Data Analysis
There is no one right way for qualitative analysis, in fact there are several approaches for qualitative data analysis. There are theoretical approaches to qualitative analysis you should be familiar with, both for designing your own research and for critically appraising qualitative research evidence. The particular approach you will take will depend on many factors, such as, the research question, the time and resource at your disposal, the overall aims of the study and what questions you want to answer after the analysis. One of the important models developed by Seidel in 1998 is explained below.
Noticing, Collecting and Thinking model
Seidel developed this model to explain the basic process of qualitative data analysis. The model consists of three sections: Noticing, Collecting, and Thinking. These parts are interlinked and cyclical. For example while thinking about things you notice further things and collect them.
You can start your observation on a general level, of noticing, observations, taking down field notes, taking interviews, gathering documents, etc. As you notice and document your findings, you create a record of your observations. Once you have produced a record, you read and focus on that record, you will start observing patterns in them and you assign codes to them to categorize under sections. Assigning codes or labels to them, based on topic, theme or pattern, potentially breaks the data into fragments and this helps as sorting and collection devices.
After you notice and label the textual information, you need to collect and sort them. This process is analogous to working on a jigsaw puzzle where you sort the pieces of the puzzle. You identify the pieces and categorize them into groups which make it easier to put the puzzle together.
In the thinking process you examine and read carefully into the data you have collected. You examine the data for patterns and relationships both within a collection and also across the collection and try to make general discoveries about the phenomena you are researching.
Pitfalls to Avoid in QDA
Do not Reduce Data to Numbers
In qualitative data analysis, do not try to reduce the data to numbers. If you do so, you will be defeating the purpose of qualitative data analysis. You have to delve into your collected data and try to find out what the data is telling you or use them as pointers for further thinking and researching. Qualitative data may be extensive involving text and multimedia, so you need to gear yourself for efficient data management.
You cannot generalize the respondents’ replies. You have to understand from their perspective and try to read into the meaning of their replies. You have to find answers to the questions like – What is unique about this individual, group or situation, why they are answering in a certain manner, and so on.
Address Limitations and Alternatives
Every study has limitations. So presenting the limitations while collecting and analyzing the data gives better clarity to the research and inferences. Also address the possible alternatives and what else might explain the results.
Qualitative data analysis plays an important role in research. It helps a researcher to understand the underlying motivations and gives a deeper meaning of circumstances, and reasons for things. Qualitative research is interesting because it looks at facts and tries to figure out what is behind the facts. This type of analysis is used mainly for interpreting how and why things happen, and this can be a tricky part of a research process. If you want to understand how to work with data and do better analysis then the course Analytics for All: Beginners to Experts gives you a detailed perspective on this topic.