Steps in Case study Data Analysis
The first step is getting to know the data. For effective data analysis, the researcher needs to understand the data. The researcher needs to read the text at least twice. If the data was collected using tape recordings, the researcher needs to listen to the tape more than once. The researcher should then evaluate whether the data collected is quality data. Sometimes, data collected maybe of no meaningful value or maybe biased. Therefore, the researcher needs to evaluate the quality of the data before data analysis to avoid arriving at an inappropriate conclusion. At this stage, the researcher should also explain any limitations given the data.
The second step is focusing the analysis. The researcher reviews the purpose of the case study and what the research seeks to find out. The researcher should identify the what, how and why questions that the research seeks to answer. How the analysis is focused is determined by the purpose of the case study and how the results will be used. There are two general approaches. The first approach is the focus by topic or question, event or time period. In this approach, the researcher focuses on how the respondents respond to each question regarding a given, event or time period. It often uses open ended questions. The data is organized by grouping questions of a particular topic, event or time period together; the respondent answers are then analyzed to identify any consistencies and inconsistencies. The second approach is the focus by case, group or individual. In this approach, the researcher is interested in only one individual or a single group. Therefore the researcher organizes all the data about the case, group or individual and analyzes it as a whole rather than grouping answers of the respondents.
The third step is categorizing the data. Categorizing the data involves coding the quantitative data to be able to identify patterns or themes. The researcher needs to give a descriptive label to each category of data that has been created. During this process, the researcher may identify other smaller themes which can be used as sub categories. There are two ways of categorizing data; preset categories and emergent categories. In preset categories, the researcher begins with a predetermined list of categories or themes and then looks for data that match the identified themes. In emergent categories, the researcher reads the text first and then identifies the themes that recur in the collected data which will be used as the categories. The categories in which the data is classified are defined as a result of the researcher working with the data. In most instances, the two approaches of categorizing data maybe used together; the researcher may begin with preset categories and later on add other categories as they became necessary. Case study is an iterative process; therefore, the initial categories may need to be adjusted as the researcher works with the data. New categories may also be defined to accommodate data that do not fit in any of the existing categories.
The fourth stage is identifying connections and patterns within and between categories. After organizing the collected data into categories, the researcher should begin to identify any connections and patterns within and between categories. There are various ways of achieving this. The researcher maybe interested in summarizing information regarding a particular theme, or identifying consistencies or differences in respondents answers within a given category. To achieve this, the researcher needs to; assemble all the collected data regarding that particular theme, identify the ideas expressed within the category, analyze any subtle variations and then write a summary of each category. The researcher maybe interested in creating larger ideas or concepts. In this case, the researcher should work up by combining several smaller categories to create larger categories. The researcher maybe interested in identifying the relative importance of a theme. In this case, it would be necessary to determine the frequency with which a particular theme comes up in order to provide relative importance of the various themes. Lastly, the researcher maybe interested in determining the relationships between two or more categories. In this case the researcher needs to identify if there are any themes that occur together consistently in the collected data.
The last step of analyzing any data is interpreting the analysis results.It is interpreting the data that attach meaning to any data analysis. The researcher needs to use the themes, categories and any identified connections to explain the research findings. Visual display can be used be used to communicate the findings and make it easier for the targeted audience to synthesize it.
References
Christensen, L. B., Johnson, R. B., & Turner, L. (2011). Research Methods, Design, and Analysis. New Jersey: Prentice Hall .
Creswell, J. W. (2009). Research Design: Qualitative, Quantitative, and Mixed Methods Approaches (3, illustrated ed.). New York: Sage Publications.
Gravetter, F. J., & Forzano, L.-A. B. (2011). Research Methods for the Behavioral Sciences (4 ed.). London: Cengage Learning.