Introduction
Designing a plan for the process of data analysis is of the same significance as the process of data collection itself. It is vital to divide it into distinct phases by determining the objectives of each stage so that the process is flawless and the goals of the change project are achieved. It is also significant to note that creating a process for data analysis should be based on reviewing the data obtained from risk assessment because it would help assure that the data obtained during the collection stage is reliable and relevant.
Risk Assessment
There are several primary risks that might affect the credibility and relevance of the obtained data. First of all, because the interview was chosen as the form of collecting data, there is the risk of people being suspicious in the anonymity and security of data storage. That is why the respondent might not feel free to give true and complete answers to the questions. This risk is impossible to eradicate because the research implies using both open and close-ended questions. If the answers to the close-ended questions can be obtained from questionnaires, the only way to collect the responses to open-ended questions is through conducting interviews. Second, there is the risk of emotional reaction to the questions. It implies that the answers can be affected by the emotional state of the respondents. For example, some of them might be in a bad mood or employees might be stressed because of the fear to lose their positions. Moreover, there is a risk of insufficient time for the interviews because it was determined that every respondent will have half an hour. Finally, there is the risk of a lack of knowledge and skills to conduct a comprehensive research. All these risks can be minimized. That said, in the case of the first two risks, the potential way to diminish them is to guarantee anonymity and safety of the obtained information as well as offer some tea or coffee while making a brief acquaintance creating a needed atmosphere. As of the time risk, it can be minimized by prompting the respondent to provide short answers with precise attention to details, but without overloading with them. Finally, the option for mitigating the risk of insufficient knowledge is to review literature on the issue under investigation and data analysis tools and methods.
Creating a Matrix for Data Analysis
The process will contain several distinct stages. It will be peaked with a matrix representing the data review and the primary findings of the data analysis. The first stage implies becoming familiar with the data. At this point, it is paramount to read and re-read the answers to the questionnaires and listen and re-listen the records of the interviews. The primary objective of this stage is to achieve what is known as feature extraction, i.e. estimating the trends in the answers of the respondents (Krogerus, Rokala & Koskinen, 2012).
This step will become the foundation for the second stage of the data analysis process – grouping the responses. It will center on the statistical method of data analysis, i.e. distinguishing the trends in the answers of the respondents (Harris, Roussel, Thomas, & Dearman, 2015). It can be easily used when analyzing the responses to close-ended questions. As of the open-ended questions, the results could be grouped based on the moods in the respondents’ replies. The primary objective of this stage is naming themes, i.e. grouping the answers based on the primary themes of the answers (Murshidi, 2015).
Later, this data will be used for building graphs and charts that would represent the primary answers to the questionnaires and interviews, i.e. the percentage of agreement between the respondents (McKinney & Hess, 2012; McConnel et al., 2014). Because the research is quantitative, what would be taken into consideration is the correlation between variables such as age, sex, education, and income, on one hand, and the frequency of occurrence of a particular answer on the other hand (Ingham-Broomfield, 2015). The set goal of this phase is to provide a visual representation of the research outcomes so that it is easier to analyze the data and perceive the findings. The final step of the data analysis is to prepare the report consisting of all the necessary information about the objectives of the change project, the process of collecting and analyzing data, and the primary findings (Murshidi, 2015).
The Matrix will be divided into two sections. The first one represents the answers to the close-ended questions (check the respondent’s answer). It will be used for determining the frequency of occurrence of the answer with the aim of building graphs. The second one shows the answers to the open-ended questions based on the themes whether they are keywords or figures.
Table 1. a) Matrix, part 1: analyzing the answers to close-ended questions (frequency of occurrence, number of respondents)
b) Matrix, part 2: analyzing the answers to open-ended questions (frequency of occurrence, number of respondents).
Conclusion
In conclusion, it is paramount to note that creating a process for data analysis as well as acknowledging the risks are significant for maintaining the continuity of the change project because they are beneficial for becoming aware of the primary risks and the volume of work that needs to be done in order to achieve the expected objectives. This data will be effectively integrated into the project change because it will help determine the existing problems, the perception of the situation, and find potential ways to solve the challenges.
References
Harris, J. L., Roussel, L. A., Thomas, T. & Dearman, C. (2015). Project planning & Management: A guide for nurses and interprofessional teams (2nd ed.). Burlington, MA: Jones & Bartlett Learning.
Ingham-Broomfield, R. (2015). A nurse’s guide to quantitative research. Australian Journal of Advanced Nursing (Online), 32(2), 32-38.
Krogerus, T., Rokala, M. & Koskinen, K. T. (2012). Data analysis process or working hydraulics of small mobile machines. International Journal of Fluid Power, 13(3), 5-14.
McConnel, E. R., Bell S. M., Cote I., Wang R. L., Perkins E. J., Garcia-Reyero, N.,… Lyle D. Burgoon. (2014) Systematic Omics Analysis Review (SOAR) Tool to Support Risk Assessment. PLoS ONE, 9(12), 1-14.
McKinney, C., & Hess, R. (2012). Implementing business intelligence in your healthcare organization. Chicago, IL: HIMSS Books.
Murshidi, G. A. (2015). Gulf Region students’ acculturation into the academic world: Qualitative analysis of data process. World Journal of English Language, 4(2), 14-20.