Your Data and Shifting Your Thinking

PLEASE Respond to My TWO Peer's Post, Below IN RELATION TO THESE QUESTIONS

PLEASE RESPOND IN A DISCUSSION FORM

response posts (approximately 125-150 words each

Consider the following scenario: you have spent months collecting and analyzing your dissertation data only to find that your results do not support your initial hypotheses. 

How will you know if the mismatch between results and expectations is a result of your theory of action, your data itself or the analyses?

What would you do?

1ST PEER IS DEBORAH

Research projects may face challenges of a mismatch between the results and expectations if the best practices are not adopted. Several factors are likely to contribute to such a mismatch, and they include analyses approaches, data, and theory of action. In instances where the results of a dissertation do not support the initial hypothesis, a researcher may be necessitated to evaluate the research processes to determine where the fault transpired. Understanding whether the collected data is the reason for the inconsistency may entail several considerations. For instance, Mbotwa, Singini & Mukaka (2017) assert that data may be collected from one time-point or at various time-points from a similar subject. Therefore, having insights regarding the procedure of data gathering is a milestone towards identifying the reason between a mismatch in the results and the hypothesis.

An inappropriate theory of action may result in an inconsistency between the expectations and the outcomes. According to Mbotwa et al. (2017), study designs must be in line with the methods of analysis to ensure that the outcomes of a project are accurate. Therefore, determining whether the mismatch between results and hypothesis is as a result of the theory plan may involve examining the processes of research, such as the strategies for data analysis and the study design. Finally, finding out whether the procedure for data analysis is the reason for inconsistency between study expectations and outcomes may entail the scrutiny of the analysis methods in relation to the hypothesis and study design. Agravante (2018) asserts that making changes in the study process and revising the hypothesis may help in instances where the results do not support the hypothesis. Hence, the step I would take, in this case, is altering the research process to ensure that all the best practices are adopted.

 

2ND PEER IS CARLA

Many organizations have tried to fit outcome measures into a system which does not support them (Jones, 2014). This notion of a high performing measurement culture is based on organizational culture.  Overall, when leaders and researchers try data-driven methods or activities before analyzing the culture the outcomes may not be successful (Jones, 2014). In collecting and analyzing the dissertation data many find out that the results do not support the initial hypotheses which could result in incorrection assumptions.

          The following questions will enable me to know if the mismatch between results and expectations is a result of my theory of action, my data, or the analyses. One way to correct this is to compare the results to what initially was intended and examine why those results were different. I would probably ask the following questions. 1. Was the sample size random? 2. Was the data collection instrument used valid and reliable? 3. Was my research question too broad or too narrow? 4. Did I examine the organization’s culture before collecting data? 5. Did I use the wrong methods (qualitative/quantitative)? Do the results contradict previous research?

Therefore, I can rewrite the RQ in a broader sense to include the new findings and analyze previous research.  I can continue to collect data to see if I get similar results. I will also dig through the data (data mining) to see if I come up with other exciting discoveries. Researchers argue that both quantitative and qualitative (mixed) methodologies are used to gain new perspectives in which regulate the data (Mwangi & Bettencourt, 2017).