Research Measures in a Dissertation
Research measures should be written in a way that provides accurate and reliable data. As a result, the dissertation may rely on procedures used in previous research or develop its measures. This is accomplished by defining sets of rules used to determine what is being measured, the units to be used, and the rules by which the assessment components are assigned to the items within (Cottrell & McKenzie, 2011).
Benefits and Drawbacks of Developing Instruments of Measure
The benefits and drawbacks of developing instruments of measure to analyze constructs for a dissertation will be discussed in this paper. There are several benefits and disadvantages to using questionnaires and surveys as measures in the study.
To begin with, advantages include access to all information that is relevant to the study. This is because the researcher can obtain a large number of responses which can be analyzed and also allows for the paper to maintain originality. This differs from existing literature since the reports omit the questionnaires and surveys and only present a summary of the actual information obtained.
Secondly, there is an increased probability that by creating a questionnaire and conducting a survey there is higher stability, representative and equivalence reliabilities. Stability reliability indicates that the responses obtained to fit the time and environment of the study and will thus reflect the truth in reflection to current happening. The second reliability, the representative, indicates responses from different segments of a population and where one creates their own questionnaire, he would be able to meet this reliability y formulating questions that fit into the demographic sub-groups. The final reliability obtained is equivalence which the researcher van obtain by ensuring wording is able to distinctively query on subjective measures (Hyman, Lamb, & Bulmer, 2006)
As concerns disadvantages, there is the issue of time used towards generating the questions and the time spent in finalizing the survey. This is because the researcher will have to identify the specific questions and completed surveys that align to the focus of the dissertation. This is a time-consuming exercise spent in constructing questions and conducting research that can be omitted where the research relies on pre-existing measures.
The second disadvantage is that pre-existing measures can be identified in a manner showing that the questionnaire format and survey implementation are precise in light of the researcher's intention. This element may be absent since a researcher might not be able to construct his assessments in a manner that meets testing the hypothesis.
The last disadvantage relates to the lack of configuration of the aforementioned measures in order to obtain the most accurate responses in self-created measures. This is especially true as concerns questions and surveys that are personal in nature and thus require the use of self-completion techniques. To achieve the aforementioned technique is a skill that might be difficult for people who use it for the first time and thus, alter the validity of a paper.
The paper has discussed the advantages and disadvantages of using questionnaires and surveys as assessment methods as a choice over using pre-existing measures in the same form. It is evident that despite the weaknesses, a researcher may be able to increase reliability, accuracy, and validity of their dissertation by ensuring that the data collected meets high quality standards that might otherwise be unachievable in instances where the study relies on existing measures.
Cottrell, R., & McKenzie, J. F. (2011). Health Promotion & Education Research Methods: Using the Five Chapter Thesis/Dissertation Model. Burlington: Jones & Bartlett Learning.
Hyman, L., Lamb, J., & Bulmer, M. (2006). The Use of Pre-Existing Survey Questions: Implications for Data Quality. (E. Commision, Ed.) Retrieved March 24, 2017, from ec.europa.eu: http://ec.europa.eu/eurostat/documents/64157/4374310/22-Use-of-pre-existing-survey-questions-implications-for-data-quality-2006.pdf/e953a39e-50be-40b3-910f-6c0d83f55ed4