Introduction
Quantitative data analysis is generally needed for proper assessment of the numeric data associated with any type of research. Within-subject design, as well as between-subject design types are regarded as the most reliable types of researches for achieving the reliable and effective set of quantitative data. Therefore, if people are offered three variants for participating in a survey, the between-subject research will be the most effective solution, while within subject research will be featured with a lower error rate.
Research Design
The two variants of the study will involve the opportunity of sending a test e-mail to the target audience of the research. As for the matters of the research design, the variants available for the analysis are as given below:
- Three separate e-mails for every participant
- One e-mail with three links
These are the possible approaches for the within-subject study design. However, there is high credibility that e-mails will be marked as spam, especially if they are sent separately.
The other variant is diversifying the audience, and sending one e-mail with a single link to every single person. This may be featured with the increased error rate, however, more data will be collected for the study, as people will be less irritated with unwelcomed messages.
Discussion
Assuming that experiment will involve three variants, the design of the experiment in general will involve assessment of the click rates for each variant. Therefore, people will be offered three variants of the test (it is preferable that the participants did not guess about the experiment): three types of e-mails may be sent to the target audience of the research. One will simply contain a hyperlink with no explanation provided. The other will emphasize that $10 will be donated to charity if a person participates in the survey, and the last will state that a person will participate in a lottery with $ 1000 prize if he/she participates.
In the light of the fact that the research data will be needed for proper assessment of human behavior, the evaluation of the quantitative data will be performed in accordance with the principles of within-subject design, as well as between-subject design types. In fact, both principles involve the same methods of data evaluation, therefore, the key steps of data analysis will be:
- The generation of models and concepts
- Development of measurement instruments and grades
- Experimental control
- Data collection
- Modeling
Assessment of the results
The only important aspect of research design is explained by the specific hypothesis of the research. As it is stated by Newman and Benz (2005) people are reluctant on participating in numerous researches, however, they may gladly answer several questions of the same questionnaire. The offered hypothesis presupposes that people will perceive the generated e-mails as three different actions, and if all three will be sent to an entire audience, up to 85 of the e-mails will be erased as e-mail spam (Duffy and Chenail, 2008). On the other hand, the audience may be explained that they are participating in a research, and the three hyperlinks are the variants of answers for a single question of the research. Hence, the design of the study will be of a within-subject type.
Between-subject design will help to preserve the anonymous nature of the research in general, and get a wider range of frank answers (when people click the links ruled by their own interest and without knowing that they participate in a study). Therefore, between subject design is featured with the advantages that are closely associated with the differentiation of the audience, and the following differentiation of the treatments which is impossible for the within-subject design. As it is stated by Grinnell and Unrau (2005, p. 144):
This type of design is often called an independent measures design because every participant is only subjected to a single treatment. This lowers the chances of participants suffering boredom after a long series of tests or, alternatively, becoming more accomplished through practice and experience, skewing the results.
Therefore, between-subject design is closely linked with the matters of audience differentiation and purposes of the study. Since the offered study involves violation of personal informational space of the audience, sending three e-mails in a row will be inappropriate.
As for the assessment of the results, both variants of study design will involve the analysis of the results from the perspective of the audience’s treatment of the research subjects, and the motivation of the audience to choose one of the three offered variants. (Denmark, Milner, et.al. 2008) Therefore, data measurement will be performed by counting clicks for each link, and calculating rejection rates (the amount of clicks will be lower then the amount of messages sent. Therefore, this difference will be regarded as the rejection rate).
Conclusion
The design analysis patterns are generally regarded as the significant aspects for achieving the results for the research. Hence, while the within-subject design is too obsessive, the between-subject design will be helpful for obtaining wider results, and performing a more reliable analysis of the research data.
References
Denmark, D. L., Milner, L. C., & Buck, K. J. (2008). Interval-Specific Congenic Animals for High-Resolution Quantitative Trait Loci Mapping. Alcohol Research & Health, 31(3), 266.
Duffy, M., & Chenail, R. J. (2008). Values in Qualitative and Quantitative Research. Counseling and Values, 53(1), 22.
Grinnell, R. M. & Unrau, Y. A. (Eds.). (2005). Social Work Research and Evaluation: Quantitative and Qualitative Approaches (7th ed.). New York: Oxford University Press.
Newman, I., & Benz, C. R. (2005). Qualitative-Quantitative Research Methodology: Exploring the Interactive Continuum. Carbondale, IL: Southern Illinois University Press.