Hello, as the title said. I am considering writing a Bachelor's thesis. One of the main aspects of the thesis is how internet users behave when it comes to understanding how their data is being used and what actions they take, if any, to protecting it.
I am considering doing a mixture of interviews and online surveys. I read that doing online surveys by posting them on websites and forums would be considered "Convenience sampling" but the problem is I read that it can potentially have bias and cannot be easily generalized to the general population. However, I do not know what else to consider as this is the only method I can think of since the topic is literally based on internet users' behaviour so I cannot see how it could be biased or find an alternative.
Would convenience sampling be fine as it is or is there some other method that a student can potentially use to get some good results from the survey?
If someone has some advice on how I could tackle this topic, I would greatly appreciate it.
Convenience sampling involves recruiting participants who are “convenient” to a researcher. Yes, you can utilize convenience sampling when you attempt to examine user behavior. However, you need to justify using it. For online survey, you could go through its pros and cons summarized by Ball (2019), referenced below.
Ball, H. L. (2019). Conducting online surveys. Journal of Human Lactation, 35(3), 413–417. https://doi.org/10.1177/0890334419848734
Good luck,
The short answer. Is no. The enduser of the information will have zero meaningful conclusions on which to base his/her conclusions. The first response is correct but if you do that the most probable result is that the enduser will still not have any useable information. If a decent sample is too costly in any sense including there is no way to meet the necessary requirements with the
currently available technology at least say so in your report. Let the buyer beware by giving them the honest value of THEIR report.. Most statistics associations have this requirement in their ethics statement. Best wishes, David Booth
https://www.amstat.org/ASA/Your-Career/Ethical-Guidelines-for-Statistical-Practice.aspx gives the quidelines from the American Statistical Association
David Booth
The following articles used convenience sampling to study user behavior. Jordaan and Van Heerden (2017), for instance, used a survey on a convenience sample to examine the effect of privacy-related predictors on Facebook usage intensity. Besides, Mohallick et al. (2018) utilized an online survey and a convenience sampling in their investigation of users' perceptions towards online privacy.
Jordaan, Y., & Van Heerden, G. (2017). Online privacy-related predictors of Facebook usage intensity. Computers in Human Behavior, 70, 90–96. https://doi.org/10.1016/j.chb.2016.12.048
Mohallick, I., De Moor, K., Özgöbek, Ö., & Gulla, J. A. (2018). Towards new privacy regulations in europe: Users’ privacy perception in recommender systems. In G. Wang, J. Chen, & L. T. Yang (Eds.), Security, Privacy, and Anonymity in Computation, Communication, and Storage (Vol. 11342, pp. 319–330). Springer International Publishing. https://doi.org/10.1007/978-3-030-05345-1_27
Wiese, M., & Akareem, H. S. (2020). Determining perceptions, attitudes and behaviour towards social network site advertising in a three-country context. Journal of Marketing Management, 36(5–6), 420–455. https://doi.org/10.1080/0267257X.2020.1751242
Yahya, W. K., Hashim, N. H., Husin, N., & Abdul Rahim, N. (2020). Online customer shopping behaviour: The mediating role of online perceived risk. Global Business Management Review (GBMR), 12(Number 2), 1–18. https://doi.org/10.32890/gbmr2020.12.2.1
Good luck,
Sometimes.
A lot of medical and psychology research research uses convenience samples (e.g., those who volunteer for a COVID vaccine study). What the researchers ideally do is compare a control group with, in this case, the vaccine group, where the people have been allocated (often randomly, but in much medical research this is not possible, so things like propensity matching is used) to one of the two groups in a double-blind fashion (and again, double blind isn't always possible). Thus, in these studies the random allocation is important for making inference, but sampling is important to know what the populations the researchers should make inferences about (in this example, is the vaccine effective for people who volunteer for a vaccine study).
Another example where convenience samples are used is where the researcher wants to show that a theory/hypothesis is untrue in the population, generally, so showing it is a specific situation satisfies this. So does light go in a straight line? Astronomers point their telescopes at convenience samples (objects they can observe) and make inference. Light bends during a total eclipse (a convenience sample as high school astronomers will tell you), and this allows you to reject the hypothesis that light never bends.
- Badges
- Science topic
- Similar topics
- Thesis Research