Hi All,
I am carrying out an international research with clinicians (speech-language pathologists/ therapists). International professional associations will be distributing the questionnaire link to their members. Although I can ask each specific association to provide the total number of members that will receive the questionnaire, not all members will be able to complete the survey as there is an eligibility criteria (e.g. assess and treat patients with a particular speech disorder as part of their case load). Most probably, associations will not have data about the number of participants that can participate in this questionnaire.
How do you go about calculating the response rate in such cases?
Thanks,
Pasquale
Pasquale Balzan, I am familiar with your problem. It is less troublesome in situations where, for example, a known number of people (e.g., the number of students in a class) are sent an invitation to participate that they are all likely to see (e.g., on a class site they are expected to access regularly).
In situations such as yours, however, I think you simply have to describe how you attempted to recruit participants. Response rate is simply inaccessible.
Maybe you could indicate how many of the surveys that you received had to be discarded and for whatever reason(s) - e.g., too much missing data, the same response selected throughout all Likert-type items. If you did that, you could provide a retention rate that indicates the percentage of received surveys that could be analysed.
Apart from that, maybe the demographic questions you asked your participants would allow you to provide an adequate / helpful description about the kind of participants in your research.
Pasquale Balzan, good to hear from you.
I hope it's not blowing my own trumpet inappropriately if I let you know about some research that my colleagues and I had published a little over a year ago. Here is the reference:
Ma, K., Trevethan, R., & Lu, S. (2019). Measuring teacher sense of efficacy: Insights and recommendations concerning scale design and data analysis from research with preservice and inservice teachers in China. Frontiers of Education in China, 14(4), 612–686. https://doi.org/10.1007/s11516-019-0029-1
Although I put a copy on RG, it's an open-access article, so you should have no difficulty being able to access it. It's a long article, but I'm pretty sure you'll find some relevant information in it. I dealt with the kind of thing you're facing within the response characteristics and discussion sections.
I hope it's helpful.
Incidentally, I wrote pretty much all of the text, so any deficiencies can probably be sheeted home to me.
If I might be able to help further, feel free to ask.
You might consider not mentioning the eligibility criterion in the request for participation, and instead using that criterion as a screener question very early in the questionnaire. Ineligible respondents would then be routed, based on their answer to that question, directly to the end of the questionnaire, and either asked a few demographics or simply thanked for participating. That way, you would know the overall response rate (without regard to eligibility) and could estimate the eligibility rate (from the screener data). The % eligible (perhaps broken down by demographics) could itself be information of interest to your main research question.
Whatever you decide to do, or not do, with that suggestion, you might find it helpful to review the resources on the website of the American Association for Public Opinion Research (AAPOR). Those resources provide a wealth of instruction about different ways of defining the response rate, completion rates, etc.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics