I am looking at a questionnaire where on of the questions gives multiple options for participants to pick from. I am thinking of reporting the total frequency of each option. Can anyone suggest a better approach?
It may depend on the nature of the question and what you are trying to communicate about the responses. If you are simply looking to report the options made then a simple frequency would be fine. You could convert this to a rank order, ratio or percentage if that suited. You might also be interested in the number of respondents who chose none, one, or more than one response regardless of what they selected as their response. However, your question says analyse which makes me think you might want more from these selections than just a description?
Hi Abel. As @Jason says, it's difficult to use multiple choice in analyses, but description is feasible. You just have to note that the percentages sum is >100 due to the multiple choice possibility.
See descriptive use in this article (Table 1; here it was coding of open ended questions, but in principle it is a similar issue).
Best
John-Kåre
For a statistical test, you could use Cochran's Q to determine if one response was statistically more popular than other responses. The post-hoc for this is pairwise McNemar tests.
Hi @Salvatore, please explain more about the Cochran's Q, e.g., which software has included it.
Best
John-Kåre
Cochran's Q test can be thought of as an extension of McNemar's test for marginal homogeneity to multiple groups or occurrences. It appears that the test can be conducted in SAS, SPSS, and a couple of different R packages.
The SAEPER reference below has an example.
The coin package reference below describes the relationship among the McNemar test, the Cochran Q test, the Stuart(-Maxwell) test, and the Madansky test. This is in the MarginalHomogenityTests function description.
Wikipedia. https://en.wikipedia.org/wiki/Cochran%27s_Q_test .
SAS. https://support.sas.com/documentation/cdl/en/statug/63962/HTML/default/viewer.htm#statug_freq_sect034.htm .
SPSS. https://www.spss-tutorials.com/spss-cochran-q-test/ .
R. Examples in SAEPER. http://rcompanion.org/handbook/H_07.html .
R. RVAideMemoire package (cochran.qtest). https://cran.r-project.org/web/packages/RVAideMemoire/RVAideMemoire.pdf.
R. Coin package (mh_test). https://cran.r-project.org/web/packages/coin/coin.pdf
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Applied Statistics
- Survey Design
- Questionnaire