I'm searching for the most appropriate and simplest analysis to statistically test for differences among 3 groups ("Type1", "Type2", "Type3") of individuals (N=75) according to their answers to a set of 30 questions - the questions are of the type "Do you have any knowledge about topic XYZ?", which are answered Y/N - asked to each individual. In detail, the set of questions is comprised of 3 groups of topics, so there are 3 topic-classes, each with 10 questions. The hypothesesis to be tested are (I) overall knowledge, which could be quantified by summing Y in each "Type", is different among Types - (II) the "kind of knowledge", quantified by the sum of Y-answers within each "topic-class", is different among "Types". The sample is a random sample from a population of about 1000 teachers. Thanks in advance!

  • $\begingroup$ What are the research questions you wish to answer? $\endgroup$ – Penguin_Knight Jan 6 '16 at 21:47
  • $\begingroup$ Sorry, I was just about to elaborate more on the design and hypothesis! Please see the updated Q. $\endgroup$ – Kay Jan 6 '16 at 21:58
  • $\begingroup$ You say that this is a survey dataset. Before anyone can provide you with a reliable answer, you'll need to describe the survey a bit more. How was the sample drawn for this survey? Can you tell us more about how the sampling and survey was actually carried out? $\endgroup$ – StatsStudent Jan 6 '16 at 22:49
  • $\begingroup$ It is a random sample. $\endgroup$ – Kay Jan 7 '16 at 6:57

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.