Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. It only takes a minute to sign up.
Sign up to join this community
Please, can someone advise me on how I can approach my nominal data and test its significance.
I measured jerking movement as a behavioural effect in a fish exposed to each of Chemical A and Chemical B at different concentrations (or treatments) based on below metrics:
No effect = 1 Low effect = 2 Moderate effect = 3 High effect = 4
I want to now evaluate if there is a significant difference between effect of Chemical A from B. This is how the data look:
You could do a chi-square analysis, but you probably have too few participants - you could try a Fisher's Exact Test, but again statistical tests work best with lots of respondents so you may have to rely on descriptives (crosstabulations) and graphs.
This is not a nominal but ordinal data, hence I think kuskal wallis followed by man whitney will be more appropriate
