> You'd need a much larger study with totally different design to even begin to approach the question
Yes, that is my point. As the OP remarked; "The others may be “complicated” but the effect also looks close to noise. " is disregarding that data.
When one thinks of the word "noise" one hears something that bothers them, like "there is too much noise in here". This is the problem with research. By getting rid of the "noise" they will only zero in to the thing they wish to hear clearly.
