p-value = Indian Head Nod ?

I like to think of p-value in statistics similar to an Indian head nod. I might expect to answer yes or no in relation to the hypothesis or theory, i.e. if there is an effect or not. But you can't answer that question convincingly just yet.

This is because p-value is just a rule to guide behaviour in the long run. You can act as if the data is not noise. Act because you are yet not sure about the theory but only that data not being noise. Your statement regarding the p-value can only relate to the data and not the theory, i.e. the way to interpret is 'my data is in line with the theory I want to test'.

Just like the Indian head nod that instils the uncertainty and cautiousness, yet to a keen observer can provide a certain directionality from the facial clues :)