I enjoyed Knight’s warning on pg 179 about statistical significance. Proving something is statisically true does not neccessarily also prove it is socially relevant. I took a stats course before, and that prof used the statement in the title of this post to help illustrate that to us. It was helpful to me and quite fun, so I thought I’d share with you lot.
In reality, though, when you’re doing real research, this is a real tricky thing. I mean, how do you as the researcher decide which statisical truth is relevant and which is not? How do you keep your own bias out of it?