You'd then analyze the results using a [independent] 2-sample t-test. But what about this?.... Let's say that it's possible for us to give each child one of each type of shoe... both from manufacturer A and from manufacturer B. Let's say that it's the amount of tread wear that we're interested in, so really I'm only interested in the sole of the shoe anyway. If we do that, then, each child is different - and that's OK - some of them are going to be running around more than others, but each ...