Testing Hypotheses

I was at a doctoral defence today and one of the examiners said something in passing that gave me pause for thought: "People are often tryig to prove their hypothesis rather than test their hypothesis." It may seem like a subtle difference, but I think it is an important distinction. I've had many discussions with many people about my frustration at the way some people view science, specifically the way they treat "negative results." When you run an experiment and confirm the null hypothesis (e.g., there is no difference between the groups being compared), this is not a failure of your experiment (although many people view it that way). So long as you have designed your experiment well and you have sufficient power to detect a difference, this outcome is just as valid as confirming the alternative hypothesis. I think it can lead to real problems when people set out to "prove" their hypothesis -- especially when it leads to not publishing "negative results," whether that's because the investigators themselves don't try to publish them, believing them to be invalid, or because reviewers/editors take this view.