Originally Posted by
DScott
If you can't prove the study's hypothesis, you HAVE to accept the null hypothesis (that there's no difference). You can't say "well, there is no difference in my study, but I want to believe there is, so I'm not going to accept these results and will continue to believe what I want, in spite of what the numbers say." Well you
can say that, but then you'd be wrong.
Bottom line, if you went by these results, you should be able to generate the same power on cranks that range from 145 to 170mm in length. Not a great advertisement for the PwerCrank product, if that's what they're selling.
The study was cited by Powercranks, but it was conducted by an independent academic (Jim Martin, University of Utah). And I think we agree on the conclusion, but again, if you insist on being pedantic, the power numbers are different, but this difference is not statistically significant. The same means just that- that they are the same, not that they fail to differ in a way that is statistically significant. Science is about precision, rigour and being systematic, and these two claims do not have the same meaning.
A study that has a larger sample could very well find statistically different power differences, therefore- and this is the core of science- we do not want to draw premature conclusions. The discussion is not closed. The scientific conclusion is not "we can conclude that there is no difference" the scientific conclusion is "more research is necessary". And yes, this is why "science is a mutha".