A. There will be no significant difference in a persons height due to the number of jelly beans eaten. B. Those who eat more jelly beans will be more likely to grow taller then those who eat less jelly beans.
An experimenter has an idea that a certain outcome will follow from a premise. It is usual that in setting up an experiment to prove this, the experimenter composes his hypothesis suggesting the opposite of what he believes, and then sets out to disprove that hypothesis.
This would be the hypothesis that there is no significant difference between specified populations, any observed difference being due to sampling or experimental error - yet with the hope, and probably expectation that the reverse will prove to be the case. The aim is to make a precise ultimate statement by reference to the statistical procedures and results obtained.