The importance of the null hypothesis.
When researchers carry out studies it is the null hypothesis they are testing, not the research hypothesis. The null hypothesis states that there will be no difference between the groups being tested so the means of the groups will be exactly the same. In comparison the research hypothesis states that there is a difference between the groups. With the null hypothesis declaring that there is no difference between samples then there are two possible outcomes, there is or is not a difference. However if you were to test the research hypothesis there would be so many possible outcomes it would be near impossible to test.
In order to see if there actually is a difference we need to examine how different the two groups actually are. We do this by looking at the variability within groups and between groups. The more different the individuals are in a group the more difference there needs to be between groups in order for there to be a difference overall. To work out the difference between groups you have to divide between group variance by within group variance. Ideally you want large between group variance and small within group variance, so the standard deviation is clustered tightly around the mean. Most commonly researchers find that they have small between group variance and small within group variance, meaning a smaller effect size. The less overlap there is between the distributions the more likely you are to find a significant difference.
In conclusion we need the null hypothesis to determine if there is a difference between groups being tested or not. Without it we would be swamped with possibilities making it almost impossible to test.