A hypothesis is a testable statement that tries to explain relationships, and it can be accepted or rejected through scientific research.

A fundamental hypothesis expresses one's belief or suspicion about a relationship, e.g., " Smoking causes lung cancer." This statement is not easily testable, however.

A research hypothesis is a more precise and testable statement, such as, " People who smoke cigarettes regularly will have a higher incidence of lung cancer over a 10-year period than people who do not smoke cigarettes."

The Null Hypothesis:

We test hypotheses by taking samples of people from a population, and there is always the possibility that the results will be misleading if the samples are not representative of the population from which they were drawn. This is called sampling error or random error, i.e., "the luck of the draw".

In order to assess the likelihood of sampling error, we reframe the research hypothesis as a null hypothesis , such as, " Over a 10-year period the incidence of lung cancer is the same in people who smoke regularly compared to those who do not. "

By beginning with the null hypothesis, one can quantify the magnitude of difference between the groups in the samples and ask, "What is the probability of seeing a difference in this great or greater due to sampling error?" In the probability that the difference was due to sampling error is very low, then we have sufficient evidence to reject the null hypothesis (i.e., conclude that it is probably not correct), leading us to accept the alternative hypothesis, i.e., that the groups are different. If the probability of sampling error is not low, we conclude that there is insufficient evidence to conclude that there is a difference. This does not mean that the groups are the same, however; it just means there was insufficient evidence to conclude that they differ.