A hypothesis is nothing more than a statement that requires verification. Hence, it remains speculation until tested. Hypotheses are useful for verifying inferences from data and for determining the differences between observations and expectations.
A hypothesis has two parts: the null hypothesis (Ho) and the alternate hypothesis (Ha). The null hypothesis is a negative statement while the alternate hypothesis is phrased positively.
A problem with having a null and alternate hypothesis is that an incorrect conclusion can be drawn, also known as an inferential error, from a sample. There are two types of these errors: type I and type II. Type I occurs when the null hypothesis is rejected even though it is, in fact, true. Type II occurs when the null hypothesis is accepted even though it is, in fact, false.
A common approach for testing a hypothesis is the test of significance. Basically, this entails assessing the degree of difference between the null and the alternate hypothesis. The difference is then assessed to be significant or insignificant. The probability of one of the differences being more wrong than the others is called the significance level. The degree of certainty is the confidence level.
There is one major benefit of hypothesis formulation and testing. It provides a means for testing inferences so that decisions can be made without relying on false assumptions.
for Hypothesis Formulation and Testing
3.142.249.42