Hypothesis testing
It provides an approach to making inference about a population on the basis
of sample information.
Decisions are made under uncertainty. The idea behind hypothesis testing is
to develop a statistical tool to minimize the probability of error.
The method consists of selecting a sample to check the validity of a
conjecture or hypothesis.
Null and alternative
The maintained hypothesis or conjecture is called Ho.
The alternative hypothesis (H1) is a conjecture assumed to be true if Ho is
false.
Objective
The objective of the test is to show evidence against the null. The
typical analogy is when evidence is presented against a defendant, the
null is that the defendant is inocent.
Elements of a test of hypothesis
1. Null Ho
2. Alternative H1
3. Test statistic
4. Rejection region (or level of significance)
5. Assumptions about population
6. Sample and compute the test statistic
7. Perform the test
8. Conclusion of the test