[MUSIC] While discussing on hypothesis testing, we need to make the distinction between simple hypotheses and composite hypotheses. Whenever the hypotheses are made through one or more equalities, then, are simple hypotheses. If instead the hypothesis provides the operators inequality, greater than, or smaller than, then, the hypotheses are called composite. It is very important to keep in mind that hypothesis testing is always about the population parameters. Hypothesis testing means making a decision starting from the sample data on whether or not to reject that certain restrictions that are satisfied by our model. The restrictions that we test are indicated by the expression null hypothesis denoted by H0. Thus, the null hypothesis is a statement that we make on the population parameters. The null hypothesis is always a simple hypothesis. That is we always formulate the null hypothesis by using the operator equality. It is worth noticing that each equality implies a restriction on the parameters of the model. Some examples of null hypothesis concerning the regression model are H0 beta 1 = 0, or H0 beta 1 + beta 2 = 0.5. H0 beta 1 = beta 2 = 1, or H0 beta 3 = beta 2 = 0. We test the null hypothesis against another hypothesis which is called the alternative hypothesis. The alternative hypothesis is denoted by H1. And it is our conclusion if after performing the test, our outcome is that a0 is false. The alternative hypothesis is very often formulated using the operator inequality. For example, the null hypothesis is H0 beta 1 = 1. The alternative will be H1 beta 1 different from 1. Which is a two sides alternative hypothesis. Or H0 beta 1 = 1 and the alternative hypothesis H1 beta 1 greater than 1. Or the null hypothesis, beta 1 = 1, and the alternative beta 1 less than 1, which are one side alternative hypothesis. [MUSIC]