Rule for Testing a Hypothesis

The procedure for testing a hypothesis is as follows - 

1. Mention the null hypothesis H0 to be tested along with an alternative hypothesis H1.
2. Make some assumptions such as the sample os random, the population os normal, the ca==variances of two different populations are equal or unknown.
3. Then find the most appropriate test statistic together with its sampling distribution. A statistic whose primary role is that of providing a test of some hypothesis is called a test statistic. 
4. On the basis of the sampling distribution make a decision to either accept or rejecting the null hypothesis H0. Let a die be thrown. then the null hypothesis H0 os that the die is unbiased, i.e. the proportion of aces is 1/6 on any number of throws. Let H1 be the proportion of aces 1/7. then the following rule be suggested for testing our hypothesis-Accept H0 if there are more than 17 aces if