From the list below , choose all the criteria that need to be choosed to ensure a T distribution is an appropriate model for a paired samples T test . 1. The sample is randomly selected 2. The sample size if at least 30 if we don't don't know that the distribution of difference is normally distributed. 3. There are at least 10 success 4. There are at least 10 failures. 5. The sampling distribution of the difference is normally distributed (seen by looking at a graph of the sample data) 6. The samples are dependent 7. The samples are independent