QUESTION 17

1. A MET CS professor is curious whether virtual formats are more difficult to learn from than in-person formats. They collect final exam scores for 20 in-person students and 20 students taking the virtual version of CS 555 offered in Spring 2020. They perform a two-sample t-test to compare performance between these two groups. In-person students had on average a higher test score by 1.5 points, and the p-value for the t-test is 0.03. Which of the following is true, assuming a significance threshold of 0.05? (Select all that apply)

OPTIONS GIVEN BELOW:

		The 95% confidence interval for the difference in means could be (-0.5,3.5)
		There is a 3% chance that the null hypothesis is true (i.e., a 3% chance that there is no difference in means between these groups)
		The distribution of test scores must be normally distributed for both groups for this test to be valid.
		A two-sample t-test is an incorrect choice. This should be a one-sample, matched pairs t-test.
		If the difference in means and the variability of the samples were equal, but the professor had a larger sample size for both groups, then the p-value would decrease.