Question

1. If we are only interested in testing hypotheses about the sample for which we have data, which of the following forms of uncertainty do we need to account for?

a) Uncertainty stemming from the fact that our sample is drawn from the population

b) Uncertainty stemming from the fact that you only observe one possible permutation of the treatment assignment

c) Both

Answer 1

Since, hypothesis testing allows us to find out, in a formal manner, if the sample supports our idea about the population. Because the samples drawn from any population is vary,.In uncertain hypothesis testing, we call H0 the null hypothesis and H1 the alternative hypothesis. H0 will be tested on the basis of data from the two empirical uncertainty distributions to decide to reject it or not.

If uncertainty exists about what constitutes the population then it becomes impossible to ensure that one studies a sample randomly drawn from the population.
Hence, population uncertainty generates sample uncertainty.

Thus we can say that,Uncertainty stemming from the fact that our sample is drawn from the population.

Hence option (1) is correct answer.