If the study were conducted over and over (selecting different samples of people each time), which one of the following would be true regarding the resulting sample proportions of "yes" responses?
Different sample proportions would result each time, but for sample size 900 they would be centered (have their mean) at the true population proportion, whereas for sample size 100 they would not. Different sample proportions would result each time, but for sample size 100 they would be centered (have their mean) at the true population proportion, whereas for sample size 900 they would not. Different sample proportions would result each time, but for either sample size, they would be centered (have their mean) at the true population proportion. For either sample size, using the same size each time, as long as the sampling is done with replacement, their mean would be 0. None of the above is true, since it makes no sense to talk about the mean of sample proportions.