The formula in the calculator uses p1 - p2. So if you would like to look at the effect of a treatment in an experiment, it might be useful to have "p1" represent the treatment group and "p2" the control group so that the results represent the estimated effect of the treatment. Ultimately, the order is just relative and it's always a good idea to double check that the estimate sign makes sense for how you're interpreting the results. For example, at 3:15 in the video I can see that p1 = 0.899 and p2 = 0.958, and the center of the interval (-0.0814, -0.0366) is negative, so the results must be corresponding to p1 - p2 (as our point estimate of this difference is negative: 0.899 - 0.958 = -0.059), not p2 - p1 (estimated difference is positive: 0.958 - 0.899 = 0.059).
One of your denominators is 10,000. You have 1,000 for both.
Thank you -- great catch! Pinning this comment (even if much belatedly) so others who also might have seen that know it was an error.
So how do you know what to make p1 and p2 or are they interchangeable
The formula in the calculator uses p1 - p2. So if you would like to look at the effect of a treatment in an experiment, it might be useful to have "p1" represent the treatment group and "p2" the control group so that the results represent the estimated effect of the treatment. Ultimately, the order is just relative and it's always a good idea to double check that the estimate sign makes sense for how you're interpreting the results. For example, at 3:15 in the video I can see that p1 = 0.899 and p2 = 0.958, and the center of the interval (-0.0814, -0.0366) is negative, so the results must be corresponding to p1 - p2 (as our point estimate of this difference is negative: 0.899 - 0.958 = -0.059), not p2 - p1 (estimated difference is positive: 0.958 - 0.899 = 0.059).
Thanks! Saves me an unthinkable amount of time on the final!
Thank you! I finished my homework just in time before the homework due time ran out!