Confidence Intervals

Why might it be risky to implement a policy that has an that has average treatment effect with a confidence interval that overlaps with zero?

50 XP

Because the confidence interval equation defaults to 0 with large amounts of data.
Because having zero in one's confidence interval implies that a treatment effect could have a positive or negative effect on the outcome of interest.
Because having zero in one's confidence interval implies that a treatment effect has no effect.
It's incorrect to think this would be risky; as long as relationship between the policy and its treatment effect are within the desired range, a confidence interval that includes zero is not a problem.