Here is the StatCrunch output:
Hypothesis Test Results:
μ1: Mean of Population 1
μ2: Mean of Population 2
μ1 - μ2: Difference between two means
H0: μ1 - μ2 = 0
Ha: μ1 - μ2 > 0
(without pooled variances)
Difference | Sample Mean | Std. Err. | DF | T-Stat | P-value |
---|---|---|---|---|---|
μ1 - μ2 | 4.9 | 0.92291766 | 1545.8916 | 5.3092494 | <0.0001 |
As the output mentions, recall that we were testing
H0: μ1 - μ2 = 0
Ha: μ1 - μ2 > 0
and based on the small P-value, we rejected H0 and concluded that males 20 to 29 years old weigh more, on average, than males 75+ years old. It would be interesting to follow up this conclusion and estimate how much more males 20 to 29 years old weigh, on average. The 95% confidence interval does exactly that.