We can see from these graphs that, when sample size increases, the distributions are more leptokurtic, with thinner tails of the distribution. This occurs because the standard deviation of the sampling distribution (standard error) is smaller. Our alpha level and the distance between the means of each sample are the same. We have more statistical power with this test because of the longer, thinner tails. The critical value that cuts off 5% of the area under the curve (our alpha level) has a higher value, which gives us more statistical power.
|
