Summary
Highlights
The video introduces hypothesis tests for a population mean using the p-value approach when the population standard deviation is known. An example is presented: a random sample of 25 observations from a normal population has a mean of 22. With a known population standard deviation of 4.9, the question is whether the population mean is significantly below 24 at α = 0.01.
For the given example, the alternative hypothesis (H1) is μ < 24, and the null hypothesis (H0) is μ = 24. It's noted that, technically, H0 should be μ ≥ 24 but is simplified for explanation. Since the population standard deviation (sigma) is known, a z-test statistic is used, resulting in a z-stat of -2.04.
This is a left-tailed test, meaning the p-value is the area under the curve to the left of the test statistic. For z = -2.04, the p-value is 0.0207. This means if the null hypothesis is true, there's about a 2% chance of obtaining such an extreme test statistic. The significance of this p-value determines whether the sample mean is too far from the assumed population mean.
The p-value is compared to the significance level alpha. If p-value ≤ alpha, the null hypothesis is rejected. In the example, with α = 0.01, since the p-value (0.0207) > α, we fail to reject the null hypothesis. There's not enough evidence to conclude the population mean is less than 24 at α = 0.01. However, at α = 0.05, the p-value < α, leading to the rejection of the null hypothesis.
The video then covers a two-tailed test, where the goal is to determine if the population mean differs from 24 at α = 0.05. The alternative hypothesis is μ ≠ 24. The p-value for a two-tailed test is twice the one-tailed p-value. If this p-value is less than alpha, the null hypothesis is rejected, concluding that the population mean differs from 24. At α = 0.01, the conclusion might change.
A right-tailed test is demonstrated with a sample mean of 26, population standard deviation of 5.5, and testing at α = 0.05 whether the population mean is greater than 24 (H1: μ > 24). The test statistic is 1.82. The p-value, which is the area to the right of z = 1.82, is 0.0344. Since this p-value (0.0344) < α (0.05), the null hypothesis is rejected, concluding the population mean is greater than 24.
Finally, the video re-examines the data from the right-tailed test scenario for a two-tailed test, asking if the true mean has 'changed' from 24 (H1: μ ≠ 24) at α = 0.05. The one-tail area is multiplied by 2 to get the p-value. In this case, the p-value is greater than 0.05, leading to a failure to reject the null hypothesis and an inability to conclude that the population mean is different from 24.