91Ó°ÊÓ

In hypothesis testing, the null hypothesis serves as a starting point. It is a statement that there is no effect or no difference, and it's what we set out to test against. In this context, the null hypothesis is denoted as \(H_0: \mu = 0\). This means we assume that the population mean is zero.
If the data provides sufficient evidence, we may reject this hypothesis in favor of the alternative. Here, the alternative hypothesis \(H_a: \mu eq 0\) suggests that the population mean is indeed different from zero, signaling a two-tailed test as it allows for deviations in either direction.
During the testing process, our aim is to determine whether there is enough statistical proof to reject \(H_0\) and support \(H_a\). Nevertheless, rejecting the null hypothesis doesn’t automatically prove the alternative true; it simply shows what's more likely given the available data.

The Z-test is a statistical method used when the population variance is known or the sample size is large (usually \(n \geq 30\)). However, it can also be employed for smaller samples if the population is normal, as in this exercise with 20 observations.
A Z-test determines if there is a significant difference between the sample mean and the population mean under the null hypothesis.
The formula for the Z-test is:

• \( z = \frac{\bar{x} - \mu}{\frac{\sigma}{\sqrt{n}}} \)

Here, \(\bar{x}\) is the sample mean, \(\mu\) is the population mean, \(\sigma\) is the population standard deviation, and \(n\) is the sample size. The Z-test uses the standard normal distribution, making it a widely used test in hypothesis testing scenarios.

The significance level, denoted as \(\alpha\), is a threshold used to decide when to reject the null hypothesis. In this scenario, \(\alpha = 0.001\), indicating an extremely strict criterion. This means we are only willing to accept a 0.1% risk of rejecting the null hypothesis if it is indeed true.
The lower the significance level, the stronger the evidence must be to reject \(H_0\). A 0.001 significance level requires very convincing data since the likelihood of making a Type I error (rejecting a true null hypothesis) is minimized.
Choosing a significance level involves trade-offs. While a lower \(\alpha\) reduces the risk of a Type I error, it may increase the risk of a Type II error (failing to reject a false null hypothesis). This balance is important in fields requiring high certainty, such as medical or scientific research.

Critical values are the cut-off points that define regions where the test statistic would lead to the rejection of the null hypothesis. For a two-tailed test like in this scenario, we find critical values for both tails of the distribution.

• For \(\alpha = 0.001\), each tail gets half, or 0.0005.

Using a Z-table or calculator, these probabilities correspond to critical z-values of \(-3.291\) and \(3.291\).
If the calculated z-statistic falls beyond these critical values, it is in the rejection region, implying statistical significance. Thus in this test, any z-value where \(|z| > 3.291\) leads to rejection of the null hypothesis.
Understanding critical values is essential in hypothesis testing as it helps determine the significance of the test results. Always ensure to select critical values matching your test's tails count (one or two-tailed) alongside the significance level.