91Ó°ÊÓ

In statistical testing, the null hypothesis is a fundamental concept that acts as the starting point for any test. Its main purpose is to propose a default assumption about a particular parameter of a population. In our KFC potato wedges example, the null hypothesis, denoted as \(H_0\), states that the average number of calories in small bags of KFC potato wedges is exactly equal to the advertised value, which is 280 calories. Simply put, it is the claim that there is no difference between the observed sample data and the stated average.The null hypothesis works on the presumption of no effect or no difference, aiming to disprove itself through statistical evidence. It is assumed true until sufficient evidence suggests otherwise. This implies that under the null hypothesis:

• The sample mean is expected to be close to the population mean.
• Any deviation from the population mean can be attributed to random sampling variation.

Understanding the null hypothesis is crucial, as it forms the basis of the decision-making process in statistical tests.

The alternative hypothesis is an integral part of hypothesis testing. It represents a contrary position to the null hypothesis and expresses what researchers aim to support through their analysis. In the scenario with KFC's potato wedges, the alternative hypothesis, denoted as \(H_a\), posits that the average number of calories in small bags of KFC potato wedges is greater than the advertised 280 calories.This hypothesis signals a difference or effect that researchers want to detect. In hypothesis testing, the goal becomes either to provide support for the alternative hypothesis by showing that the null hypothesis can likely be rejected, or to show that the evidence is insufficient to reject the null hypothesis.Key points about the alternative hypothesis:

• It is considered true when the null hypothesis is rejected based on statistical evidence.
• In our case, it emphasizes the suspicion that KFC potato wedges contain more calories than advertised, requiring evidence to support this claim.
• It is always directional (greater than, less than) or non-directional (not equal to), specifying the nature of the expected difference.

The significance level is a critical aspect of hypothesis testing used to determine whether to reject the null hypothesis. Denoted by \(\alpha\), it specifies the probability of committing a Type I error, which is the error made by rejecting a true null hypothesis. In simple terms, it reflects the researchers' tolerance for false positives.In our example, the test is conducted at a 1% significance level, which means:

• There's a 1% risk of concluding that the average calories are more than advertised when, in fact, they are not.
• A smaller \(\alpha\) indicates stricter evidence is required to reject the null hypothesis.
• This choice controls how stringent the test is, balancing the need for evidence against the acceptance of possible errors.

Choosing a significance level depends on the context of the test. In some fields, a 5% level is standard, but health and safety applications often demand a more stringent 1% level, as seen in our exercise.

The critical value is a key element in determining the outcome of hypothesis tests. It represents the threshold beyond which the null hypothesis is rejected. It is derived from the test's specific distribution and is influenced by the chosen significance level and degrees of freedom.In the KFC potato wedges problem, with a significance level of 1% and 9 degrees of freedom (since there are 10 samples), we find the critical value using a t-distribution table. The critical t-value for a one-sample t-test in this context is approximately 2.821.Understanding critical values involves:

• Comparing the calculated test statistic's value to this threshold.
• Rejecting \(H_0\) if the test statistic surpasses this value, indicating enough evidence against \(H_0\).
• Thus, in our example, since the test statistic (4.57) is greater than the critical value (2.821), the null hypothesis is rejected.

The critical value provides a concrete benchmark that assists in making decisions based on statistical evidence.