91Ó°ÊÓ

Hypothesis testing helps us to make decisions based on data. It starts with two conflicting hypotheses: the null hypothesis \(H_{0}\) and the alternative hypothesis \(H_{1}\). In the given exercise, the null hypothesis is \[H_{0}: M_{D}=0\], suggesting no difference between the pairs.
The alternative hypothesis \[H_{1}: M_{D}<0\] suggests the median difference is less than zero. We follow a systematic process to determine whether the data provides enough evidence to reject \(H_{0}\) in favor of \(H_{1}\). This involves calculating a test statistic and comparing it to a critical value.
Understanding hypothesis testing is fundamental, as it is widely applicable in various fields of study.

The significance level, denoted by \(\alpha\), is the threshold for determining when to reject the null hypothesis. It represents the probability of making a Type I error, which is rejecting \(H_{0}\) when it's actually true.
In our exercise, the significance level is set at \(\alpha=0.05\). This means we are willing to accept a 5% chance of incorrectly rejecting the null hypothesis. Essentially, smaller \(\alpha\)-values require stronger evidence to reject \(H_{0}\).
Choosing an appropriate significance level is critical. Common choices like 0.05, 0.01, and 0.10 balance the risk and reliability of our conclusions.

Non-parametric tests, like the Wilcoxon matched-pairs signed-ranks test used in our exercise, do not assume that the data follows a specific distribution. This makes them flexible and useful when we cannot assume normality in our samples.
In the Wilcoxon test, we rank the differences between paired observations and use these ranks to test our hypotheses. Because it does not depend on the underlying data distribution, it is robust against outliers and non-normal data.
Non-parametric tests are particularly valuable for small sample sizes or when dealing with ordinal data. They offer a practical solution when traditional parametric tests are not applicable.

The critical value is a threshold that the test statistic must exceed to reject the null hypothesis. It depends on the significance level and sample size. In the Wilcoxon test from our exercise, we found the critical value using a table.
For \(n = 35\) and \(\alpha = 0.05\) in a one-tailed test, the critical value is 240. We compare our test statistic \(T_{+}=210\) with this critical value. Since \(T_{+} < 240\), we reject the null hypothesis.
Understanding how to determine and use critical values is essential. This ensures we make accurate decisions based on our hypothesis tests.