91Ó°ÊÓ

The null hypothesis is a starting point in hypothesis testing. It is a statement that there is no effect or no difference. In our example, the null hypothesis is that there is no difference in the mean number of traffic citations given by the two officers. We write this as \( H_0: \mu_d = 0 \).
This means that we assume any observed difference is due to random chance. The null hypothesis serves as the default or "no change" statement that we attempt to test.
If the data provides enough evidence against the null hypothesis, it may be rejected, indicating that there is a significant effect or difference. However, if the evidence is not strong enough, we do not reject the null hypothesis.

The alternate hypothesis is a statement that contradicts the null hypothesis. It suggests that there is an effect or a difference. In this case, the alternate hypothesis is that the mean number of citations given is not equal between the two officers. We express this as \( H_1: \mu_d eq 0 \).
The alternate hypothesis is usually what the researcher is trying to prove. Finding evidence in favor of the alternate hypothesis suggests that the effect or difference is real and not due to random chance alone.
In a paired sample t-test, proving the alternate hypothesis means showing that the differences in paired observations are consistent with an actual effect.

The significance level, denoted by \( \alpha \), is the probability of rejecting the null hypothesis when it is actually true. It is a threshold for how confident we want to be about rejecting the null hypothesis. Commonly used significance levels are 0.05 and 0.01.
In our scenario, the significance level is 0.05. This means that there is a 5% risk of concluding that a difference exists when there is none. A significance level of 0.05 balances being cautious and allowing for sufficient sensitivity to detect actual differences.

• A higher significance level means a higher chance of making a Type I error (wrongly rejecting a true null hypothesis).
• A lower significance level reduces this risk but can also make the test less sensitive to detecting a real effect.

Choosing a significance level is important as it reflects how much risk of error is tolerable in the specific context.

Standard deviation is a measure of the amount of variation or dispersion in a set of values. In the context of paired sample t-tests, the standard deviation helps understand how varied the pair differences are.
Computing the standard deviation involves calculating how much each observation differs from the mean, squaring those differences, averaging them, and taking the square root. In our step-by-step guide, the formula \( s_d = \sqrt{\frac{\sum (d_i - \bar{d})^2}{n-1}} \) is used.
The standard deviation provides critical insight when interpreting the test statistic. A smaller standard deviation indicates the data points are close to the mean, suggesting consistency in differences. A larger standard deviation implies the differences vary more widely, which might affect the t-test outcome.
Understanding standard deviation helps in assessing the reliability and variability of the presented data.