91Ó°ÊÓ

When conducting hypothesis testing, the starting point is the null hypothesis. This hypothesis, denoted as \(H_0\), represents the default or original state, suggesting there is no change, no effect, or no difference. In the context of the automobile dealership problem, the null hypothesis posits that the new bonus plan does not influence the average sales volume.
For this scenario, the null hypothesis is mathematically expressed as \(H_0: \mu = 14\). Here, \(\mu\) represents the mean monthly sales of automobiles with the bonus plan.
The null hypothesis serves as a baseline, and it remains accepted unless there is sufficient evidence to suggest a significant change. Therefore, it is crucial to assess whether the observed results are purely by chance or indicate a genuine effect, which brings us to the alternative hypothesis.

The alternative hypothesis, noted as \(H_a\), stands in opposition to the null hypothesis. It suggests that there is a detectable effect or a difference. In our dealership example, it states that the new bonus plan leads to an increase in the sales volume.
Formulated as \(H_a: \mu > 14\), the alternative hypothesis asserts that the mean sales are greater than the existing average of 14 automobiles per month.
The role of the alternative hypothesis is to express what the researcher aims to prove. If sufficient evidence is found, the null hypothesis is rejected in favor of the alternative hypothesis. This process involves statistical testing to gauge whether observed data supports the alternative hypothesis significantly.

After formulating both hypotheses, the next step is to draw a statistical conclusion based on the data collected. This decision hinges on whether you reject or fail to reject the null hypothesis.
If the null hypothesis \(H_0\) cannot be rejected, it suggests the data lacks evidence to show the new bonus plan increases sales. In simpler terms, we conclude the sales remain around 14 cars per month.

• The hypothesis testing does not prove \(H_0\) true but merely indicates insufficient evidence against it.

Conversely, if \(H_0\) is rejected, it implies we have enough statistical evidence to support the alternative hypothesis. The conclusion here is that the mean sales exceed 14 cars, hence affirming the bonus plan's effectiveness.

• Rejecting \(H_0\) gives confidence in adopting the new bonus strategy as it seemingly boosts sales volume.

Overall, the statistical conclusion helps in making informed decisions based on empirical evidence, guiding subsequent actions such as adopting or revising business strategies.