91Ó°ÊÓ

Understanding the purpose of null and alternative hypotheses is essential for anyone delving into hypothesis testing in statistics. These hypotheses represent two mutually exclusive statements about a population parameter. The null hypothesis (\(H_0\)) typically suggests that there is no effect or difference, and it serves as the statement we attempt to challenge. In our example concerning Morro Bay duck hunting, we define \(H_0\): \(p \[leq\] 0.5 \), indicating that less than or equal to half of the local residents oppose hunting.

The alternative hypothesis (\(H_1\) or \(H_a\)), on the other hand, is the assertion we hope to provide evidence for. In our case, \(H_1\): \(p \[gt\] 0.5\), implying a belief that more than half of the locals are against hunting. This setup prepares us for the next steps in our testing procedure—calculating the test statistic and interpreting the results.

The test statistic is a standardized value that helps us make a decision regarding our hypotheses. It's calculated from sample data and is used to assess the plausibility of the null hypothesis. For our one-sample z-test scenario, we compute the test statistic using the formula \(z = (\hat{p} - p_0) \ \sqrt{(\hat{p}(1-\hat{p})/n)} \), where \(\hat{p}\) is the sample proportion, \(p_0\) is the population proportion under the null hypothesis, and \(n\) is the sample size.

In the Morro Bay example, by plugging the observed sample proportion and the assumed population proportion into the formula, we calculate the z-value that helps us to understand how far the sample proportion is from the null hypothesis proportion, when measured in standard deviations.

The p-value is a critical concept for interpreting test results. It represents the probability of observing sample results as extreme as those obtained, assuming the null hypothesis is true. A small p-value indicates that such extreme data would be very unlikely under the null hypothesis and thus provides evidence against \(H_0\).

Specifically, if the p-value is less than our significance level (\(\alpha\))—which is \(.01\) in the Morro Bay case—we have strong grounds for rejecting the null hypothesis. This result would mean it is highly likely that a greater proportion of the population opposes duck hunting than our null hypothesis stated. A p-value greater than \(\alpha\), however, would mean we do not have enough evidence to dismiss \(H_0\), and we would say that we 'fail to reject' it.

A one-sample z-test is a type of statistical test used when comparing the sample mean to a known population mean (\(p_0\)) when the population standard deviation is known. In the context of the Morro Bay survey, we're comparing the sample proportion of residents opposing duck hunting to an expected population proportion under the null hypothesis. After calculating the z-test statistic from the sample data, we refer to a standard normal distribution table—or use statistical software—to find the probability associated with the z-value.

In this case, we conclude the test by deciding whether to reject or not reject \(H_0\) based on whether the computed p-value is lower than our predetermined significance level (\(\alpha = .01\)). If we do reject \(H_0\), we're saying that the evidence suggests a majority of the residents oppose duck hunting, which could have implications for future regulations and policy-making in Morro Bay.