91Ó°ÊÓ

In the realm of hypothesis testing, the null and alternative hypotheses are the initial key elements to any analysis. The null hypothesis, denoted as H₀, is a statement of no effect or no difference and serves as the assumption that we initially accept to be true until evidence suggests otherwise.

Conversely, the alternative hypothesis, symbolized as H₁ or H_a, represents what the researcher is seeking to prove. It is a statement indicating the presence of an effect or a difference. The alternative hypothesis is accepted when there is sufficient statistical evidence to reject the null hypothesis.

Using the exercise as an example, the null hypothesis (H₀) posits that the proportion of all apartments that prohibit children is 75%, symbolically expressed as H₀: p = 0.75. On the flip side, the alternative hypothesis (H₁) suggests that this proportion is greater than 75%, written as H₁: p > 0.75. This sets the stage for testing whether the evidence supports legislative consideration due to a higher exclusion rate.

A test statistic is a standardized value that is calculated from sample data during a hypothesis test. It's essentially a z-score: the number of standard deviations a data-point is from the mean of the sampling distribution of the statistic.

To calculate the test statistic in our exercise, we use the formula:

\[ Z = \frac{ \hat{p} - p_0 }{ \sqrt{ p_0 * (1 - p_0) / n} } \]

where \( \hat{p} \) is the sample proportion, \( p_0 \) is the proportion under the null hypothesis (in this case 0.75), and \( n \) is the sample size. By substituting the sample data into this formula, we obtain a z-score which tells us how extreme the sample is, assuming the null hypothesis is true. A high absolute value of the test statistic indicates that the observed sample data is unlikely under the null hypothesis and can lead to a rejection of H₀.

The p-value is a probability that reflects the strength of the evidence against the null hypothesis. Specifically, it is the probability of observing a test statistic as extreme as, or more extreme than, the one computed from the sample data, under the assumption that the null hypothesis is true.

The critical value is a threshold that determines the boundary for rejecting the null hypothesis. It's derived from the level of significance of the test, denoted as \( \alpha \), which is the probability of making a Type I error -- rejecting the null hypothesis when it's actually true.

In the case of the exercise, using the 0.05 level of significance for a one-tailed test indicates that the test statistic should be compared against a critical value from the standard normal distribution. If our calculated test statistic exceeds this critical value or if the p-value is less than 0.05, we reject the null hypothesis, concluding that a higher proportion of apartments exclude children. This pivotal comparison is what determines the statistical validity of our hypotheses.

The power of a test is the probability that it correctly rejects a false null hypothesis (i.e., avoids a Type II error). It's essentially the test's sensitivity to detect an actual effect when there is one.

To perform a power analysis, as mentioned in Part B of the exercise, we calculate the probability of successfully rejecting the null hypothesis when a certain true proportion (in this context, is specified as \( p = 0.8 \)) is present. This calculation requires information on the significance level (\( \alpha \)), the effect size (difference between \( p \) and \( p_0 \)), and the sample size (\( n \)).

High power is desirable and means that there's a good chance of detecting an effect if one exists. If the calculated power is low, the test may not be sensitive enough, which implies that even if apartments significantly exclude children more than the hypothesized proportion, the test could fail to provide enough evidence to take legislative actions. Thus, comprehending the power of a test contributes to the reliability and adequacy of statistical conclusions.