91Ó°ÊÓ

When conducting a t-test, one of the first steps is to formulate the null hypothesis, denoted as \( H_0 \). The null hypothesis acts as a default claim that there is no effect or no difference between groups. In the context of testing whether the annual returns of stocks listed on the NYSE are higher than those on NASDAQ, the null hypothesis states that there is no difference in the mean annual rates of return between the two stock exchanges. This can be expressed as \( \mu_{\text{NYSE}} = \mu_{\text{NASDAQ}} \).

Essentially, the null hypothesis is something we aim to test against. Our goal is to either reject it, in favor of the alternative hypothesis, or fail to reject it, which means we do not have enough statistical evidence to claim there's a difference. It's critical to remember that failing to reject the null hypothesis does not prove the null hypothesis is true—it simply means there's insufficient evidence against it.

When setting up hypotheses, the null hypothesis is usually a statement of "no effect" or "no difference," serving as a neutral ground for testing.

The alternative hypothesis, denoted as \( H_a \), stands in contrast to the null hypothesis. It is a statement that indicates the presence of an effect or a difference that we expect or suspect. In our t-test scenario, the alternative hypothesis posits that the mean annual rate of return for the NYSE stocks is higher than that of the NASDAQ stocks. Mathematically, this is written as \( \mu_{\text{NYSE}} > \mu_{\text{NASDAQ}} \).

If the data provide sufficient evidence against the null hypothesis, we accept the alternative hypothesis. This means that the results support the idea that NYSE returns might indeed be higher.

The alternative hypothesis is directional since it indicates a specific direction of difference (greater than), which is crucial for determining whether to use a one-tailed or two-tailed test. In this example, a one-tailed test is appropriate as we're specifically interested in whether NYSE returns are greater.

Standard deviation is a measure of how spread out the numbers in a data set are. It provides insights into the data's variability. For our t-test, the standard deviations of both NYSE and NASDAQ data sets are crucial because they influence the calculation of the test statistic.

To compute the standard deviation of the samples, we first find the variance by taking the average of the squared differences from the mean. The formula for standard deviation is: \( s = \sqrt{\frac{\sum{(x_i - \bar{x})^2}}{n - 1}} \), where \( \bar{x} \) is the sample mean, \( n \) is the number of observations, and \( x_i \) represents each data value.

In our case, the standard deviations were calculated to be 5.33 for NYSE and 5.62 for NASDAQ. These tell us about the typical spread of returns around their respective means. Lower standard deviation indicates that the data points tend to be closer to the mean, while a higher standard deviation suggests they are more spread out. The standard deviation values feed into the pooled standard deviation \( s_p \) used in the t-test formula, affecting the t-statistic outcome.

The significance level, often denoted as \( \alpha \), represents the probability threshold for rejecting the null hypothesis. It's a critical value that defines how rigorous our test is—a kind of safeguard against making a Type I error, which occurs when we wrongly reject a true null hypothesis.

In this exercise, a significance level of 0.10 is chosen. This means we are willing to accept a 10% risk of declaring a difference when there actually isn't one.

During hypothesis testing, the calculated p-value is compared against the significance level:

• If the p-value is less than the significance level, we reject the null hypothesis, indicating a significant result.
• If the p-value is greater, we fail to reject the null hypothesis, concluding insufficient proof of significant difference.

The significance level determines the critical value for our test. In our scenario, it forms the basis for deciding whether the difference in annual returns is statistically significant or simply due to chance.