91Ó°ÊÓ

The t-distribution, also known as Student's t-distribution, is a probability distribution that is often used in hypothesis testing when the sample size is small and the population standard deviation is unknown. Unlike the normal distribution, the t-distribution has thicker tails, which allows it to account for the extra variability introduced by estimating the population standard deviation. This characteristic means it can handle samples that deviate more significantly from the mean.

The shape of the t-distribution depends on the degrees of freedom, which we'll discuss in the next section. A unique feature of this distribution is its symmetry around zero. This symmetry is useful in hypothesis testing, especially in two-tailed tests where the test statistic can be in either tail of the distribution.

• Thicker tails than normal distribution.
• Used with small sample sizes and unknown variance.
• Symmetric around zero.

Degrees of freedom (df) is a concept in statistics that represents the number of independent values or quantities which can be assigned to a statistical distribution. When performing a t-test, it's important to calculate the degrees of freedom to understand the correct shape of the t-distribution you should be using. The formula to calculate degrees of freedom for a simple t-test is straightforward: subtract one from the sample size, or mathematically, it is expressed as:\[ df = n - 1 \]where \(n\) is the sample size. For the exercise at hand, with a sample size of 20, the degrees of freedom is: \[ df = 20 - 1 = 19 \]This parameter is crucial because the shape of the t-distribution varies with the degrees of freedom. As the degrees of freedom increase, the t-distribution approaches the standard normal distribution.

• Defined as \( n - 1 \) for a t-test.
• Indicates the number of independent pieces of information in the data.
• Affects the shape of the t-distribution.

A two-tailed test in hypothesis testing is used when we want to determine if there is either an increase or decrease in the population parameter, compared to a specific value. This type of test is symmetrical and tests for the possibility of the relationship in both directions.

In our given hypothesis test, we have a null hypothesis \( H_0: \mu = 7 \) and an alternative hypothesis \( H_1: \mu eq 7 \). The symbol \( eq \) indicates that we are looking for deviations on both sides of the value 7. This is why we apply a two-tailed test, which essentially doubles the p-value obtained from the t-distribution. Because the decision rule for a two-tailed test is:- Reject the null hypothesis if the test statistic exceeds the critical value in either tail of the distribution

This methodology allows researchers to evaluate both potential directions of effect without bias.

• Tests both higher and lower values from the mean.
• Used when \( eq \) is part of the alternative hypothesis.
• Involves doubling the one-tailed p-value.

Calculating the p-value is an essential step in hypothesis testing, as it helps to determine the significance of the test results. A p-value is the probability that the observed data would occur if the null hypothesis were true. To find the p-value for a t-test, compare the test statistic to the t-distribution.

In a two-tailed test as in our exercise, the p-value is the probability of observing a test statistic as extreme as, or more extreme than, the observed value. Since the t-distribution is symmetric:- Multiply the one-tailed probability by 2 to convert to a two-tailed p-value, because the test statistic can fall in either tail.

For example, with a test statistic of \( t_0 = 2.05 \) and degrees of freedom 19, determine \( P(T > 2.05) \) and then:\[ P = 2 \times P(T > 2.05) \]This approach allows you to interpret the p-value against a significance threshold, like \( \alpha = 0.05 \), to make informed decisions about your hypotheses.

• Probability comparison under null hypothesis assumption.
• Involves doubling one-tailed p-values for two-tailed tests.
• Essential for making decisions about hypothesis validity.