91Ó°ÊÓ

Hypothesis testing is a fundamental concept in statistics that involves making decisions about populations based on sample data. It begins with formulating two competing hypotheses: the null hypothesis ( H_0) and the alternative hypothesis ( H_1).

• The null hypothesis usually states that there is no effect or no difference, representing the status quo or a baseline to test against.
• The alternative hypothesis is what you want to test for; it suggests that there is an effect or a difference.

The objective of hypothesis testing is to use sample data to decide whether there's enough evidence to reject the null hypothesis in favor of the alternative hypothesis. This decision is aided by calculating a test statistic and comparing it to a critical value, which determines the threshold for significance. Hypothesis testing can lead to two types of errors:

• Type I error occurs if the null hypothesis is rejected when it is actually true.
• Type II error happens if we fail to reject the null hypothesis when the alternative hypothesis is true, denoted as \( \beta \left(\mu^{\prime}\right) \).

The main aim is to minimize these errors, thereby making accurate decisions based on the data.

A Z-test is a type of statistical test that is used when the population variance or standard deviation is known, and the sample size is large (usually \( n \ge 30 \)). It is most commonly used to test hypotheses about the population mean.
To perform a Z-test, calculate the test statistic using the formula:

• \( Z = \frac{\bar{X} - \mu_0}{\sigma/\sqrt{n}} \)

Here:

• \( \bar{X} \) represents the sample mean.
• \( \mu_0 \) is the mean under the null hypothesis.
• \( \sigma \) is the known population standard deviation.
• \( n \) is the sample size.

The computed Z value is then compared against a critical value from the Z-distribution table to decide whether to reject the null hypothesis. This comparison helps determine the statistical significance of our test results. Z-tests are crucial when dealing with normally distributed data or when the Central Limit Theorem applies, allowing us to approximate the distribution of the sample mean by a normal distribution.

The sample size has a significant impact on hypothesis testing and the power of the statistical test. The power of a test is its ability to detect an effect when there is one. It is the probability that the test rejects the null hypothesis correctly when the alternative hypothesis is true.

• A larger sample size generally leads to a higher test power, as it provides more precise estimates of the population parameters.
• As \( n \to \infty \), the parameter \( \sigma/\sqrt{n} \) in the Z-statistic formula becomes very small.

This results in the sampling distribution of the sample mean becoming more concentrated around the true population mean. Consequently, the critical regions for rejecting the null hypothesis become easier to achieve, making Type II error probability \( \beta \left(\mu^{\prime}\right) \) approach zero. This means the likelihood of failing to detect a true effect diminishes with an increase in sample size, enhancing the reliability of the test.

The concept of the normal distribution is integral to hypothesis testing, particularly in the context of Z-tests. The normal distribution is a continuous probability distribution that is symmetric around its mean, often depicted as the "bell curve."

• It is characterized by two parameters: mean ( \( \mu \)) and standard deviation ( \( \sigma \)).
• The total area under the curve is 1, with 68% of the data falling within one standard deviation of the mean, 95% within two, and 99.7% within three.

One reason the normal distribution is pivotal is due to the Central Limit Theorem (CLT), which states that, regardless of the population distribution, the distribution of the sample means approaches normality as the sample size increases. This property allows statisticians to apply the Z-test to a wide variety of datasets across different fields. By using tables of the standard normal distribution, it is possible to make decisions about the null hypothesis in a reliable manner, using the principles of probability and standard deviations to establish critical values and p-values for statistical significance.