91Ó°ÊÓ

In hypothesis testing, it's crucial to understand the possible errors that can occur. A Type I error happens when you wrongly reject a true null hypothesis. Think of it as a false alarm, where you believe there's an effect or difference when there isn't. It's denoted by the symbol \( \alpha \), which is also known as the significance level of a test. This value represents the probability of committing a Type I error and it's typically set by the researcher, commonly at 0.05 or 5%.

A Type II error, represented by \( \beta \), occurs when you fail to reject a false null hypothesis. This might be considered a missed opportunity to detect an actual effect. The probability of committing a Type II error is influenced by several factors, such as the sample size, the effect size, and the chosen significance level. Minimizing both \( \alpha \) and \( \beta \) is a balancing act since decreasing one usually increases the other, given a fixed sample size.

The test statistic is a critical part of hypothesis testing. It's a formula that helps us determine whether to reject the null hypothesis, \( H_0 \), based on the data collected. When the population standard deviation is known and the sample size is sufficiently large, we often use the z-test statistic, which under the standard normal distribution, compares the sample mean to the population mean stated by the null hypothesis.

In the given problem, the test statistic is calculated as \( z = \frac{\bar{x} - 10}{0.1} \) where \( \bar{x} \) is the sample mean. This z-score tells us how many standard deviations the sample mean is away from the population mean under the null hypothesis. If this value falls into the critical region (for instance, being lower than -1.28 as in our example) we would reject the null hypothesis.

The standard normal distribution, also called the z-distribution, is a special case of the normal distribution. It has a mean of 0 and a standard deviation of 1. It is widely used in hypothesis testing because many test statistics, including z-scores, can be standardized and then compared to this distribution.

To find the probabilities related to the z-scores (like in calculating \( \alpha \)), you look up the z-value in a standard normal distribution table or use software to find the area under the curve. This area gives us the probability of observing a test statistic as extreme as, or more extreme than, the one calculated from our sample, assuming the null hypothesis is true.

The statistical power of a hypothesis test is its ability to detect an effect when there actually is one. In other words, it's the probability of correctly rejecting a false null hypothesis. Therefore, it is represented as \(1 - \beta\), where \(\beta\) is the probability of a Type II error.

High power is desirable and means that the test is sensitive enough to pick up on the effects that are present. Factors that influence power include the sample size, the chosen significance level (\(\alpha\)), and the effect size - the larger the effect size or sample, or the higher the significance level, the more powerful the test. In our example, by calculating the test power as \(1 - \beta_{9.8}\) and \(1 - \beta_{9.5}\), we see how likely it is that the test will find a true difference when the actual average lifetime of the pens differs from the hypothesized mean of 10 hours.