91Ó°ÊÓ

In hypothesis testing, a Type I error is a kind of error that can occur when we reject a true null hypothesis. Simply put, it's like sounding a false alarm. When the allergist tests the hypothesis that at least 30% of the public is allergic to cheese products, and wrongly concludes that they are indeed allergic when they are not, a Type I error has been made.
This error leads to an incorrect conclusion, thinking there is an effect or a difference when there isn't one. Imagine claiming that more people are allergic to cheese than really are—that's the essence of a Type I error. Type I errors are often represented by the Greek letter \(\alpha\), which stands for the significance level used in the test, usually set at 0.05 or 5%. This value indicates the probability of making a Type I error. Lowering \(\alpha\) reduces the risk of committing this type of error, but it comes with trade-offs.

• **Type I Error**: Rejecting true null hypothesis
• **Example**: Incorrectly believing more than 30% are allergic
• **Symbol**: \(\alpha\)
• **Risk**: False alarms

A Type II error happens when we fail to reject a false null hypothesis. It's like missing a signal or the opposite of a false alarm. It occurs when the allergist concludes wrongly that less than 30% of the public is allergic when, in fact, 30% or more are.
This error leads to a belief that there is no significant effect or difference when actually there is. It's similar to failing to detect an allergy that actually exists. If the allergist's analysis shows no significant level of allergy when there is one, that's a Type II error. This kind of error is represented by the Greek letter \(\beta\), and unlike \(\alpha\), it is not typically set prior but rather calculated after data analysis.

• **Type II Error**: Accepting a false null hypothesis
• **Example**: Missing the fact that at least 30% are allergic
• **Symbol**: \(\beta\)
• **Risk**: Missed detections

The null hypothesis is a fundamental concept in hypothesis testing. It acts as the default position that there is no relationship or difference between two measured phenomena. In our allergist's example, the null hypothesis would state that less than 30% of the public is allergic to cheese products.
The purpose of the null hypothesis is to be tested and potentially contradicted by empirical data. If you reject it, you're suggesting that there's enough evidence to support the alternative hypothesis, such as more than 30% being allergic. It's critical for maintaining statistical objectivity. The null hypothesis is commonly denoted by \(H_0\), and it serves as the benchmark against which the test statistics are evaluated.

• **Null Hypothesis**: Assumes no effect or no difference
• **Example**: Less than 30% are allergic
• **Symbol**: \(H_0\)
• **Role**: Baseline for testing