Confidence Intervals - Level of Significance

"The level of significance (α) is the probability of making

a Type I error [e.g., 0.05]." - Donnelly textbook

You're probably wondering what a Type I error is.

Actually, Type I and Type II errors will be discussed in detail during the next lecture.

Suffice it to say at this point:

1. A Type I error is when we reject a null hypothesis

when in fact it is true.

2. The probability of a Type I error = α.

3. For 95% confidence intervals, α = 0.05 and 1 - α = 0.95.

DON'T CONFUSE

LEVEL OF SIGNIFICANCE (e.g., 0.05)

WITH

CONFIDENCE LEVEL (e.g., 95%).

Although they are mathematically related, they are different.

In 1925 R.A. Fisher recommended using the 5% (0.05) level of significance. Unless you have very good reason to use a different value for α, it is wise to stick with 0.05.

Distribution of Means