In statistical analysis, there are two types of errors: Type I is a false positive, Type II is a false negative. I still get these mixed up. I spent five minutes trying to think of a clever mnemonic and I couldn’t come up with anything. Any ideas?
A nice summary from wikipedia (below the fold):
When an observer makes a Type I error, they are observing a statistical difference when in truth there is none (rejecting a null hypothesis when it is actually true). For example, a pregnancy test with a positive result (indicating that the person taking the test is pregnant) has produced a false positive in the case where the person is not pregnant. A Type II error, or a “false negative”, is the error of failing to reject a null hypothesis when the alternative hypothesis is the true state of nature. For example, a type II error occurs if a pregnancy test reports negative when the person is, in fact, pregnant.
5 thoughts on “errors of all types”
Oh crud. I thought I had this right, and I thought I had a good way to remember it–I heard rumors a student had been told to his face by a professor that they were a type II error in the admissions process. So harsh I couldn’t forget it, and will now probably never get them right.
This is how I remember it. The P in positive has one vertical line (type I). The N in negative has two vertical lines (type II). A little goofy perhaps, but it works for me!
Arg. This shouldn’t be as confusing as I’m finding it right now. But the story method of remembering is correct. If the null was false and it did not get rejected, that is a type 2. I guess I had the error number correct, but was wrong on the association with false positive (1) or false negative (2)
There wouldn’t be any confusion if it was only one type of error that exist. So, what I do is simply to remember the type I error as stated in wiki and just forget the type II. Never read the two together.
It is extremely easy to remember only one, and it is extremely easy to derived the other one when you need it.
Unless I’m totally mistaken, Type II is a double (II) negative. You are wrong about being null. Type I is the other type. Did I just over simplify? I’d love to hear if I’m correct, or if this is a type II error.