Understanding type I and type II errors
When we are talking about errors in hypothesis testing, we are not talking about typos, or even mistakes made with the study to gather data. We are talking about coming up with the wrong answer. Earlier, we went over there only being two outcomes to a hypothesis test; either you accept and reject
or you accept
and reject
. Those are the only two possible outcomes. We also discussed that this is based on probability and there will always be a small chance that you choose incorrectly. Even a 95% chance of being right means you are wrong 1 in 20 times. In other words, both of the two possible outcomes have an error associated with them. These errors are called type I and type II errors.
Type I error
Type I error is when you incorrectly accept and reject
. Your p-value was smaller than your alpha, so you said there was a statistically significant difference between the two groups, but it turns out they were really just the same thing. Going...