Timeline for What is the relationship between $p$ values and Type I errors
Current License: CC BY-SA 3.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Dec 18, 2014 at 22:09 | history | edited | Horst Grünbusch | CC BY-SA 3.0 |
added 339 characters in body
|
| Dec 18, 2014 at 21:53 | comment | added | Horst Grünbusch | I didn't say to change $\alpha$. The second paragraph is just the converse of the decision rule "reject iff $p<\alpha$". | |
| Dec 18, 2014 at 19:53 | comment | added | John | How could the $p$ be the minimum $\alpha$? What would the maximum be? Maybe you mean that it could have been the minimum criterion if you had selected it a priori. You can't change $\alpha$ after the finding has been observed. | |
| Dec 18, 2014 at 18:46 | comment | added | tomka | I did not rate down - would be interested why the reader did so. | |
| Dec 18, 2014 at 18:33 | comment | added | tomka | So if I imagine that (minimum $\alpha=p$), wouldn't $p$ then always indicate the probability of falsely rejecting the null? | |
| Dec 18, 2014 at 18:17 | history | answered | Horst Grünbusch | CC BY-SA 3.0 |