I find it very difficult to believe that anyone in
Post# of 153887
(Total Views: 742)
Posted On: 11/06/2020 3:49:19 PM
I find it very difficult to believe that anyone in their right mind would let the trial run if the interim demonstrated 70% mortality reduction.
Anybody, I don't care who they are, who observed a 70% mortality reduction with leronlimab in the interim analysis would have done somehting with this result, I think.
But I am clueless as to the mathematics of "power".
The meaning of p-value is relatively straightforward.
The "p-value" answers the question: What is the probablity that the observed results occurred by random chance?
Often the FDA uses a p-value of 0.05.
A P-value of 0.05 can be translated into the following English sentence:
The probablitity that the drug caused the observed results is greater than 95%.
This reference, https://www.statisticsteacher.org/2017/09/15/what-is-power/, describes power as:
"Power is the probability that a test of significance will detect an effect that is present."
So just using the plain text of the definition of power and p-value, it seems to me that no one should care what the "power" is if the p-value has been hit.
Who cares what the probability of success was if the p-value indicates success has been achieved?
Unfortunately for my confusion, my point of view is apparently confirmed by the reference that I listed above. This reference provides the following example:
In Study A, the key element is the p-value of 0.034. Since this is less than alpha of 0.05, the results are statistically significant and we can stop at the blue stop sign in the START box. While the study is still at risk of making a Type I error, this result does not leave open the possibility of a Type II error. Said another way, the power is adequate to detect a difference because they did detect a difference that was statistically significant. It does not matter that there is no power or sample size calculation when the p-value is less than alpha.
So the reference I listed would seem to support the thesis that if you hit the p-value then the power is not important.
So from this can the conclusion be drawn that the CD12 interim analysis missed the p-value? Don't ask me. I am more confused than ever
Anybody, I don't care who they are, who observed a 70% mortality reduction with leronlimab in the interim analysis would have done somehting with this result, I think.
But I am clueless as to the mathematics of "power".
The meaning of p-value is relatively straightforward.
The "p-value" answers the question: What is the probablity that the observed results occurred by random chance?
Often the FDA uses a p-value of 0.05.
A P-value of 0.05 can be translated into the following English sentence:
The probablitity that the drug caused the observed results is greater than 95%.
This reference, https://www.statisticsteacher.org/2017/09/15/what-is-power/, describes power as:
"Power is the probability that a test of significance will detect an effect that is present."
So just using the plain text of the definition of power and p-value, it seems to me that no one should care what the "power" is if the p-value has been hit.
Who cares what the probability of success was if the p-value indicates success has been achieved?
Unfortunately for my confusion, my point of view is apparently confirmed by the reference that I listed above. This reference provides the following example:
In Study A, the key element is the p-value of 0.034. Since this is less than alpha of 0.05, the results are statistically significant and we can stop at the blue stop sign in the START box. While the study is still at risk of making a Type I error, this result does not leave open the possibility of a Type II error. Said another way, the power is adequate to detect a difference because they did detect a difference that was statistically significant. It does not matter that there is no power or sample size calculation when the p-value is less than alpha.
So the reference I listed would seem to support the thesis that if you hit the p-value then the power is not important.
So from this can the conclusion be drawn that the CD12 interim analysis missed the p-value? Don't ask me. I am more confused than ever
(3)
(0)