Search All of the Math Forum:
Views expressed in these public forums are not endorsed by
Drexel University or The Math Forum.


Luis A. Afonso
Posts:
4,615
From:
LIsbon (Portugal)
Registered:
2/16/05


Against improper sayings: H0_false, H0_true
Posted:
Sep 22, 2013 8:49 AM


The correct way NHST decisions should be formulated
Ronald Fisher had stated : The null hypothesis, H0, can never be proved true or false, when we regard * to prove * exactly as the definition : no way to be denied. Furthermore as we must let a value to the type I error, the decisions are * conditioned * by the value of alpha, the maximum value of p WE ASSUME compatible with H0 true.
If you had found that: Pvalue >= alpha, there is no sufficient evidence H0 is false Pvalue < alpha : H0 is likely/presumably false. Dictionary (Mac Millan): presumably: use for saying you think something is true based on what you know, although you are not really certain.
Luis A. Afonso



