Accepting the null


Fortran must die
I was always taught you can never accept the null, but I have seen this comment before for bounds testing.

"For accepting or rejecting the null hypothesis there are 2 critical bounds, upper and lower bound. If the F-value of bound test is larger than upper bound value at 5% level of significance then null hypothesis is rejected. Moreover, if the F-value is smaller than the lower bound value, then the null hypothesis is accepted. If the F-value is in between the upper and lower bound that would fall in inconclusive zone, showing that there will be no affirmative results and decision cannot be made for the long run relationship."


Active Member
It seems strange to me too. If the F value is very high then there is a likely reason - probably there is a real difference between the groups. However, no matter how low the F values gets, this doesn't mean that the real difference is is more likely to be zero than some non zero value. In fact, in the real world the real difference is very unlikely to be exactly zero.