search

RobinHankin / hyper2

https://robinhankin.github.io/hyper2/
5 stars 3 forks source link

specificp.ne.test() bug #201

Open RobinHankin opened 1 year ago

RobinHankin commented 1 year ago

Look:

> specificp.ne.test(icons,"L",0)
Error in constrOptim(theta = startp_try, f = objective, grad = gradfun,  : 
  initial value is not in the interior of the feasible region
known R bug (bugzilla ID 17703; wmmin not finite).  Kludge:  maxp_single() will try  a slightly different start point
Error in constrOptim(theta = startp_try, f = objective, grad = gradfun,  : 
  initial value is not in the interior of the feasible region
[snip]

But FWIW I do not think this is actually a 17703 problem at all.

RobinHankin commented 1 year ago

Interestingly, the following two calls do not give an error:

specificp.gt.test(icons,"L",0)
specificp.lt.test(icons,"L",0)