It seems like the default max.it = 25 on mlEstimationTruncDist() is way too low and might trick users into thinking the estimation has converged (to the wrong values). The unit tests always use at least 500, and I often find myself using 1 000, so I was wondering if the default should be set to one of the latter.
Rene's suggestion: 100. Our method is derivative-based and ?optim says " ‘maxit’ The maximum number of iterations. Defaults to ‘100’ for the derivative-based methods, and ‘500’ for ‘"Nelder-Mead"’`.
It seems like the default
max.it = 25
onmlEstimationTruncDist()
is way too low and might trick users into thinking the estimation has converged (to the wrong values). The unit tests always use at least 500, and I often find myself using 1 000, so I was wondering if the default should be set to one of the latter.