[R] [FORGED] Re: nls model parameter compare?

[Rolf Turner]

On 26/08/15 10:59, Bert Gunter wrote:

<SNIP>

> Gratuitous Question born from personal frustration with such
> queries(so feel free to ignore): Why are you using (statistical)
> procedures that you do not understand? Of course the parameters for
> different treatments are "different"! -- but how and with what
> importance depends on the context in which you are working. Instead of
> fooling with cryptic statistical mumbo jumbo that invite misuse -- and
> which are probably valueless or idiotic anyway --  why don't you make
> some graphs and consider what they say in terms of the substantive
> issues at play? (Of course I know the answer -- it is because that is
> what your academic culture/journals demand. But therein lies the
> problem: what is demanded is junk).

Fortune nomination!!!

cheers,

Rolf Turner

-- 
Technical Editor ANZJS
Department of Statistics
University of Auckland
Phone: +64-9-373-7599 ext. 88276