Hello,
I am using the nlme package in R:
model <- lme(
response ~ response_type + x_y + x_z - 1,
random = ~ response_type - 1 | group,
weights = varIdent(form = ~ 1 | response_type),
data = data_long,
control = lmeControl(opt = "optim")
)
Is it possible to know what estimation process this is using? For example, is it
using EM? Or is it use Newton-Raphson with GLS/RMLE?
Thanks!
[[alternative HTML version deleted]]
Just reading the documentation, it seems the argument
'lmeControl(opt="optim")' says to use the optim optimizer.
Then the R command ?optim describes what is done.
?optim
"General-purpose optimization based on Nelder-Mead, quasi-Newton
and conjugate-gradient algorithms. It includes an option for
box-constrained optimization and simulated annealing."
On Sat, Sep 20, 2025 at 10:55?AM sasha a <watermelon_canada at
outlook.com>
wrote:
> Hello,
>
> I am using the nlme package in R:
>
> model <- lme(
> response ~ response_type + x_y + x_z - 1,
> random = ~ response_type - 1 | group,
> weights = varIdent(form = ~ 1 | response_type),
> data = data_long,
> control = lmeControl(opt = "optim")
> )
>
> Is it possible to know what estimation process this is using? For example,
> is it using EM? Or is it use Newton-Raphson with GLS/RMLE?
>
> Thanks!
>
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> https://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
[[alternative HTML version deleted]]
On 9/19/2025 2:36 PM, sasha a wrote:> Hello, > > I am using the nlme package in R: > > model <- lme( > response ~ response_type + x_y + x_z - 1, > random = ~ response_type - 1 | group, > weights = varIdent(form = ~ 1 | response_type), > data = data_long, > control = lmeControl(opt = "optim") > ) > > Is it possible to know what estimation process this is using? For example, is it using EM? Or is it use Newton-Raphson with GLS/RMLE? > > Thanks! > > > [[alternative HTML version deleted]] > > ______________________________________________ > R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide https://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code.Hello, I am not sure this answers the question but nlme::lme.formula optimization function defaults to ?optim, which defaults to method Nelder-Mead. Users can change this via ?lmeControl, with two possible values for the method, ?nlminb and optim. Hope this helps, Rui Barradas