[R-sig-ME] Question about gls

Dan Brooks dan at brooksbaseball.net
Fri Mar 23 20:52:15 CET 2018


Hi Louise:

Perhaps try what seems to be suggested here?
http://r.789695.n4.nabble.com/Extracting-Phi-from-gls-lme-td803811.html

coef(fit.gls$modelStruct$corStruct,unconstrained = FALSE)

Best-
Dan

On Fri, Mar 23, 2018 at 3:27 PM, Louise Ryan <Louise.M.Ryan at uts.edu.au>
wrote:

> Hi there,
>
> I am using your function gls in R to fit some AR models (it is part of a
> larger thing I am trying to do). I can see from the printed output that the
> function is estimating the AR parameter.  But I CANNOT for the life of me
> figure out how to extract this parameter so I can use it for something else.
>
> Here’s a bit of code that simulates some data and runs the model.
>
> #####
> # Set true parameter values:
> beta0True <- 0.3
> beta1True <- 1.6
> sigmaTrue <- 0.5
> rhoTrue <- 0.2
>
> # Generate data:
> set.seed(1)
> n <- 500
> x <- seq(0,1,length=n)
> epsilon <- rep(NA,n)
> epsilon[1] <- sigmaTrue*rnorm(1)
> for (i in 2:n) {epsilon[i] <- rhoTrue*epsilon[i-1] + sigmaTrue*rnorm(1)}
> y <- beta0True + beta1True*x + epsilon
>
> fit.gls <- gls(y~x,  correlation=corAR1())
> print(summary(fit.gls))
> ###########################
>
> For my little simulation, the parameter Phi is being estimated as .1748786.
>
> I have looked at attributes(fit.gls) and just cannot figure out where this
> estimate is stored!
>
> I’d appreciate your help!
>
> Louise
> UTS CRICOS Provider Code: 00099F DISCLAIMER: This email message and any
> accompanying attachments may contain confidential information. If you are
> not the intended recipient, do not read, use, disseminate, distribute or
> copy this message or attachments. If you have received this message in
> error, please notify the sender immediately and delete this message. Any
> views expressed in this message are those of the individual sender, except
> where the sender expressly, and with authority, states them to be the views
> of the University of Technology Sydney. Before opening any attachments,
> please check them for viruses and defects. Think. Green. Do. Please
> consider the environment before printing this email.
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>

	[[alternative HTML version deleted]]



More information about the R-sig-mixed-models mailing list