racd installation
Vis, 1. You've switched from a topic related to racd to one relating to rmgarch. Please start a new thread with an appropriate title (i.e. rmgarch in title). 2. I know that this list may have shrunk over time, but I am not the only person on it. Please address the question to the group, not me personally. 3. I recently added a dispatch function function for gogarchsim to accept goGARCHfilter as well as goGARCHfit classes. This will allow easier fitting, filtering with new data, and then simulating the n-ahead predictive density. When I find time I will add some examples and clean up the warnings. Alexios
On 22/09/2016 02:11, Vis Chen wrote:
Dear Alexios, I have tested "rmgarch.test4.R" in the rmgarch package, and when I run the rmgarch.test4b commands:
data(dji30retw) Dat = dji30retw[, 1:15, drop = FALSE] spec2 = gogarchspec(mean.model = list(model = "AR", lag = 2),
+ variance.model = list(model = "gjrGARCH", garchOrder = c(1,1)),
+ distribution.model = c("mvnorm", "manig", "magh")[2],
+ ica = "fastica")
M.gg = fmoments(spec2, Data = dji30retw[,1:15], n.ahead = 1, roll = 2,
+ solver = "solnp", cluster = cluster, gfun = "tanh", maxiter1=20000, + A.init = diag(15)) There were 15 warnings (use warnings() to see them)
warnings()
Warning messages: 1: unidentified option(s) in fit.control: eval.se <http://eval.se> I tried to solve this by adding: M.gg = fmoments(spec3x, Data = P, n.ahead = 1, roll = 8, *fit.control = list(fixed.se <http://fixed.se> = FALSE, stationarity = TRUE, scale = FALSE)*, solver = "solnp", cluster = cluster, gfun = "tanh", maxiter1=20000, A.init = diag(10)) But I have difficulties interpreting how this fit.control affect the model. Lastly, I tried to apply my own data to the same script and I received these warnings:
M.gg = fmoments(spec3x, Data = P, n.ahead = 1, roll = 8,
fit.control = list(fixed.se <http://fixed.se> = FALSE, stationarity = TRUE, scale = FALSE), + solver = "solnp", cluster = cluster, gfun = "tanh", maxiter1=20000, + A.init = diag(10)) Warning messages: 1: In sqrt(ans$h) : NaNs produced 2: In sqrt(ans$h) : NaNs produced 3: In sqrt(ans$h) : NaNs produced 4: In sqrt(ans$h) : NaNs produced I have some returns that equal to 0 can this be a problem? Would M.gg be invalid as a consequence of these warnings? Regards, Vis On Wed, Sep 21, 2016 at 1:26 PM, Open Business Management Solutions JSC <openbmsjsc at gmail.com <mailto:openbmsjsc at gmail.com>> wrote: It looks like an issue with X display. If you're installing this on a server through a x-terminal, make sure you export the DISPLAY environment, e.g. export DISPLAY=0.0 2016-09-21 16:48 GMT+07:00 Le Hai Trung KNH <trunglh at hvnh.edu.vn <mailto:trunglh at hvnh.edu.vn>>:
> Hi,
> I am trying to install 'racd' package of Alexios to R 3.3.1 and
come up
> with the following error messages.
> -----
> > require(devtools)
> Loading required package: devtools
> > install_bitbucket("alexiosg/racd")
>
> ** preparing package for lazy loading
> Warning in rgl.init(initValue, onlyNULL) :
> RGL: unable to open X11 display
> Warning: 'rgl_init' failed, running with rgl.useNULL = TRUE
> Error : object 'as.vector' is not exported by 'namespace:Matrix'
> ERROR: lazy loading failed for package 'racd'
> * removing '/gpfs/software/R/3.3.1/gcc/lib64/R/library/racd'
> Error: Command failed (1)
>
> -----
> How could I solve for these errors? By the way, when will the
'racd' could
> be downloaded directly from CRAN?
>
> Regards,
> Trung
>
> [[alternative HTML version deleted]]
>
> _______________________________________________
> R-SIG-Finance at r-project.org <mailto:R-SIG-Finance at r-project.org>
mailing list
> -- Subscriber-posting only. If you want to post, subscribe first.
> -- Also note that this is not the r-help list where general R
questions
> should go.
>
--
OpenBMS - *Unlock your potentials*
Level 6, Master Building
41-43 Tran Cao Van Street
Ward 6, District 3, Hochiminh City
[[alternative HTML version deleted]]
_______________________________________________
R-SIG-Finance at r-project.org <mailto:R-SIG-Finance at r-project.org>
mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
<https://stat.ethz.ch/mailman/listinfo/r-sig-finance>
-- Subscriber-posting only. If you want to post, subscribe first.
-- Also note that this is not the r-help list where general R
questions should go.