Many thanks to everyone who contributed to this discussion. It looks
like plotly and dygraphs both work well for zooming plots with
thousands of points (and many other things).
Thanks again, I appreciate your help.
best,
Robert Dodier
On Fri, Apr 24, 2020 at 11:11 AM Robert Dodier wrote:
>
>
it's been a long time but I vaguely remember Rvmminb computing
gradients ( and possibly hessians )
subject to constraints. John can say more about this but, if one is going
to go through the anguish of
creating a fitdstr2, then you may want to have it call Rvmminb instead of
whatever is
I thought about this some more and realized my last suggestion is
unlikely to work.
Another possibility would be to create a new function to compute the
Hessian with a smaller step size, but I suspect there will be more
problems.
Possibly a much simpler approach would be to:
Modify the source
On 27/04/20 3:01 am, J C Nash wrote:
:
Peter is correct. I was about to reply when I saw his post.
It should be possible to suppress the Hessian call. I try to do this
generally in my optimx package as computing the Hessian by finite differences
uses a lot more compute-time than solving the
Jim solution posted
Yousri
-- Forwarded message -
From: Jim Lemon
Date: Sun, Apr 26, 2020 at 6:30 AM
Subject: Re: [R] How to edit a dataframe/tibble in R console
To: Yousri Fanous
Hi Yousri,
This may help:
rootstock.df<-as.data.frame(lapply(rootstock,as.vector))
> Dear Ms. Spurdle
I usually refer to myself as "He".
(But then, that's not the whole story...)
I'm not an expert on maximum likelihood approaches.
So, I apologize if the following suggestion is a poor one.
Does your likelihood function have a limit, as alpha approaches zero (say zero)?
If so,
OK, perfecto, justo lo que buscaba.
Es que luego quiero hacer una selección de variables y al "cambiar el nombre"
me fastidiaba.
Gracias
De: Salvador Castillo Raya
Enviado: domingo, 26 de abril de 2020 20:40
Para: Samura . ; Lista R
Asunto: RE: Mantener
Hola Samura,
Realmente no. R no está cambiando tus variables.
El nombre “LeagueN” corresponde al nivel N de la variable League.
Seguramente debes tener otro nivel — como no aparece, éste es el nivel de
referencia. Lo mismo aplica para las demás variables dentro del modelo de
RLM. Eso si, tus
Buenas noches,
Esta sería una forma de hacerlo:
library(ISLR)
data(Hitters)
df <-na.omit(Hitters)
df$League <- ifelse(df$League == 'N', 0, 1)
df$Division <- ifelse(df$Division == 'W', 0, 1)
df$NewLeague <- ifelse(df$NewLeague == 'N', 0, 1)
modelo <- lm(Salary~.,data= df)
Saludos,
Salva
From:
On 4/26/20 12:00 PM, David Winsemius wrote:
On 4/26/20 11:26 AM, Alex Serafim wrote:
there is a function called "confbands", which is no longer available in
software R. It is not "confband" or "confBands", but "confbands", I
need to
use this object to add confidence intervals in my work.
Hola
tengo la siguiente duda,
�C�mo hago para que R no me cambie el nombre de las variables en este ejemplo?
library(ISLR)
data(Hitters)
Hitters<-na.omit(Hitters)
modelo=lm(Salary~.,data=Hitters)
modelo
las variables
League
Division
NewLeague
ahora se llaman
LeagueN
DivisionW
NewLeagueN
On 4/26/20 11:26 AM, Alex Serafim wrote:
there is a function called "confbands", which is no longer available in
software R. It is not "confband" or "confBands", but "confbands", I need to
use this object to add confidence intervals in my work. Why is this
function not available?
attached is
there is a function called "confbands", which is no longer available in
software R. It is not "confband" or "confBands", but "confbands", I need to
use this object to add confidence intervals in my work. Why is this
function not available?
attached is an image that shows how the graph should look,
On Sun, 26 Apr 2020, Patrick (Malone Quantitative) wrote:
A package on github called yamlpack appears to do a lot of the work
involved. I can't vouch for it personally.
https://github.com/combiz/yamlpack
Thanks, Patrick. I'll take a close look at this, too.
Stay well,
Rich
On Sun, 26 Apr 2020, Sarah Goslee wrote:
Not so coincidentally, I just worked thru this for myself.
Thanks, Sarah.
Stay well,
Rich
__
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
A package on github called yamlpack appears to do a lot of the work
involved. I can't vouch for it personally.
https://github.com/combiz/yamlpack
On Sun, Apr 26, 2020 at 1:12 PM Sarah Goslee wrote:
> Not so coincidentally, I just worked thru this for myself.
>
> I did want to rebuild and
Not so coincidentally, I just worked thru this for myself.
I did want to rebuild and reinstall everything, but as automatically
as possible, although in a way that let me see what happened and what
went wrong.
http://numberwright.com/2020/04/clean-and-new/
There are several things to consider:
I am using the 'coin' package to compute bootstrapped correlations. I am able
to extract the p-value with confidence intervals as well as the test statistic
Z. However, I am unable to find rho, i.e. the correlation coefficient. Can
someone help?
Kind regards,
Christine
[[alternative
On Sun, 26 Apr 2020, Bert Gunter wrote:
?install.packages (argument dependencies)
which is explicitly pointed to by ?update.packages
"Warning
Take care when using dependencies (passed to install.packages) with
update.packages, for it is unclear where new dependencies should be
installed.
?install.packages (argument dependencies)
which is explicitly pointed to by ?update.packages
"Warning
Take care when using dependencies (passed to install.packages) with
update.packages, for it is unclear where new dependencies should be
installed. The current implementation will only allow it
cpolwart wrote:
> the event can only happen once
>
1. Yes, I'm not interested in repeat events.
2. I just had an interest in learning the code for survival analysis
in case there are: event, left censored (not left truncating) and
right censored, nothing more! But I no longer want to burden anyone
After upgrading from -3.6.2 to -4.0.0 I ran 'update.packages()' and spent
time rebuilding dependencies, too. Is there a script or method that
automates package updates after a major version change in R?
My web searches on this topic found tips for only regular package updates
without rebuilding
Las pruebas de normalidad en muestras grandes sufren de sobre-sensiblidad.
Según lo que he leído (y cualquier reviewer aceptará...) cuando hay una
muestra grande la inspección visual del qq-plot será suficiente!
El dom., 26 abr. 2020 a las 12:51, Carlos Ortega ()
escribió:
> Hola,
>
> Aquí
Hola María,
La mayoría de los paquetes de R que trabajan con datos espaciales permiten
mapear datos proyectados.
Pero si no eres más específica de al menos decirnos con que paquete estás
trabajando es muy difícil poder ayudarte.
Manuel
El dom., 26 abr. 2020 a las 5:01, María Ángeles Onieva (<
Peter is correct. I was about to reply when I saw his post.
It should be possible to suppress the Hessian call. I try to do this
generally in my optimx package as computing the Hessian by finite differences
uses a lot more compute-time than solving the optimization problem that
precedes the usual
Thank you Jim.
It works like a charm
Yousri
On Sat, Apr 25, 2020 at 11:25 PM Yousri Fanous
wrote:
> I recently installed R 3.6.3 on my windows laptop.
>
> R version 3.6.3 (2020-02-29)
>
> I am trying to import a stata .dta file to R
>
> >url<-“http://www.stata-press.com/data/r10/rootstock.dta”
Hola!
En una búsqueda rápida por google:
https://mappinggis.com/2018/08/analisis-espacial-con-r-usa-r-como-un-sistema-de-informacion-geografica/
http://rstudio-pubs-static.s3.amazonaws.com/19879_7e13ab80d5ed416c8e235bd6bb93cf3e.html
El primer enlace es general a un libro interesante.
El segundo
On 2020-04-26 10:48, Medic wrote:
Very grateful for the all comments!
My data contains:
• left censored
• right censored
• events
(interval censored does not contain!)
(P.S. I understood, that the code with "type = 'left'" is not
suitable, because is ONLY for left-censored.)
I wanted to get
Buenos días,
Me gustaría representar los casos en un mapa que fuera interactivo en el
sentido de que fueran apareciendo según fecha de aparición.
Dispongo de las coordenadas X e Y, en proyección UTM y la fecha de
aparición.
La mayoría de tutoriales que encuentro por internet de R explican la
Hola,
Aquí tienes una forma alternativa:
https://stackoverflow.com/questions/17125458/r-shapiro-test-cannot-deal-with-more-than-5000-data-points
Saludos,
Carlos Ortega
www.qualityexcellence.es
El dom., 26 abr. 2020 a las 12:11, Rafael Santamaria (<
rsantamar...@gmail.com>) escribió:
> Hola!
>
Hi Robert,
Maybe you can use something simple like this:
zoomInScatterPlot<-function(x=NULL,y,...) {
if(is.null(x)) x<-1:length(y)
plot(x,y,...)
xylim<-par("usr")
boxed.labels(xylim[1]-diff(xylim[1:2])/20,
xylim[3]-diff(xylim[3:4])/10,"Done")
xy1<-locator(1)
done<-FALSE
while(!done) {
Hola!
Necesito evaluar la normalidad de una variable para la que tengo más de
5000 observaciones.
Shapiro-Wilks no funciona para muestras mayores 5000 observaciones.
AAlshap <- lapply(AAdf, shapiro.test)
Error in FUN(X[[i]], ...) : sample size must be between 3 and 5000
Alguna sugerencia?
Very grateful for the all comments!
My data contains:
• left censored
• right censored
• events
(interval censored does not contain!)
(P.S. I understood, that the code with "type = 'left'" is not
suitable, because is ONLY for left-censored.)
I wanted to get the appropriate code for my so mix
The optim() function has trouble calculating derivatives at/near the boundary,
because it is using a simplistic finite-difference formula centered on the
parameter. optimx::optimr() may work better.
-pd
> On 26 Apr 2020, at 09:02 , Abby Spurdle wrote:
>
> I ran your example.
> It's possible
Dear Ms. Spurdle ,
Thanks for looking into this. I think that you are correct in that it
is a problem with the hessian calculation. It seems that fitdistr()
explicitly sets hessian=TRUE, with no possibility of opting out.
It also seems that optim() ignores the "lower" argument when
fitdistr computes a Hessian matrix.
I think optim ignores the lower value computing the Hessian.
Here's the result after removing the Hessian and Hessian-dependent info:
> str (fit)
List of 3
$ estimate: Named num [1:2] 0.000149 1.0797684972
..- attr(*, "names")= chr [1:2] "alpha" "beta"
I recently installed R 3.6.3 on my windows laptop.
R version 3.6.3 (2020-02-29)
I am trying to import a stata .dta file to R
>url<-“http://www.stata-press.com/data/r10/rootstock.dta”
>library(tidyverse)
>library(haven)
>rootstock<-read_dta(url)
All works as expected.
>class(rootstock)
I ran your example.
It's possible that it's another bug in the optim function.
Here's the optim call (from within fitdistr):
stats::optim(x = c(1, 4, 1, 2, 3, 1, 1, 1, 2, 2, 2, 2, 1, 1,
1, 1, 1, 4, 4, 3, 1, 2, 2, 1, 1, 3, 1, 1, 1, 4, 1, 1, 1, 1, 1, #more lines...
1, 4, 1, 1, 1, 5, 5, 5, 4, 5, 2,
38 matches
Mail list logo