I'm not positive of the question you are asking b/c I lost some of initial
messages in thread but I think
>predict(model, type="expected")
gives fitted probabilities
Apologies if I answered a question no one asked.
On Feb 28, 2013, at 7:45 PM, lisa wrote:
> I do appreciate this answer. I hea
This update adds an intercept option (by popular request) - now one can fit a
model without an intercept
Glmnet is a package that fits the regularization path for a number of
generalized linear models, with with "elastic net"
regularization (tunable mixture of L1 and L2 penalties). Glmnet uses
Thanks, everyone, I will definitely avoid it. Is there any tips on naming
variables? I've seen the Google R style guider and Hadley R style guide.
For example, I want to use pie_t, to denote stationary distribution pie at
time t. Both "pi" and "pie" are function names themselves.
Mike
On Fri,
> Gabor Grothendieck wrote
>> On Fri, Mar 1, 2013 at 7:16 PM, Frank Harrell <
>
>> f.harrell@
>
>> > wrote:
>>> The lattice package uses special logic to allow for multiple
>>> left-hand-side
>>> variables in a formula, e.g. y1 + y2 ~ x. Is there an elegant way to do
>>> this outside of lattice?
> See fortune("dog").
To wit:
"Firstly, don't call your matrix 'matrix'. Would you call your dog 'dog'?
Anyway, it might clash with the function 'matrix'"
I once had a cat named "kitty" and she never had a problem with it.
Clashes between non-functions and functions that cause problems are not
Thank you Bill. A temporary re-arrangement of the formula will allow me to
do the usual subset= na.action= processing afterwards. Nice idea. I don't
need the dot notation very often for this application.
Frank
William Dunlap wrote
> I don't know how much of the information that model.frame supp
Thanks for your reply Gabor. That doesn't handle a mixture of factor and
numeric variables on the left hand side.
Frank
Gabor Grothendieck wrote
> On Fri, Mar 1, 2013 at 7:16 PM, Frank Harrell <
> f.harrell@
> > wrote:
>> The lattice package uses special logic to allow for multiple
>> left-hand
On 03/02/2013 01:12 PM, Sarah Goslee wrote:
On Fri, Mar 1, 2013 at 7:06 PM, C W wrote:
Thanks, that was just an example I came up with. I was just curious if
using same variable names in different functions would cause problems.
No. The environment of a function is independent of other functi
I don't know how much of the information that model.frame supplies you need,
but you could make a data.frame containing all the variables on both sides of
them
formula by changing lhs~rhs into ~lhs+rsh before calling model.frame. E.g.,
f <- function (formula) {
if (length(formula) == 3) { #
On Fri, Mar 1, 2013 at 7:16 PM, Frank Harrell wrote:
> The lattice package uses special logic to allow for multiple left-hand-side
> variables in a formula, e.g. y1 + y2 ~ x. Is there an elegant way to do
> this outside of lattice? I'm trying to implement a data summarization
> function that log
The lattice package uses special logic to allow for multiple left-hand-side
variables in a formula, e.g. y1 + y2 ~ x. Is there an elegant way to do
this outside of lattice? I'm trying to implement a data summarization
function that logically takes multiple dependent variables. The usual
invocati
On Fri, Mar 1, 2013 at 7:06 PM, C W wrote:
> Thanks, that was just an example I came up with. I was just curious if
> using same variable names in different functions would cause problems.
No. The environment of a function is independent of other functions.
> Especially with reserved words.
Y
On 2013-02-28 15:05, Elaine Kuo wrote:
Hello,
I am using library(latticeExtra) resizePanels to have better visual display
in dotplot (lattice).
However, some panels became smaller and the strip letters of those panels
were partially missing.
Please kindly advise how to keep all strip letters rem
Thanks, that was just an example I came up with. I was just curious if
using same variable names in different functions would cause problems.
Especially with reserved words.
Mike
On Fri, Mar 1, 2013 at 5:45 PM, David Winsemius wrote:
>
> On Mar 1, 2013, at 1:56 PM, C W wrote:
>
> > Hi list,
>
Hello,
You're right, it should be names(coef(model)). I had tested the function
before changing it to allow for a zero intercept. Sorry for the mess.
realroots <- function(model, b){
is.zero <- function(x, tol = .Machine$double.eps^0.5) abs(x) < tol
if(names(coef(model))[1] ==
Thanks.
Rui Barradas
Em 01-03-2013 20:35, arun escreveu:
Hi Rui,
Looks like a bug:
###if(names(model)[1] = "(Intercept)")
Should this be:
if(names(model)[1] == "(Intercept)")
A.K.
- Original Message -
From: Rui Barradas
To: Mike Rennie
Cc: r-help Mailing List
Sent: Friday, Marc
On Mar 1, 2013, at 1:56 PM, C W wrote:
> Hi list,
> I am writing several functions and running out variable names. I am using
> words such as "t", "c", "matrix" to keep the notation same as formulas I am
> using.
>
> For example I have,
>
> unnormalized <- function(t, x, y){
>val <- rnorm(
Hi,
I think I got it. I will try tomorrow morning and if works I will writte
the code if you want please no send the question to avoid others time
Thanks a lot
2013/3/1 Jose Narillos de Santos
> Hi all,
>
> I want to plot moving correlation and to complete color on the correlation
> line and "
You can avoid doing the algebra by using uniroot() to numerically find where
the predicted value hits your desired value. E.g.,
> fit <- lm(a ~ poly(b, 4))
> invertFit <- function(a){
+ stopifnot(length(a)==1)
+ uniroot(function(b)predict(fit, newdata=list(b=b))-a,
interval=range
Doh- I'm a moron. I get it now. The last line is the confirmation that
function "realroots" is working. Sorry- late in the day on a friday.
Thanks everyone for your help with this- Uber-useful, and much appreciated.
Mike
On 3/1/13, Mike Rennie wrote:
> Hi Peter,
>
> With the edit you suggested,
Hi list,
I am writing several functions and running out variable names. I am using
words such as "t", "c", "matrix" to keep the notation same as formulas I am
using.
For example I have,
unnormalized <- function(t, x, y){
val <- rnorm(t, mean=x, var=y)
return(val)
}
metropolis <- functio
Hi,
It seems like you haven't even looked at the output of d2, (first d2)
d2<- cbind(d,d1)
head(d2,3)
# m1 n1 x1 y1 p11 p12 term1_p0 term1_p1 Qm Qn
#1 2 2 0 0 0 0.0 0.81450625 0.31640625 1.000 1.000
#2 2 2 0 1 0 0.5 0.08573750 0.21093750 0.666 0.666
#3 2 2 0 2 0 1.0
Hi Peter,
With the edit you suggested, now I'm just getting back the value of a
that I put in, not the expected value of b...
> cbind(a,b)
a b
[1,] 1 1.0
[2,] 2 2.0
[3,] 3 2.5
[4,] 4 3.0
[5,] 5 3.5
[6,] 6 4.0
[7,] 7 6.0
[8,] 8 7.0
[9,] 9 7.5
[10,] 10 8.0
#a of 5 should
On 2013-03-01 13:06, Mike Rennie wrote:
Hi guys,
Perhaps on the right track? However, not sure if it's correct. I fixed
the bug that A.K. indicated above (== vs =), but the values don't seem
right. From the original data, an a of 3 should give b of 2.5.
realroots <- function(model, b){
+
Hi guys,
Perhaps on the right track? However, not sure if it's correct. I fixed
the bug that A.K. indicated above (== vs =), but the values don't seem
right. From the original data, an a of 3 should give b of 2.5.
> realroots <- function(model, b){
+ is.zero <- function(x, tol = .Machine$
On Mar 1, 2013, at 6:22 AM, Lisa Sheng wrote:
> Sorry I was asking a question inspired by the original question, which
> relates to the out of sample prediction.
>
> He was asking why it's not of the probability range, and I also found that
> clogit only gives out linear predictors in both es
> For Sectors the results are correct, but for some (Country, Industry,
> FISCALYEAR) combinations or (Country,FISCALYEAR)combinations > the result
> don't match the spreadsheet (Excel) computation
Well the normal assumption here is to assume that Excel is wrong. I am not
joking. Spreadsheets ar
Hi Rui,
Looks like a bug:
###if(names(model)[1] = "(Intercept)")
Should this be:
if(names(model)[1] == "(Intercept)")
A.K.
- Original Message -
From: Rui Barradas
To: Mike Rennie
Cc: r-help Mailing List
Sent: Friday, March 1, 2013 3:18 PM
Subject: Re: [R] solving x in a polynomial
On 03/01/2013 11:21 AM, Joseph Clark wrote:
Date: Fri, 1 Mar 2013 10:21:02 -0800
From: mtmor...@fhcrc.org
likely you will be able to install with
install.packages("path/to/SVGAnnotation_0.93-1.tar.gz", repos=NULL,
type="source")
Thanks, I think you're on the right track but it still didn't
Hello,
Try the following.
a <- 1:10
b <- c(1, 2, 2.5, 3, 3.5, 4, 6, 7, 7.5, 8)
dat <- data.frame(a = a, b = b) # for lm(), it's better to use a df
po.lm <- lm(a~b+I(b^2)+I(b^3)+I(b^4), data = dat); summary(po.lm)
realroots <- function(model, b){
is.zero <- function(x, tol = .Machine
For Sectors the results are correct, but for some (Country, Industry,
FISCALYEAR) combinations or (Country, FISCALYEAR) combinations the
result don't match the spreadsheet (Excel) computation, so verifying
from experts, whether I am using ddply correctly with the right
intention?
On Fri, Mar 1,
I suppose you have your filenames stored in a character vector, which I
will name "myfiles". (Within R, it is not a "list"; lists have a special
structure).
There is no such thing as a "tab separated matrix" in R. "tab separated"
would refer to the file, I presume.
for (nm in myfiles) {
tmpdat
Is there any chance you meant
ddply (dat1 , .(Sector, FISCALYEAR), summarise, WROE=wavg(ROE, MKT))
??
It gives a result but I have no idea if it makes sense.
John Kane
Kingston ON Canada
> -Original Message-
> From: anandpu...@gmail.com
> Sent: Fri, 1 Mar 2013 14:13:37 -0500
> To: r-he
See my last post which crossed yours.
John Kane
Kingston ON Canada
> -Original Message-
> From: anandpu...@gmail.com
> Sent: Fri, 1 Mar 2013 14:33:17 -0500
> To: jrkrid...@inbox.com
> Subject: Re: [R] Conditional Weighted Average (ddply or any other
> function)
>
> oops - it should be
oops - it should be MKT, I have been playing with a number of data
sets simultaneously.
ddply (dataread , .(Sector, FISCALYEAR), summarise,WROE=wavg(ROE, MKT)))
On Fri, Mar 1, 2013 at 2:23 PM, John Kane wrote:
> Okay I got the data but you seem to have an undefined variable in wavg.
> You write
Thanks for the data .
You have an undefined variable in the ddply statement. There is no MKTCAP in
the data.frame.
You also have one two many ) in the statement. I think it should read:
ddply (dat1 , .(Sector, FISCALYEAR), summarise, WROE=wavg(ROE, MKTCAP))
John Kane
Kingston ON Canada
Okay I got the data but you seem to have an undefined variable in wavg.
You write :
ddply (dataread , .(Sector, FISCALYEAR), summarise,WROE=wavg(ROE, MKTCAP)))
There is no MKTCAP in the data.frame. Also there is one too many ) in the
equation: I think you mean :
ddply (dataread , .(Sector, FISC
> Date: Fri, 1 Mar 2013 10:21:02 -0800
> From: mtmor...@fhcrc.org
>
> likely you will be able to install with
>
> install.packages("path/to/SVGAnnotation_0.93-1.tar.gz", repos=NULL,
> type="source")
>
Thanks, I think you're on the right track but it still didn't work for me.
Perhaps there's
Hi John,
The sample size is huge involving 10,000 + firms. I have put a
representative sample using dput ( Name, ticker and country have been
changed so that firms cannot be identified due to proprietary data
set, also EPS is not required and removed from the dataset)
structure(list(NAME = struct
help.search("polynomial")
---
Jeff NewmillerThe . . Go Live...
DCN:Basics: ##.#. ##.#. Live Go...
Live: OO#.. Dead: OO#.. Playin
Hi there,
Does anyone know how I solve for x from a given y in a polynomial
function? Here's some example code:
##example file
a<-1:10
b<-c(1,2,2.5,3,3.5,4,6,7,7.5,8)
po.lm<-lm(a~b+I(b^2)+I(b^3)+I(b^4)); summary(po.lm)
(please ignore that the model is severely overfit- that's not the point).
On 3/1/2013 9:12 AM, Joseph Clark wrote:
Hi all:I found some great demonstrations of interactive presentation graphics generated
in R with the SVGAnnotation package,
here:http://www.omegahat.org/SVGAnnotation/http://www.omegahat.org/SVGAnnotation/SVGAnnotationPaper/SVGAnnotationPaper.htmlI
tr
On 03/01/2013 06:13 AM, Simon Zehnder wrote:
Dear R-users,
I am working on a project that uses S4-classes. At some point I encountered the
problem - well known to R - that I have to pass 3 different objects to a
function, that should modify several slots of them and of course there is no
pass
You did not get any replies because this is largely off topic. Please
stop posting here and post to the r-sig-mixed-models list instead.
-- Bert
On Fri, Mar 1, 2013 at 9:33 AM, KAYIS Seyit Ali wrote:
> (Apologise for re-sending. I am re-sending in case subject name did not give
> enough informa
On 01/03/2013 11:20 AM, William Dunlap wrote:
> R shouldn't have trouble with names like that
You will need to enclose the names with backquotes, `odd Name (parens)`, when
using them
in expressions. E.g.,
> d <- data.frame(`P/E`=c(20,25,22), `% Growth`=c(2.4, 2.8, 5.0),
`+-`=c(TRUE,TRUE,F
If you want to receive all the e-mails, but don't want your e-mail program
to pop up a message every time an e-mail from r-help comes in then you can
configure your e-mail client to automatically move all the e-mails from
r-help to a specific folder/label/etc. and that should make it so you can
loo
Try RStudio's "Shiny".
---
Jeff NewmillerThe . . Go Live...
DCN:Basics: ##.#. ##.#. Live Go...
Live: OO#.. Dead: OO#.. Playing
R
+44 1865 272861 (self)
1 South Parks Road, +44 1865 272866 (PA)
Oxford OX1 3TG, UKFax: +44 1865 272595
--
BEGIN-ANTISPAM-VOTING-LINKS
--
Teach CanIt if this mail (ID 02J6h9Lik) is spam:
Spam:
https://www.spamtrap.odu.e
(Apologise for re-sending. I am re-sending in case subject name did not give
enough information. Any shared experience with lme is deeply appreciated)
Dear all,
Â
I have data from the following experimental design and trying to fit a mixed
model with lme function according to following steps b
It is not at all clear what you are doing. You state that the data set you are
using is what I have called dat1 : see dput form below.
As far as I can see there is no numerical value in there.
##===data set in dput form#
dat1 <- structure(list(Name = c("N1", "N1", "N
Hi all:I found some great demonstrations of interactive presentation graphics
generated in R with the SVGAnnotation package,
here:http://www.omegahat.org/SVGAnnotation/http://www.omegahat.org/SVGAnnotation/SVGAnnotationPaper/SVGAnnotationPaper.htmlI
tried to install the package available at tha
On 01/03/2013 15:49, Adams, Jean wrote:
I do not use these functions myself. But, why don't you do a little test
on some paths that you can control. Put the same files in directories with
and without spaces and see if you can get the functions to work.
In the case of RODBC, it never uses file
Sorry:
> sub("[(]","", names(dataFrame)
>
> and
>
> sub("[)]","", names(dataFrame)
>
> Frans
2013/3/1 Frans Marcelissen :
> Try
>
> sub("[(]","", names(dataFrams)
>
> and
>
> sub("[)]","", names(dataFrams)
>
> Frans
>
>
>
>
> 2013/2/28 Jesus Munoz Serrano
>>
>> Dear all
>>
>> I'm having some prob
Try
sub("[(]","", names(dataFrams)
and
sub("[)]","", names(dataFrams)
Frans
2013/2/28 Jesus Munoz Serrano
>
> Dear all
>
> I'm having some problems with a data set that has parenthesis within the
> variable names. A example of this kind of variable names is the following:
>
>
Hello R community,
I am computing weighted average statistic by using ddply function:
My data set is:
N1 T1 S1 I1 C1 FY-4 ROE11 EPS11 MKT11
N1 T1 S1 I1 C1 FY-3 ROE12 EPS12 MKT12
N1 T1 S1 I1 C1 FY-2 ROE13 EPS13 MKT13
N1 T1 S1 I1 C1 FY-1 ROE14 EPS14 MKT14
N1 T1 S1 I1 C1
> R shouldn't have trouble with names like that
You will need to enclose the names with backquotes, `odd Name (parens)`, when
using them
in expressions. E.g.,
> d <- data.frame(`P/E`=c(20,25,22), `% Growth`=c(2.4, 2.8, 5.0),
`+-`=c(TRUE,TRUE,FALSE), check.names=FALSE)
> # In the former you
I do not use these functions myself. But, why don't you do a little test
on some paths that you can control. Put the same files in directories with
and without spaces and see if you can get the functions to work.
Jean
On Thu, Feb 28, 2013 at 2:54 PM, Lane, Michael wrote:
> This seems like a
This definitely looks like a job for Jim Lemon. :)
I am pretty sure that you cannot do it in ggplot2 as there is no way that I am
aware of to have two y-axes except as if y2 is a transformation of y1. For
example, apparently, it is possible to have a Centigrade and Fahrenheit
scale--something t
Sorry I was asking a question inspired by the original question, which relates
to the out of sample prediction.
He was asking why it's not of the probability range, and I also found that
clogit only gives out linear predictors in both estimation and prediction, but
never the probability. For i
ok, found a workaround using 'useOuterStrips':
#Example:
require(lattice)
#require(latticeExtra)
f <- data.frame(a = c(1:40), b = c(1:10, 20:29, 990:999, 20:29),
d = c(rep("A", 20), rep("B", 20)),
e = c(rep("X", 10), rep("Y", 10), rep("X", 10), rep("Y",
10)))
useO
Dear R-users,
I am working on a project that uses S4-classes. At some point I encountered the
problem - well known to R - that I have to pass 3 different objects to a
function, that should modify several slots of them and of course there is no
passing by reference in R.
Then I read this threa
Hi Duncan,
Thanks for your reply.
It is my understanding the whole problem arises from using 'relation =
free'. It looks like xlab.top ignores this and positions the labels as if
'relation = same'.
My example is actually a simplified version of a much more complicated plot.
It creates a 12 by 5
>>> I still don't think the exp(lp)/(1+exp(lp)) gonna work. Since this is
>>> conditional logit model, while this formula is only used in unconditional
>>> ones. By using this, one neglects the information based on stratum. Though
>>> I don't know how to solve it to. I am also working on a proje
On 13-02-28 11:10 AM, Duncan Murdoch wrote:
On 28/02/2013 11:00 AM, Glenn Stauffer wrote:
Ahh, I should have known about the MDI and SDI options - choosing SDI lets
me do what I want. Thanks.
On #2, I realized that when the change directory dialog window pops up, if I
resize it, R remembers the
Hi,
On Fri, Mar 1, 2013 at 6:31 AM, ankita kumari
wrote:
> i dont want to receive messages about all the posts as i get too many in my
> inbox. how can i get emails from everyone who posts in this site.
> please help me out
Maybe you are looking for digest mode? got to
https://stat.ethz.ch/mailm
On 01-03-2013, at 12:31, ankita kumari wrote:
> i dont want to receive messages about all the posts as i get too many in my
> inbox.
You don't want to get the emails?
> how can i get emails from everyone who posts in this site.
You do want the emails?
> please help me out
>
Difficult given
i dont want to receive messages about all the posts as i get too many in my
inbox. how can i get emails from everyone who posts in this site.
please help me out
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://st
Hello,
Inline.
Em 28-02-2013 12:50, Rasmus Hedegaard escreveu:
Hello, The dataset "cats" contain information about the heart weight ("Hwt"), body weight ("Bwt") and gender ("Sex") of a group of 144 cats. I write
the following piece of code: library(MASS)attach(cats)ratio <- Hwt/Bwtmale <-
The build system rolled up R-2.15.3.tar.gz (codename "Security Blanket") at
9:00 this morning. This is intended to be the final round-up release of the
2.15 series, and in fact of the entire 2.x.y series which started 2004-10-04.
The list below details the changes in this release.
You can get t
On 03/01/2013 10:54 AM, Benoit Gendreau-Berthiaume wrote:
Hello I am trying to plot a 20 x 20 grid of points with the colors of each
point refering to percent cover of that specific point
So basically the point are all the same size and their position on the
graph is base on their coordinates (
70 matches
Mail list logo
