Dear community,
I've an rpart object, and I know the CP I want. I'd like to know if it's
possible also to fix the number of terminal nodes I want.
Thanks in advance, u...@host.com as u...@host.com
--
View this message in context:
Dear community,
I've check it while working, but just to reassure myself. Let's say we have
2 models:
model1 - lm(vdep ~ log(v1) + v2 + v3 + I(v4^2) , data = mydata)
model2 - lm(vdep ~ log(v1) + v2 + v3 + v4^2, data = mydata)
So in model1 you really square v4; and in model2, v4*^2
Dear community,
I've a tree which included at first 23 variables. Then I've pruned this
tree, and there are only 8 variables involved.
I'd like to predict and only introduce in newdata the values of these 8
variables involved. However, as the tree was built with the 23, it asked me
for 15
Dear community,
I want to prune a rpart object and select the one that has 13 splits:
object.rpart$cptable
CP nsplit rel errorxerror xstd
1 0.09489173 0 1.000 1.0006465 0.05641905
2 0.05053897 1 0.9051083 0.9234187 0.05427033
.
.
.
10 0.01279452 12
Dear community,
I want to call R from .net. I've been reading this article:
http://www.codeproject.com/Articles/25819/The-R-Statistical-Language-and-C-NET-Foundations.
It says that first I need to download the COM server. When I do this, I see
that the COM server is from 2008;
Dear community,
I want to call R from .net. Precisely I´d really like to call rpart from
.net, plot decision trees and predict with them.
I have installed the COM server
(http://cran.es.r-project.org/contrib/extra/dcom/). Just to note, because it
is from 2008, the only way to work with this
Dear community,
I'm using rpart and would like to extract 95% prediction interval at each
terminal node from a regression tree (built with rpart, method= anova) Is
that possible?
Thanks in advance, u...@host.com as crossp...@host.com
--
View this message in context:
Sorry, but I need the same and i don't understand your help.
So, after fitting my lm model, how can i identify my data? I was trying the
following, but it doesn't work.
/identify(qnorm(c(0.25,
0.75)),quantile(rstandard(mymodel)[!is.na(rstandard(mymodel))], c(0.25,
0.75)),row.names(mydata))
Find the data attached,
http://r.789695.n4.nabble.com/file/n4623493/mydata.txt mydata.txt
The model would be /lmmodel - lm(log(vdep) ~ v1 + sqrt(v2) + v3 +v5 + v6 +
v7 + v8 + v9 + v10, data = mydata)/
Thanks again,
u...@host.com
--
View this message in context:
Dear community,
First of all, apologies, I'm pretty newbie, and maybe have not truly
understood this multiple correspondence analysis.
I have 9 categorial variables with 15, 12,12,7,9,11,8 ,4 , 31 levels
respectively; that is 109 levels.
(*By the way, is there any problem because of having
Dear community,
I'd like to fix a mixed model. I have unbalance data, what should i use:
lme in nlme package , or lmer in lme4.
Thanks, u...@host.com as u...@host.com
--
View this message in context:
http://r.789695.n4.nabble.com/lme-or-lmer-for-unbalance-data-tp4608425.html
Sent from the R
Dear community,
I'm having this silly problem.
I've a linear model. After fixing it, I wanted to know which data had
studentized residuals larger than 3, so i tried this:
d1 - cooks.distance(lmmodel)
r - sqrt(abs(rstandard(lmmodel)))
rstu - abs(rstudent(lmmodel))
a - cbind( mydata, d1,
Dear Community,
I've a Work -Shift Scheduling Problem I'd like to solve via constraint
linear programming.
Maybe something similar to
http://support.sas.com/documentation/cdl/en/orcpug/63349/HTML/default/viewer.htm#orcpug_clp_sect037.htm
Can anybody suggest me any package/R examples to solve
Dear community,
Apologies, I'm still pretty newbie. Anyway, I am performing linar regression
analysis. As a common cause of non-normally distributed residuals is
non-normally predictor variables, i'm interested in achieving the best
transformation of the predictors.
I've seen some commands at
Dear all,
Thanks all of u for your help. Now I've another similar problem. I want to
plot within the same plot, different lines, each one in a different color
depending on the factor level. I've been able to do it like this, but if i
try with rainbow colors it doesn't work. Can anybody help me
Dear community,
I've plotted data and coloured depending on the factor variable v3.
In the legend, I'd like to assign properly the same colors than in the
factor (the factor has 5 levels).
I've been trying this but it doesn't work.
plot(var1, var2, xlab = var1, ylab = var2, col =var3 ,
Dear community,
I'm trying to examine my grouped data following page 6
http://cran.r-project.org/doc/contrib/Fox-Companion/appendix-mixed-models.pdf.
I'm trying lmList this way:
model.list - lmList(log(v.dep) ~ log(v2) +log(v4) + v3 | v5, subset =
v6=0, data=data)
and obtain this error
Dear Community,
I'd like to plot an rq object the same way I do with a lm one, is it
possible? Something like this
plot(rqmodel , 1:4, id.labels=rownames(pga1)); where
rqmodel - rq(log(vd) ~ v1 + log(v2) +log(v3) + v4 + v5 ,data =dat)
Thanks in advance and apologies, I'm pretty newbie with
Dear community,
I'm trying to model growth with this function: Yi = A* exp(-k*(1/ti^m)) ; A
asymptote, k rate of decrease of the relative growth rate, m shape
parameter.
I don't have variable time so, finally, following some papers, I try to fit
Yi+a = A*exp(-k*
Dear community,
I would like to try prp function, I read here:
http://www.milbo.org/rpart-plot/prp.pdf,
but I cannot find in which package is included, can anybody help?
Thanks in advance,
u...@host.com
--
View this message in context:
Thank you,
I guess it didn't work for me, maybe is not possible?
I've tried:
con- odbcDriverConnect(Driver=SQL Server;
Server=...\\...;Database=...;Uid=...;Pwd=... ;)
v1=sqlQuery(con, select v1 from sqltable where v3 =cte and v2 in (select
v2 from R_dataframe) order by (select v2 from
Before loading sql packages, i was wondering, once all packages required are
installed, if it's possible to do from R console sth like this:
SQL select v1 from sql_table
where v2 in (R_variable) # being R_variable a vector
Thanks in advance, u...@host.com
--
View this message in
The thing is that I've already been working with df1, and I was looking for
a function that could replace values knowing rows and columns. Does it
exist?
Thank you, u...@host.com
--
View this message in context:
Dear community,
I'm working with the data.frame attached (
http://r.789695.n4.nabble.com/file/n4122926/df1.xls df1.xls ), let's call it
df1.
I typed: df1- read.xls(C:/... dir .../df1.xls,colNames= TRUE, rowNames=
TRUE)
Then I splited randomly df1 using splitdf function
Dear Community:
Thank you Michael, I did it as you said. However I still have a little
problem with this staff.
I try my lm's in my df1's variables. Let's say: lm1 - lm( df1$vi) ~ df1$v1
+ df1$v2)
Then I usally type: plot(lm1, 1:4)
I'd like to see in the plots obtained the name of the
Dear Community,
I'm having a similar problem. I'm working with the data.frame attached (
http://r.789695.n4.nabble.com/file/n4099139/df1.xls df1.xls ), let's call it
df1 (and when I type str(df1) it answers data.frame)
df1 has its own rownames (In the .xls the column id, not 1,2,3, ...), and
I've manged this way:
df2 - df1[-match(784, row.names(df1)), ]
Isn't there any other way?? How can I retrieve/delete three rows with the
same command line?u...@host.com
--
View this message in context:
Dear Community,
I would like to know if the outliers from the outcome of aq.plot are the
ones with probability associated with D2 is .001.
Thanks in advance, u...@host.com
--
View this message in context:
http://r.789695.n4.nabble.com/aq-plot-outcome-tp4092210p4092210.html
Sent from the R
Dear Community,
I want to identify outliers in my data. I don't know how to use identify
command in the plots obtained.
I've gone through help files and use mahalanobis example for my purpose:
NormalMultivarianteComparefunc - function(x) {
Sx - cov(x)
D2 - mahalanobis(x,
I also have the same problem. Can you send me the link to download a proper
Sun Java application (I have Microsot Windows XP Profesional V.2002)?
Anyway, this is what I tried:
library(JGR)
Loading required package: JavaGD
Loading required package: iplots
Error : .onLoad failed in
Dear all,
First of all apologies, I'm pretty newbie, and secondly I know this is not a
question for the forum but I'd be very grateful if you'd help me.
I had problems with normality assumptions, and I tried with weights in the
linear regression this way:
modelw
Dear community,
I uploaded an excel with read.xls. My xls file actually have a column which
is an id, (plot is the id) :
plot height area
347.6 5.4
853.2 4.1
895.4 8.4
121 6.76.2
...
1325 2.11.5
However R uses another id, this way:
r id plot height area
Dear community,
Thanks for regr2.plot. I've another question.
When fixing OLS I used training data and test data.
I'd like to know if it's possible to draw the plane I've fixed with the
training data, and draw the observed and predicted points achieved with the
test data. If so any help or
Hi, thanks, I think I've changed the previous as you told me but I'm having
this error, what does it mean?
model- lm(log(v1)~log(v2)+v3, data=dat)
newax- expand.grid(
v2 = seq(min(log(dat$v2)), max(log(dat$v2)), length=100),
v3= seq(min(dat$v3), max(dat$v3), length=100))
fit -
Dear community,
As it's explained I've tried the following:
model- lm(log(v1)~log(v2)+v3, data=dat)
newax- expand.grid(
v2 = seq(min(log(dat$v2)), max(log(dat$v2)), length=100),
v3= seq(min(dat$v3), max(dat$v3), length=100)
)
fit - predict(model,newax)
graph -
Dear all,
I want to measure the goodness of prediction of my linear model. That's why
I was thinking about the area under roc curve.
I'm trying the following, but I don't know how to avoid the error. Any help
would be appreciated.
library(ROCR)
model.lm -
Dear all,
I've tried an lm model. I want to check indepence of the residuals, so I was
trying the following:
library(ape)
plot.correlogram(residuals(model1))
I obtain this error:
Error en x$p.values : $ operator is invalid for atomic vectors
Any idea? Thanks in advance, u...@host.com
Dear all,
According to the post I was trying:
factorA = c(2,2,3,3,4,4,3,4,2,2)
levels(factor - c(lv1,lv2,lv3) )
But this returns NULL and doesn't change factor names.
Actually, my factor is included in a data.frame, so I also tried:
levels(df$factorA)[levels(df$factorA)==2] - lv1 Also
Dear all,
According to the post I was trying:
factorA = c(2,2,3,3,4,4,3,4,2,2)
levels(factorA - c(lv1,lv2,lv3) )
But this returns NULL and doesn't change factor names.
Actually, my factor is included in a data.frame, so I also tried:
levels(df$factorA)[levels(df$factorA)==2] - lv1 Also
Dear all,
I've fitted a lm using 61 data (training data), and I'left 10 as test data.
Training data and test data are stored in an excell.
training - read.xls(C:/./training.xls) , the same for test. That is:
v1
v2
...
v15
When I type str(training) and str(test), both sets have the same
Dear all,
I've fitted this model with train data
lms - lm(vd ~ log(v1) + fv2+ fv5+ fv7 )
and predicted over test data using
plms - predict.lm(lmsub, new=test,interval=predict,
level=0.95,se.fit=TRUE)
I've two questions:
q1: what's the difference between writing interval predict or
Dear all,
I want to improve my adj - R sq. I 've chequed some established models and
they introduce two times the same variable, one transformed, and the other
not. It also improves my adj - R sq.
But, isn't this bad for the collinearity? Do I interpret coefficients as
usual?
I rewrite my previous comand, CVlm works now. It was related to having the
same names in the df than in the formula included at CVlm .
Now I'd like to know if the seed is of any special importance, or I can type
just seed=29 like in the example.
Thanks in advance, u...@host.com
--
View this
I rewrite my previous comand, CVlm works now. It was related to having the
same names in the df than in the formula included at CVlm .
Now I'd like to know:
Q1: if the seed is of any special importance, or I can type just seed=29
like in the example?
Q2: I typed:
CVlm(df = mydf, form.lm =
Dear community,
I have fitted a model using comands above, (rlm, lmrob or lmRob). I don't
have new data to validate de models obtained. I was wondering if exists
something similar to CVlm in robust regression. In case there isn't, any
suggestion for validation would be appreciated.
Thanks,
Does it mean that regsubsets doesn't work with categorical variables?
It's because I'm trying the following and I don't know what happens. Any
help would be appreciated.
varin - data.frame(v1,v2,...,v7, factor1,..., factor4)
Dependent variable: height
Then:
eu.subsets - regsubsets(varinc ,
I also have the same problem, can anybody help?
and I would also like to see the p-values associated with the t-value of the
coefficients.
At present I type summary (mod1.rlm) and neither of these things appear.
Thanks, u...@host.com
--
View this message in context:
Yea, sorry, that's what I mean, and v1,...,v5 and factor have the same
length, that's why I don't understand the error
dfmod.1 - data.frame(v1,v2,v3,v4, v5,factor)
CVlm(df= dfmod.1, form.lm = formula(v1 ~ v2+v3+ v4+ v5+ factor), m=3,
seed=29, plotit=TRUE, printit =TRUE)
Error en
Dear community,
Apologies for my questions, I´m pretty newbie.
The thing is, I was trying this lm:
mod.lm - lm(df$res ~ df$var1+ df$var2 + df$var3 +fact1:fact2)
And factors are like this:
table(fact1)
a b c
3 90 83
table(fact2)
a b c
4 87 85
Because of the interaction, i
Thanks for your answer, but I type the following:
dfmod.1 - data.frame(dat$v1,dat$v2,dat$v3,dat$v4, dat$v5,factor)
CVlm(df= dfmod.1, form.lm = formula(dat$v1 ~ dat$v2+dat$v3+ dat$v4+
dat$v5+ factor), m=3, seed=29, plotit=TRUE, printit =TRUE)
Error en `[.data.frame`(df, , ynam) : undefined
But I read in the forum that cv.lm is not for multiple regression, that's
why i change it ti CVlm, however i fell to the same error u...@host.com
--
View this message in context:
http://r.789695.n4.nabble.com/cv-lm-syntax-error-tp3334889p3342333.html
Sent from the R help mailing list
Dear all,
I've tried a multiple regression, and now I want to try a cross-validation.
I obtain this error (it must be sth related to df) that I don't understand,
any help would be appreciated.
cv.lm(df= dat, lm2.52f, m=3)
Error en `[.data.frame`(df, , ynam) : undefined columns selected
Dear community,
I'm doing a lm. In the independent variables I've got a categorical one.
Here is its histogram:
http://r.789695.n4.nabble.com/file/n638/altitude.png
I did this regression:
lmeo2.52f - lm(dat82$IncAltuDom ~ dat82$hdom2+log(dat82$CV)+ dat82$CA+
dat82$FCC+
Dear community,
I was wondering if it's possible to know if you have enough data for a
regression study.
I remember you must have more data than parameters to obtain, but I'd like
to know if there was something more sophisticated.
Thanks, u...@host.com
--
View this message in context:
I want to do a lm regression, some of the variables are going to be affected
with log, I would like not no take into account the values which imply doing
log(0)
for just one variable I have done the following but it doesn't work:
lmod1.lm -
Apologies, I'm really new with R, Can you help me with the syntax?
here is my data.frame in which I introduce independent variables:
varind -
data.frame(datpos$hdom2,datpos$NumPies,datpos$InHart,datpos$CV,datpos$CA,datpos$FCC)
varind has dimensions(194, 6), in case that's necessary. Then I
Apologies, I'm really new with R, Can you help me with the syntax?
here is my data.frame in which I introduce independent variables:
varind -
data.frame(datpos$hdom2,datpos$NumPies,datpos$InHart,datpos$CV,datpos$CA,datpos$FCC)
varind has dimensions(194, 6), in case that's necessary. Then I
Hi, thanks for your post, I tried what you said, and it runs, however when I
type summary ... I obtain the following: What's
happening? How can I solve it?
lmod1.lm -
tryCatch(lm(log(dat$inaltu)~log(dat$indiam),na.action=na.fail),error=function(err){NA})
summary(lmod1.lm,
Hi,
I have tried what you suggest here, and it seems not to work, can you help
me?
I want to do a lm regression, some of the variables are going to be affected
with log, I would like not no take into account those rows which imply doing
log(0)
for just one variable I have done the following
Hello, I am new with R, and I'm trying to fit a linear model, I did the
following and obtein this result, can anybody help? Thanks,
logdftodos7925vi - log(dftodos7925vi)
logALTURA7925- log(dftodos7925$ALTURA7917)
logtodos7925.lm - lm (logALTURA7925~., data= logdftodos7925vi)
Error en
I'm going to work with R and .NET in a few weeks,
I read that I need R version 11 to be able to call R from .NET,
is it true, or is it possible with version 2.12.1?
--
View this message in context:
http://r.789695.n4.nabble.com/Calling-R-from-net-environment-tp880419p3297585.html
Sent
Hi,
i'm using read.xls, and it counts more rows in my Excel than I really have.
i've used both:
especie26 - read.xls(especie26cargar.xls)
datos26 - read.xls(especie26cargar.xls, header = TRUE, as.is = FALSE,
na.strings = NA,
skip = 0, check.names = TRUE, fill = FALSE,
62 matches
Mail list logo