Miguel,
Sin tus datos es imposible brindarte una respuesta precisa pero ten en cuenta
que la descripción del argumento 'fórmula' en la función tree del paquete del
mismo nombre dice que la variable dependiente -PRECIO en tu caso- debe ser un
vector numérico si quieres estimar un árbol de regre
Have a look at the caschrono package.
There's an excellent associated book by the author of the package -Yves Aragon-
but it's in French; if you don't read French, the package documentation is very
clear.
José
-Original Message-
From: R-help [mailto:r-help-boun...@r-project.org] On Beh
Dear Antonello,
How about this? Obviously, you can change the background colours for the
confidence levels (deprespal) and for the regression lines, etc.
Surely, many in the list can improve on my rough and ready solution.
deprespal=c("#CC","#99")
p2 <- ggplot(data = df, aes(x =Levels_De
Dear Erik,
There may be more elegant solutions, but try this:
a. Create a data frame with your data, for example
data <- data.frame(agegrp, y1994, y1995, y1996)
b. Then use the which function:
as.character(aa$agegrp[which(aa$y1994==23)])
Hope it helps,
José
Prof. José Iparraguirre
Chief Ec
Also, the package caschrono is very good for Arima-X.
If you read French, the author, Yves Aragon, wrote an excellent book describing
its use: "Series temporelles avec R" (Springer).
Prof. José Iparraguirre
Chief Economist
Age UK
Age UK
Tavis House, 1- 6 Tavistock Square
London, WC1H 9NB
T 0
g, of
course), R can do it for you as well.
Best,
José
From: Paul Bernal [mailto:paulberna...@gmail.com]
Sent: 11 September 2013 15:41
To: Jose Iparraguirre
Cc: r-help@r-project.org
Subject: Re: [R] Fitting Arima Model to Daily Time Series
Dear Jose, good morning,
First of all, let me thank yo
Hi Eiko,
How about this?
> anova (m1, m2, test="Chisq")
See: ?anova.glm
Regards,
José
Prof. José Iparraguirre
Chief Economist
Age UK
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On
Behalf Of Torvon
Sent: 11 September 2013 16:48
To: r-
Hi Paul,
There are different packages in R to fit an ARIMA model. I would use the
forecast package.
In your case, perhaps you would want to explore SARIMA models to include
seasonal components?
Anyhow, the first port of call could be the auto.arima() function to select the
best fitting represe
Hi Krzysztof,
Have a look at the packages sem, lavaan and psych.
Regards,
José
Prof. José Iparraguirre
Chief Economist
Age UK
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On
Behalf Of fronc...@vizja.pl
Sent: 03 September 2013 13:33
To: r-h
Hi Ma Teresa,
Sorry, but I can't understand what you're trying to achieve.
On a statistical note, I'd tend to think more in terms of medians and would
think hard before replacing any outliers, but that's another matter.
Here I created the dataframe dd with the means column of D in its first colu
As said by arun, the code is not clear.
Ma Teresa, what is it that you actually want to do?
Regards,
José
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On
Behalf Of arun
Sent: 29 August 2013 15:12
To: R help
Subject: Re: [R] Help R
HI,
You
Hi Pablo,
Prof John Fox is a frequent contributor to this forum, and no-one is better
placed than him to respond on your particular point, but I would use the sem
and the polycor packages. There's an example in the documentation of sem which
uses polychoric correlations.
Incidentally you haven'
Hi,
In "Skew-t fits to mortality data - can a Gaussian-related distribution replace
the Gompertz-Makeham as the basis for mortality studies?" (J Gerontol A Biol
Sci Med Sci 2013 August ;68(8):903-913; doi:10.1093/Gerona/gls239) Clark et al
compares the fit of several distributions to mortality
Hola Maria Teresa!
I'd need some data to fully understand your problem, but as far as I can tell
you are overdoing things.
Again, without the data I can't help you but I'd use the ggplot2 package and
forget about splitting the data into vectors and thus creating additional
objects which look re
Hola Maria Teresa,
For multiple imputation, I would suggest the Amelia package by Gary King, James
Honaker, and Matthew Blackwell, which uses the expectation-maximisation (EM)
algorithm with bootstrap. Its excellent vignette has examples which should be
more than enough for your needs. Do read
Dear Ebrahim,
We do not deal with study or work assignments in this group.
I'd suggest, nonetheless, to look into the lme4 package and the mer-class
objects created with this package.
Regards,
José
Prof. José Iparraguirre
Chief Economist
Age UK
-Original Message-
From: r-help-boun...
Have you tried the packages 'survival' and 'eha' yet? You can use the survreg()
function in the former to compare between different models.
Have a look at this tutorial: http://www.openintro.org/stat/surv.php (a copy
can also be found here:
http://anson.ucdavis.edu/~hiwang/teaching/10fall/R_tut
Dear Cheng,
This question exceeds the topics of this group. However, you may benefit from
this recent (and excellent) paper along with the discussions:
Henning, C. and T. Liao (2013). "How to find an appropriate clustering for
mixed-type variables with application to socio-economy stratificatio
Dear Olivier,
Perhaps you're looking for this?
> yourvector[-(1:1000)]
Kind regards,
José
Prof. José Iparraguirre
Chief Economist
Age UK
Age UK
Tavis House, 1- 6 Tavistock Square
London, WC1H 9NB
T 020 303 31482
E jose.iparragui...@ageuk.org.uk
Twitter @jose.iparraguirre@ageuk
-Origin
Humber,
Have a look at this:
http://r.789695.n4.nabble.com/Multiple-Comparisons-Kruskal-Wallis-Test-kruskal-agricolae-and-kruskalmc-pgirmess-don-t-yield-the-sa-td4639004.html
Hope it helps.
Kind regards,
José
Prof. José Iparraguirre
Chief Economist
Age UK
-Original Message-
From: r-he
Hi Mikhail,
After a cursory online search using simply " A new method for non-parametric
multivariate analysis" + CRAN + R, I got the following three packages which
include this paper in their references: vegan, mefa, and TraMineR. I don't know
whether they deal with the procedure you are after
Dear Patty,
I would leave others to point you to the right packages, but I'd suggest you
read this excellent R-based book: "Data Analysis Using Regression and
Multilevel/Hierarchical Models", by Andrew Gelman and Jennifer Hill (Cambridge
University Press, 2006).
Kind regards,
José
Prof. José
Dear all,
I have been experiencing difficulties in running the x12 package. I'm
encountering the following error message which may or may not be R-related:
"CMD.EXE was started with the above path as the current directory.
UNC paths are not supported. Defaulting to Windows directory."
I don't
Dear Elaine,
One of the elements you obtain the P matrix, which is the matrix of asymptotic
p-values. In your case, you get that the asymptotic p-value of the association
between t_i and t_r is 0. That is, there would exist a perfect association
(look also at the first result, the matrix of co
Preetam,
Have a look at this post:
http://stats.stackexchange.com/questions/26999/auto-arima-warns-nans-produced-on-std-error
José
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On
Behalf Of Preetam Pal
Sent: 02 May 2013 12:24
To: r-help@r-pr
Dear Preetam,
I suggest that you read the TSA package documentation (and, if possible, the
book by Cryer and Chan (Time Series Analysis with Applications in R) -it
contains the function arimax which fits ARIMA models with exogenous variables.
One thing: once you run your model, you will get the
Dear Catalin,
I think the package dcemriS4 has this capability.
Hope it helps,
Jose
From: r-help-boun...@r-project.org [r-help-boun...@r-project.org] On Behalf Of
catalin roibu [catalinro...@gmail.com]
Sent: 21 April 2013 20:34
To: r-help@r-project.org
Sub
Dear Claudia,
Your question has been posed on many previous occasions.
The (short) answer has always been the same: have a look at the Anova function
in the car package but before doing that, get a copy of John Fox's "Applied
Regression Analysis and Generalized Linear Models" book.
Best,
José
Endy,
See the package ResourceSelection for the HL test and the package caret for the
sensitivity and specificity measures.
Regards,
Jose Iparraguirre
Chief Economist
Age UK, London
From: r-help-boun...@r-project.org [r-help-boun...@r-project.org] On
Hi Richard,
Have a look at this blog:
http://www.r-bloggers.com/recovering-marginal-effects-and-standard-errors-from-interaction-terms-in-r/
Hope it helps!
José
José Iparraguirre
Chief Economist
Age UK
T 020 303 31482
E jose.iparragui...@ageuk.org.uk
Twitter @jose.iparraguirre@ageuk
Tavis Ho
Beatriz,
In this case, use the car package and run the following:
> bp <- Boxplot(DATA$ave, data= DATA, main= "Average Size", labels=DATA$num,
> Id.method=c("y"))
This will print out the labels 211 & 225 beside the outlier points. As you can
see, the instruction assigns the values in the num c
Estimada Beatriz,
If you use the Box.plot function in the car package (notice that here it's
Box.plot, not box.plot), and add the argument id.method=c("identify"), it
should work.
You only need one instruction:
R> library(car)
R> bp <- Boxplot(DATA$ave, data= DATA, main= "Average
Size",id.meth
Yes, it should be $p.value
Have a look at the components here:
> names(ht)
José
José Iparraguirre
Chief Economist
Age UK
T 020 303 31482
E jose.iparragui...@ageuk.org.uk
Twitter @jose.iparraguirre@ageuk
Tavis House, 1- 6 Tavistock Square
London, WC1H 9NB
www.ageuk.org.uk | ageukblog.org.uk
Rebecca,
Not to contradict Prof. Ripley re the merits and de-merits of the z ratios in
an ARMA setting -far from it-, I'd like to point out that in the package
"cashcrono" you can find the function t_stat() to compute the t-statistics
tests for the coefficients of Arima models.
José
José Ipar
Hi
I'm getting an error message with the roots() function in the vars package.
Even the example in the help file comes up with an error:
> data(Canada)
> var.2c <- VAR(Canada, p = 2, type = "const")
> roots(var.2c)
Error in UseMethod("roots") :
no applicable method for 'roots' applied to an ob
nk ) using an ARIMAX. why
>>>> don't you take his paper and his data and see if you get the same
>>>> estimates using R.
>>>> That's one way if you'll know if you're doing the steps correctly.
>>>> I don't have cryer and cha
Hi Zhengyu
Surely not the most elegant piece of coding, but this should do the trick:
> m=rep(NA,nrow(seq)*ncol(seq))
> mat1=matrix(m,3)
> for(i in 1:nrow(seq)){
+ for(j in 1:ncol(seq)){
+ ifelse((seq[i,j]==1 | seq[i,j]==-1),
+ mat1[i,j]<-mat[i,j],mat1[i,j]<-NA)
+ }
+ }
> mat1
e.g. Wi
Hi
I'm trying to measure the effect of a policy intervention (Box and Tiao, 1975).
This query has to do with the coding of the model rather than with the
particulars of my dataset, so I'm not providing the actual dataset (or a
simulated one) in this case, apart from some general description.
Th
Hi Rosalinde,
If you set the argument err equal to "x", you'll get horizontal error bars.
Hope this helps,
José
José Iparraguirre
Chief Economist
Age UK
T 020 303 31482
E jose.iparragui...@ageuk.org.uk
Twitter @jose.iparraguirre@ageuk
Tavis House, 1- 6 Tavistock Square
London, WC1H 9NB
www.ag
Hi, Derek,
Try and modify the value for the overlap argument.
Hope this helps,
José
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On
Behalf Of derek@nemac
Sent: 07 February 2013 03:49
To: r-help@r-project.org
Subject: [R] coplot question
Hi Tasnuva,
You can read Scrucca, L.; Santucci, A. and Aversa, F. (2007) "Competing risk
analysis using R: an easy guide for clinicians", Bone Marrow Transplantation,
40, 381-387, and also Brock, G.; Barnes, C.; Ramirez, J. and Myers, J. (2011)
"R code for calculating the competing risks estima
Hi Steven,
You are not indexing mA properly within the loop.
In order not to change the elements of the object, I'll create a new vector,
mA2 -not strictly necessary, though.
Let's start with an empty vector:
> mA2 <- rep(0,40)
Now, the loop with the correct indexing:
> for(i in 1:40){
+ if(
Have you looked in the package 'copula'?
Regards,
José
José Iparraguirre
Chief Economist
Age UK
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On
Behalf Of eliza botto
Sent: 31 January 2013 11:13
To: r-help@r-project.org
Subject: [R] lower c
Hi Robin,
You didn't provide the list with a clear structure of your data, but I hope I
understood it properly. If not, it'd be easy for you to adapt what follows.
I guess your data looks like this:
Gene T0h T0.25h T0.5h T1h T2h T3h T6h T12h T24h T48h
1 NM_001001130 68 95
Not sure what you want this for, but work along the following:
> pool = c("s1","s2")
> subpool = c("s1")
> ifelse(pool==subpool,1,0)
[1] 1 0
Notice:
> pool2 = c("s2","s1")
> ifelse(pool2==subpool,1,0)
[1] 0 1
Etc.
Hope this helps.
José
José Iparraguirre
Chief Economist
Age UK
-Origin
Hi Nico,
You can use tapply:
> tapply( x[["Values" ]], x[[ "Names" ]], mean )
CK113234 CK113298 CK114042 CK116292 CK116296
216.5061 190.1725 222.8710 220.4324 204.5741
Alternatively,
> tapply( x$Values, x$Names, mean )
CK113234 CK113298 CK114042 CK116292 CK116296
216.5061 190.1725 222.8710 2
Simply
> colnames(seba)[1] <- "c"
> colnames(seba)[2] <- "b"
Regards,
Jose
From: r-help-boun...@r-project.org [r-help-boun...@r-project.org] On Behalf Of
Sebastian Kruk [residuo.so...@gmail.com]
Sent: 18 January 2013 18:14
To: R-help
Subject: [R] column
Dear Andrea
I may have not understood the question properly, but I guess it has to do with
replacing values before and after casting.
The molten object ('melting') is a data frame, whilst the cast object ('y') is
an array.
Crucially, the values of the variable "Rep" in the 'melting' data f
Hi Ben
I'm not sure whether I understood correctly, but is it something like this?
> sum(ifelse(b==2,1,0))
[1] 4
> sum(ifelse(b==3,1,0))
[1] 4
> sum(ifelse(b>=2,1,0))
[1] 13
> sum(ifelse(b>2,1,0))
[1] 9
Etc...
José
José Iparraguirre
Chief Economist
Age UK
-Original Message-
From: r-h
Don't know, but you can use the function draw.circle in the plotrix package.
Hope this helps,
Jose
From: r-help-boun...@r-project.org [r-help-boun...@r-project.org] On Behalf Of
Ved P. Sharma [vedsha...@gmail.com]
Sent: 12 January 2013 07:43
To: r-help@r-pr
Hi Paolo,
You say you have monthly observations of two variables, say Sales and
Customers.
Then, what you should have is something like this:
Year Month Sales Customer
2012Jan ss_12.1 cc_12.1
2012Feb ss_12.2 cc_12.2
... ... ... ...
2013Jan ss_13.1
Hi Kyong,
Even if it is not -as can be inferred from what you said- a homework or
assignment related query (and the group has clear policy against such
requests), the questions you posed have nontheless very little to do
specifically with R. Instead, they are about statistics. In this respect,
There may be more efficient ways, but here's one:
> x_new <- rep(0,nrow(df))
> x_new <- ifelse(df$T==min(T),0,1)
Regards,
José
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On
Behalf Of Carlos Nasher
Sent: 18 December 2012 14:10
To: r-help@
Try something along these lines:
> library(ggplot2)
> cbPalette <- c("#99", "#E69F00")
> df<-data.frame(y=rnorm(100,30,10),x=rnorm(100,20,5),treat=factor(rbinom(100,1,0.5)))
> p1<-ggplot(df, aes(x=x, y=y,group=treat)) + theme_bw() +
+ geom_smooth(aes(linetype=treat, colour="black"),method
"... A search online has not suggested any solution / work around."
Really?
Have a look at this: http://docs.ggplot2.org/current/geom_smooth.html
Regards,
José Iparraguirre
Chief Economist
Age UK
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org]
default in lm !!).
I just when to be able to recalculate the statistics given in this thesis.
Arnaud
2012/12/13 Jose Iparraguirre
<mailto:jose.iparragui...@ageuk.org.uk>>
Hi Arnaud,
A quick help search of lm or glm tells you that 'the "factory-fresh" default is
na.omit
Hi Arnaud,
A quick help search of lm or glm tells you that 'the "factory-fresh" default is
na.omit'.
If you then look up 'na.omit', you'll read that it 'returns the object with
incomplete cases removed'.
So, pairwise deletion is the default option in both lm and glm.
On a related note, it goes
Hi,
Imagine the data you have is in a data frame, c, with columns a and b.
Then you can do this:
> res=tapply(b,c[,-2],sum)
> res[is.na(res)]<-0
> res
0 1 2 3 4
12 40 64 111 63
Hope it helps,
José
José Iparraguirre
Chief Economist
Age UK
-Original Message-
From: r-hel
If you mean Little's Chi Sq test in particular, go to the BaylorEdPsych package.
Regards,
José
José Iparraguirre
Chief Economist
Age UK
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On
Behalf Of Sileshi Melesse
Sent: 30 November 2012 05:57
T
Hi,
You can use the car package and choose Type-III test.
Also, have a look at the package easyanova.
Regards,
José
José Iparraguirre
Chief Economist
Age UK
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On
Behalf Of humming-bird
Sent: 27 N
Hi,
Imagine the column is named XX.
Type:
> nrow(table(banca_impresa$XX))
and you'll get how many different categories there are in that column.
(If you type
> table(banca_impresa$XX)
you'll get the frequencies).
José
José Iparraguirre
Chief Economist
Age UK
T 020 303 31482
E jose.iparra
Dear AnjaM
There may be better ways of dealing with this, but the following works:
densityplot(~gcsescore | factor(score), groups=gender, data=Chem97,
auto.key=TRUE, plot.points=FALSE, ref=TRUE,
panel=function(x,...){
panel.densityplot(x,...)
Always look at the help page. If you type, in this case, ?scatterplot, you'll
see that all you need to add is the argument smooth=FALSE to omit the loess
line.
Jose
From: r-help-boun...@r-project.org [r-help-boun...@r-project.org] On Behalf Of
nprause [n
Have a look at the package mclust.
Jose
From: r-help-boun...@r-project.org [r-help-boun...@r-project.org] On Behalf Of
Ingmar Visser [i.vis...@uva.nl]
Sent: 15 November 2012 21:10
To: KitKat
Cc: r-help@r-project.org
Subject: Re: [R] cluster analysis in R
D
Hi,
Have a look at this example in plot.zoo:
## Custom x axis labelling using a custom panel.
# 1. test data
z <- zoo(c(21, 34, 33, 41, 39, 38, 37, 28, 33, 40),
as.Date(c("1992-01-10", "1992-01-17", "1992-01-24", "1992-01-31",
"1992-02-07", "1992-02-14", "1992-02-21", "1992-02-28",
Gavin,
Try simply predict()
José
José Iparraguirre
Chief Economist
Age UK
T 020 303 31482
E jose.iparragui...@ageuk.org.uk
Twitter @jose.iparraguirre@ageuk
Tavis House, 1- 6 Tavistock Square
London, WC1H 9NB
www.ageuk.org.uk | ageukblog.org.uk | @ageukcampaigns
For a copy of our new Economic
Hi Werner
I've recently used the net_stacked function here:
http://statisfactions.com/2012/improved-net-stacked-distribution-graphs-via-ggplot2-trickery/
Have a look also at this:
http://stats.stackexchange.com/questions/25109/visualizing-likert-responses-using-r-or-spss
And this:
http://stac
See the 4th example in ?ehplot in the plotrix package:
ehplot(iris$Petal.Length, iris$Species, offset=0.06,
pch=as.numeric(iris$Species))
José
José Iparraguirre
Chief Economist
Age UK
T 020 303 31482
E jose.iparragui...@ageuk.org.uk
Twitter @jose.iparraguirre@ageuk
Tavis House, 1- 6 Tavistock
Thierry's solution is such more elegant and succinct. Loukia, you'd better
forget about the multiplot() function for this...
José
-Original Message-
From: ONKELINX, Thierry [mailto:thierry.onkel...@inbo.be]
Sent: 08 November 2012 16:12
To: Jose Iparraguirre; Loukia Spineli
Hi Loukia,
I think the problem stems from the fact that the filled.contour "uses the
layout function and so is restricted to a full page display" as its
documentation reads. And if you look at the documentation of the layout
function, it says that it is "totally incompatible with the other mech
Hi Johannes,
Just a typo.
You've written
...
contains="rcfpdsuperclass")
When, in fact, you've defined the object rcfdpsuperclass
To highlight the mistake, I'll use capital letters: rcfPD... and rcfDP...
Regards,
José
José Iparraguirre
Chief Economist
Age UK
T 020 303 31482
E jose.ipar
Let's define this object:
> welch <- t.test(x,y,alt="less",var.equal=TRUE)
Then, if you type
> names(welch)
You get its contents:
[1] "statistic" "parameter" "p.value" "conf.int""estimate"
[6] "null.value" "alternative" "method" "data.name"
Now, to obtain the value of eac
Dear Debaranjan,
What's your field of specialisation or study?
Regards,
José
José Iparraguirre
Chief Economist
Age UK
T 020 303 31482
E jose.iparragui...@ageuk.org.uk
Twitter @jose.iparraguirre@ageuk
Tavis House, 1- 6 Tavistock Square
London, WC1H 9NB
www.ageuk.org.uk | ageukblog.org.uk | @ag
Have a look at this:
http://stats.stackexchange.com/questions/15486/plotting-a-boxplot-against-multiple-factors-in-r-with-ggplot2
Hope it helps.
José
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On
Behalf Of dysonsphere
Sent: 30 October 2
Hi Elisa,
Simply create a data frame with the columns you want to use and then run the
amelia() function on that data frame.
Say, you've creasted the data frame MyDF with the 3 columns you want amelia to
perform the imputation. Then type
> a.out <- amelia(MyDFl, m =M)
(where M is the number of
Sounds like a Markov-chain problem.
There are a number of packages that deal with this, including multi-state
Markov models, hidden Markov models, and Bayesian Monte Carlo chains (msm, HHM
and HiddenMarkov, MCMCpack, respectively).
But you won't get much help from us as to which model to use, e
Shortly ago I did something similar to what you intend to.
The data frame was called 'fore'. There were eight different variables and I
wanted to plot each one by column, and depict the frequencies in terms of the
size of the dots. The problem I ran into is that the plots got extremely big
for
You can run dynamic panel data models with plm -see the package's vignette
"Panel Data Econometrics in R: The plm Package" by Yves Croissant and Giovanni
Millo (section 5.4)
Check Giovanni Petris, Sonia Petrone, Patrizia Campagnoli's monograph "Dynamic
Linear Models with R" as well.
Hope this he
And there's a wealth of textbooks on time series based in R. Two to start with:
Paul S.P. Cowpertwait and Andrew V. Metcalfe (2009). Introductory Time Series
with R. Use R! Series. Springer.
Robert H. Shumway and David S. Stoffer (2006). Time Series Analysis and Its
Applications With R Examples
Hi Sachin,
You may find this tutorial useful:
http://goanna.cs.rmit.edu.au/~fscholer/anova.php
And you'll need the car package; but become yourself familiar with Type I, II
and III sums of squares models before running the Anova; the tutorial explains
these in detail.
Hope it helps.
José
Jos
Hi,
You can also have a look at this paper (no subscription needed):
Herberich, E.; Sikorski, J.; and Hothorn, T. (2010). "A Robust Procedure for
Comparing Multiple Means under Heteroscedasticity in Unbalanced Designs".
PLoSONE, Vol. 5, Issue 3, e9788. doi:10.1371/journal.pone.0009788
In this
he answer there.
Best,
Jose
From: jpm miao [miao...@gmail.com]
Sent: 27 September 2012 14:48
To: Jose Iparraguirre
Cc: r-help; kri...@ymail.com
Subject: Re: [R] Is there a function that runs AR model with Schwarz Bayesian
Information Criteria (BIC)?
Thanks. W
You'll find this in the forecast package, function auto.arima()
Regards,
José
José Iparraguirre
Chief Economist
Age UK
T 020 303 31482
E jose.iparragui...@ageuk.org.uk
Twitter @jose.iparraguirre@ageuk
Tavis House, 1- 6 Tavistock Square
London, WC1H 9NB
www.ageuk.org.uk | ageukblog.org.uk | @age
Dear Luigi,
Here's an option:
boxplot(x, boxcol="white", whiskcol="white",medcol="white",staplecol="white")
abline(h=c(-1,0,1))
grid(NA, 4, lwd = 2)
boxplot(x,add=T)
Regards,
José Iparraguirre
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org]
Dear Luigi,
Here's an option:
boxplot(x, boxcol="white", whiskcol="white",medcol="white",staplecol="white")
abline(h=c(-1,0,1))
grid(NA, 4, lwd = 2)
boxplot(x,add=T)
Regards,
José Iparraguirre
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org
Hi Nico,
Far from the most elegant solution, at least it works and will give you plenty
of freedom to choose where to place the labels:
> plot.zoo(x, type="l", main="", xlab="", ylab="",yaxt="n", xaxs="i");
> title(main="Title", xlab="index")
> mtext(names(x)[1],2,line=1,at=0.9)
> mtext(names(
Turgut,
I'm afraid you'll have to write it by yourself.
Dhanoa and Sanderson (Can J Zool, 66:821-823, 2010) mention the FREML Excel
add-in written by Ripley and Thompson (available on the Royal Society of
Chemistry's website at the moment of writing that paper) and that the
simulation and extr
Dear Elvira,
The RandForestGUI estimates the Berger-Parker dominance index.
Regarding the Brillouin Index, I found that someone posted the same question
here earlier this year:
http://tolstoy.newcastle.edu.au/R/e17/help/12/01/1132.html The answers in the
thread may help you.
Regards,
José
J
Dear Conrad,
1) Have you tried the missMDA package? It imputes missing values of a dataset
to perform multiple factor analysis, principal components analysis, etc.
2) The EM algorithm can be used for FA even in the presence of missing values.
Two references in this regard:
a) Jamshidian, M.
Hi Nooshin,
Have you tried the RColorBrewer package?
After loading the package, the following gives you the whole array of available
colour palletes.
> display.brewer.all(n=NULL, type="all", select=NULL, exact.n=TRUE)
Then, you can add to your code something like this (I'm using palette "Set3"
It does!
Thanks,
José
-Original Message-
From: R. Michael Weylandt [mailto:michael.weyla...@gmail.com]
Sent: 04 November 2011 15:18
To: Jose Iparraguirre
Cc: r-help@r-project.org
Subject: Re: [R] How to delete only those rows in a dataframe in which all
records are missing
Perhaps
Hi,
Imagine I have the following data frame:
> a <- c(1,NA,3)
> b <- c(2,NA,NA)
> c <- data.frame(cbind(a,b))
> c
a b
1 1 2
2 NA NA
3 3 NA
I want to delete the second row. If I use na.omit, that would also affect the
third row. I tried to use a loop and an ifelse clause with is.na to get
Does anyone know how to retrieve the residuals after running an ERS unit root
test on a time series (urca package)? There are no 'residuals' or 'res' (or
similar) slots in the ur.ers-class, but a plot instruction - ie
plot(ur.ers()) renders amongst other things a residual plot.
If an augmen
Dear all,
Does anyone know if the PLM package (to run Panel Data Analysis) accepts
quarterly data?
The package vignette and documentation only use annual data -and the only time
index available seems to work for years.
José
Mr José Luis Iparraguirre
Senior Research Economist
Ec
ose
-Original Message-
From: Marc Schwartz [mailto:marc_schwa...@me.com]
Sent: 30 July 2009 20:13
To: Jose Iparraguirre D'Elia
Cc: r-help@r-project.org
Subject: Re: [R] Retrieving original data frame after repetition
On Jul 30, 2009, at 11:15 AM, Jose Iparraguirre D'Elia wrot
Dear R users,
Consider the first two columns of a data frame like this:
> z[,1:2]
x y
1 1 1
2 2 2
3 3 3
4 1 4
Imagine that y represents the times that the value x happens in a population.
But z is not exactly a frequency table, because in z we have x=1 twice. So, the
x=1 in the
Mark, Ted, Gabor,
Thanks for all your input.
José
-Original Message-
From: Gabor Grothendieck [mailto:ggrothendi...@gmail.com]
Sent: 01 April 2009 18:12
To: Jose Iparraguirre D'Elia
Cc: r-help@r-project.org
Subject: Re: [R] A query about na.omit
First input the data frame:
&g
Dear all,
Say I have the following dataset:
> DF
x y z
[1] 1 1 1
[2] 2 2 2
[3] 3 3NA
[4] 4 NA 4
[5] NA 5 5
And I want to omit all the rows which have NA, but only in columns X and Y, so
that I get:
x y z
1 1 1
2 2 2
3 3 NA
I am using the function prop.test (base package), which returns a list with
class "htest". All I want to do is to assign one of its values to a variable,
but I do not want R to print the results and added warning message whenever I
invoke the function.
How can I prevent R from printing on using
Dear Sara,
You could also use the Subbotools package by Giulio Bottazzi and test the
goodness of fit of your data to this distribution.
See:
http://www.lem.sssup.it/WPLem/files/2004-14.pdf
Also, http://cafim.sssup.it/~giulio/software/subbotools/install_cygwin.html
Regards,
José
Mr José Luis
1 - 100 of 104 matches
Mail list logo
