[R] Fwd: ADF test

2013-09-09 Thread Jose Narillos de Santos 
Can anyone help me to see why maximum t-stat quantile has no Negative
values?

¿It is posible lm estimation is not fine?



-- Forwarded message --
From: Jose Narillos de Santos narillosdesan...@gmail.com
Date: 2013/9/8
Subject: ADF test
To: r-help r-help@r-project.org


Hi all,

I try to simulate an ADF test rolling on a window.

The thing is that it seems I´m doing well...applying to al AR(1) model with
unit root.

I see in some econometrical papers that the t-stat maximum and minimum
should have negative values on the quantiles 0,01 to 0,03
 and in my case only the minimum are negative values.

¿It is posible I´m doing wrong calculus on lm?

I m getting mad


Ob - 100
Re - 50


H2-matrix(0,Ob,Re)

 for (j in 1:Re){

for (i in 2:Ob){


H2[i, j] -1+ 1*H2[i-1, j]+rnorm(1)

}
}

H3-matrix(0,Ob,Re)


for (i in 2:Ob){
for (j in 1:Re){

H3[i,j]-H2[i,j]-H2[i-1,j]

}}

a3-H3[2:nrow(H3),1:ncol(H3)]
a2-H2[1:(nrow(H2)-1),1:ncol(H2)]

write.csv(a3,a3.csv)
write.csv(a2,a2.csv)

a3-read.csv(a3.csv)
a2-read.csv(a2.csv)

delta-round(Ob*(1/3))

fg-matrix(0,nrow(H3)-delta+1,Re)
  for (j in 1:Re){

for (i in delta:nrow(H3) ){



z2-(i-delta+1)
z3-i

fg[i-delta+1,j]-coef(summary(lm(a3[z2:z3,j+1]~(1+a2[z2:z3,j+1])  )
))[2,t value]
print(j)

  }
}

MaxrollingT-apply(fg, 1, max)
MinrollingT-apply(fg, 1, min)
Diffrolling-MaxrollingT-MinrollingT


Meanrolling-apply(fg, 1, mean)

write.csv(MaxrollingT, file = MaxrollingT.csv)
write.csv(MinrollingT, file = MinrollingT.csv)
write.csv(Diffrolling, file = DiffrollingT.csv)
write.csv(Meanrolling, file = Meanrolling.csv)


print(c(quantile(MaxrollingT,0.01),quantile(MinrollingT,0.01)))
print(c(quantile(MaxrollingT,0.015),quantile(MinrollingT,0.015)))
print(c(quantile(MaxrollingT,0.02),quantile(MinrollingT,0.02)))
print(c(quantile(MaxrollingT,0.025),quantile(MinrollingT,0.025)))

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] ADF test

2013-09-08 Thread Jose Narillos de Santos 
Hi all,

I try to simulate an ADF test rolling on a window.

The thing is that it seems I´m doing well...applying to al AR(1) model with
unit root.

I see in some econometrical papers that the t-stat maximum and minimum
should have negative values on the quantiles 0,01 to 0,03
 and in my case only the minimum are negative values.

¿It is posible I´m doing wrong calculus on lm?

I m getting mad


Ob - 100
Re - 50


H2-matrix(0,Ob,Re)

 for (j in 1:Re){

for (i in 2:Ob){


H2[i, j] -1+ 1*H2[i-1, j]+rnorm(1)

}
}

H3-matrix(0,Ob,Re)


for (i in 2:Ob){
for (j in 1:Re){

H3[i,j]-H2[i,j]-H2[i-1,j]

}}

a3-H3[2:nrow(H3),1:ncol(H3)]
a2-H2[1:(nrow(H2)-1),1:ncol(H2)]

write.csv(a3,a3.csv)
write.csv(a2,a2.csv)

a3-read.csv(a3.csv)
a2-read.csv(a2.csv)

delta-round(Ob*(1/3))

fg-matrix(0,nrow(H3)-delta+1,Re)
  for (j in 1:Re){

for (i in delta:nrow(H3) ){



z2-(i-delta+1)
z3-i

fg[i-delta+1,j]-coef(summary(lm(a3[z2:z3,j+1]~(1+a2[z2:z3,j+1])  )
))[2,t value]
print(j)

  }
}

MaxrollingT-apply(fg, 1, max)
MinrollingT-apply(fg, 1, min)
Diffrolling-MaxrollingT-MinrollingT


Meanrolling-apply(fg, 1, mean)

write.csv(MaxrollingT, file = MaxrollingT.csv)
write.csv(MinrollingT, file = MinrollingT.csv)
write.csv(Diffrolling, file = DiffrollingT.csv)
write.csv(Meanrolling, file = Meanrolling.csv)


print(c(quantile(MaxrollingT,0.01),quantile(MinrollingT,0.01)))
print(c(quantile(MaxrollingT,0.015),quantile(MinrollingT,0.015)))
print(c(quantile(MaxrollingT,0.02),quantile(MinrollingT,0.02)))
print(c(quantile(MaxrollingT,0.025),quantile(MinrollingT,0.025)))

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] Pie chart

2013-05-24 Thread Jose Narillos de Santos 
I have a 8 Groups composed by A,B, c, D components. The Group 9 is composed
by the 8 Groups but only components A and C.


I want to chart a plot with 1 big plot of the total Groups (from 1 to 8) on
the right and 8 mini pies on the left composed by the 4 components (the
size of each pie of group should be bigger or smaller depending on the
total).

The same structure but below this plot I want to put on the left the plot
of Group 9 composed by Component A and C and on the left 8 pies composed by
Component B and C on Each Group.

I don´t know if it is posible.


And If I have explain well...





components Component A Component B Component C Component D
Group 1 1100 1000 100 0 0
Group 2 728 380 38 10 300
Group 3 320 200 20 50 50
Group 4 110 80 8 20 2
Group 5 75 40 4 5 26
Group 6 38 30 3 2 3
Group 7 16 10 1 0 5
Group 8 10,5 5 0,5 4 1
Total 2397,5 1745 174,5 91 387
Group 9 1836 1745 0 91 0

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] Plot smooth

2013-05-04 Thread Jose Narillos de Santos 
Hi I have this data and I want to draw a plot of a line BUR the thing is I
want that this line appear smooth ¿someone knows if there is an special
function?


Thanks in advance.
  Vertice 02/05/2013  1w 0,083  2w 0,092  3w 0,1  1m 0,113  2m 0,159  3m
0,201  4m 0,236  5m 0,272  6m 0,302  7m 0,333  8m 0,363  9m 0,398  10m 0,428
11m 0,463  12m 0,493

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] Size of label axis

2013-05-04 Thread Jose Narillos de Santos 
Hi all,

I want to know if the is a possibility to increase the size of the default
numbers that appears on axis on a plot, I don´t mean a labbel I mean the
number on axis and yaxis.

You see when in excel you select a plot and select all and increase the
font letters or mark bold all the graph parametrization increases at the
same time

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] expression

2013-04-01 Thread Jose Narillos de Santos 
Hi all,

I´m using


titt- expression(paste(R con ventanas de 200 , italic(datos)))

And it works properly on a plot(...,main=titt,..)

But if I want to add an improvement to avoid typing n on the plot so that

n-200

titt- expression(paste(R con ventanas de ,n,  italic(datos)))

It doesn´t recognize that n is a variable and adds n letter instead of
200 on the plot when run:

plot(...,main=titt,..)

How can I include n in the plot authomatically without loosing the italic
letter?

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Cor color

2013-03-01 Thread Jose Narillos de Santos 
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 narillosdesan...@gmail.com

 Hi all,

 I want to plot moving correlation and to complete color on the correlation
 line and 0 line but it appears an image as attached.

 I attach code to see if someone can help.

 plot(cf,type=l,col=black, xlab=Time, ylab=Correlation,axes=F)

 grid()

 polygon(c(1, 1:st,st),c(0, cf, 0), col = blue)

 abline(h = 0, lwd = 2, col = black)

 title(Dinamic Correlation,font=4)

 par(new=T)

 variable-matrix(0,nrow(bBT),1)

 plot(tfr1,variable,type=l,ylab=,col=black,xlab= )

 mtext(Correlation,side=4,line=2,col=4)




[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] ommoting rows

2012-09-18 Thread Jose Narillos de Santos 
Hi I have an output data Data.csv

this style:

 ,V1,V2,V3  1,-9552,9552,C  2,0,9653,0
3,9614,9614,V  4,0,9527,0  5,-9752,9752,C
6,0,9883,0  7,0,9865,0
I want to create a new matrix ommintg all the rows where third column has
0.

There is a way to do it easyly?

Many thanks in advance.

My final matrix will have:

,V1,V2,V31,-9552,9552,C
3,9614,9614,V5,-9752,9752,C

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

Re: [R] ommoting rows

2012-09-18 Thread Jose Narillos de Santos 
Many ThanKs,

The subsecction on R is very clarifying.

Sorry yesterday I was a little confused

Many thanks.

2012/9/18 Ben Tupper btup...@bigelow.org

 Hi,

 On Sep 18, 2012, at 3:25 PM, Bert Gunter wrote:

  Please read An Introduction to R (or other R tutorial) to learn about
  indexing in R.
 
  ?[ or ?subset also will tell you how to do it, but they are rather
 terse.
 


 That's a great start, but it might be helpful to provide a bit more
 specificity when directing a newcomer like Jose to the Introduction to R.
  Perhaps by providing a link to the relevant sections like this...

 Here are nice descriptions of four different ways to index a vector:

 http://cran.r-project.org/doc/manuals/R-intro.html#Index-vectors

 These kinds of indexing techniques can be applied to each dimension of an
 array-like object such as your example.  You can see in David Winsemius'
 nice example that he applied the logical type of indexing to the rows of
 your data.

 Cheers,
 Ben




  -- Bert
 
  On Tue, Sep 18, 2012 at 12:08 PM, Jose Narillos de Santos
  narillosdesan...@gmail.com wrote:
  Hi I have an output data Data.csv
 
  this style:
 
  ,V1,V2,V3  1,-9552,9552,C  2,0,9653,0
  3,9614,9614,V  4,0,9527,0  5,-9752,9752,C
  6,0,9883,0  7,0,9865,0
  I want to create a new matrix ommintg all the rows where third column
 has
  0.
 
  There is a way to do it easyly?
 
  Many thanks in advance.
 
  My final matrix will have:
 
  ,V1,V2,V31,-9552,9552,C
  3,9614,9614,V5,-9752,9752,C
 
 [[alternative HTML version deleted]]
 
  __
  R-help@r-project.org mailing list
  https://stat.ethz.ch/mailman/listinfo/r-help
  PLEASE do read the posting guide
 http://www.R-project.org/posting-guide.html
  and provide commented, minimal, self-contained, reproducible code.
 
 
 
  --
 
  Bert Gunter
  Genentech Nonclinical Biostatistics
 
  Internal Contact Info:
  Phone: 467-7374
  Website:
 
 http://pharmadevelopment.roche.com/index/pdb/pdb-functional-groups/pdb-biostatistics/pdb-ncb-home.htm
 
  __
  R-help@r-project.org mailing list
  https://stat.ethz.ch/mailman/listinfo/r-help
  PLEASE do read the posting guide
 http://www.R-project.org/posting-guide.html
  and provide commented, minimal, self-contained, reproducible code.

 Ben Tupper
 Bigelow Laboratory for Ocean Sciences
 180 McKown Point Rd. P.O. Box 475
 West Boothbay Harbor, Maine   04575-0475
 http://www.bigelow.org









[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] Polygon shaded area

2012-08-02 Thread Jose Narillos de Santos 
Hi all,

I have two vectors (columns) called efinal and efinal 2.

I want to plot them on the same plot and draw a shaded area beween the
two lines using function polygon

I have tried all but I don ´t understand the polygon area, can you help me
with examples?

plot(efinal,type=l,ylim=range(min(efinal2),
max(efinal)),ylab=,main=plot)

par(new=T)
plot(efinal2,type=l,ylim=range(min(efinal2), max(efinal)),ylab=)

The efinal are two temporal series I attach?
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Polygon shaded area

2012-08-02 Thread Jose Narillos de Santos 
Hi I attach my function. No error message (it seems a line appears but
nothing similar to examples(polygon))



2012/8/2 Eik Vettorazzi e.vettora...@uke.de

 Hi Jose,
 how about this

 example(polygon)

 I think the second one is pretty much what you want.

 cheers.

 Am 02.08.2012 14:33, schrieb Jose Narillos de Santos:
  Hi all,
 
  I have two vectors (columns) called efinal and efinal 2.
 
  I want to plot them on the same plot and draw a shaded area beween the
  two lines using function polygon
 
  I have tried all but I don ´t understand the polygon area, can you help
 me
  with examples?
 
  plot(efinal,type=l,ylim=range(min(efinal2),
  max(efinal)),ylab=,main=plot)
 
  par(new=T)
  plot(efinal2,type=l,ylim=range(min(efinal2), max(efinal)),ylab=)
 
  The efinal are two temporal series I attach?
 
 
 
  __
  R-help@r-project.org mailing list
  https://stat.ethz.ch/mailman/listinfo/r-help
  PLEASE do read the posting guide
 http://www.R-project.org/posting-guide.html
  and provide commented, minimal, self-contained, reproducible code.
 


 --
 Eik Vettorazzi

 Department of Medical Biometry and Epidemiology
 University Medical Center Hamburg-Eppendorf

 Martinistr. 52
 20246 Hamburg

 T ++49/40/7410-58243
 F ++49/40/7410-57790

 --
 Pflichtangaben gemäß Gesetz über elektronische Handelsregister und
 Genossenschaftsregister sowie das Unternehmensregister (EHUG):

 Universitätsklinikum Hamburg-Eppendorf; Körperschaft des öffentlichen
 Rechts; Gerichtsstand: Hamburg

 Vorstandsmitglieder: Prof. Dr. Guido Sauter (Vertreter des Vorsitzenden),
 Dr. Alexander Kirstein, Joachim Prölß, Prof. Dr. Dr. Uwe Koch-Gromus


__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Polygon shaded area

2012-08-02 Thread Jose Narillos de Santos 
Hi many thanks,

That is my data.


 dput(efinal)c(0.9525, 0.89785, 0.8931, 0.9308, 0.89335, 0.8729, 0.8521, 
 0.8556,
0.88135, 0.9093, 0.89375, 0.91155, 0.8881, 0.86655, 0.8927, 0.8898,
0.8703, 0.84863, 0.81745, 0.8349, 0.8248, 0.85995, 0.8686, 0.83765,
0.86075, 0.8609, 0.8528, 0.8837, 0.8917, 0.8671, 0.87205, 0.90255,
0.87485, 0.8856, 0.86665, 0.8731, 0.8558, 0.8353, 0.8557130916294,
0.861971323468187, 0.865900731747475, 0.868624652247, 0.870578199623624,
0.871984527163596, 0.872976198154798, 0.873639584912775, 0.8740346818528,
0.87420517054346, 0.874184027040643, 0.873996870459551)
dput(efinal2)c(0.9525, 0.89785, 0.8931, 0.9308, 0.89335, 0.8729,
0.8521, 0.8556,
0.88135, 0.9093, 0.89375, 0.91155, 0.8881, 0.86655, 0.8927, 0.8898,
0.8703, 0.84863, 0.81745, 0.8349, 0.8248, 0.85995, 0.8686, 0.83765,
0.86075, 0.8609, 0.8528, 0.8837, 0.8917, 0.8671, 0.87205, 0.90255,
0.87485, 0.8856, 0.86665, 0.8731, 0.8558, 0.8353, 0.8073853773588,
0.793625614508213, 0.782194675217125, 0.771969223705801, 0.762514145317377,
0.753606286765605, 0.745113084762604, 0.736948166992827, 0.729051539041001,
0.721379519338542, 0.713899131829559, 0.706584757398851)



2012/8/2 John Kane jrkrid...@inbox.com

  The efinal are two temporal series I attach?

 Not attached.  R-help typically strips out any attachment to prevent
 malware being spread.

 The best way to supply sample date is to use the dput() command.  See
 ?dput for details but basically just say dput(myfile) and copy the results
 into your email.  Readers can directly paste the file into their R console
 and see exactly what your data is.

 John Kane
 Kingston ON Canada

 
 FREE ONLINE PHOTOSHARING - Share your photos online with your friends and
 family!
 Visit http://www.inbox.com/photosharing to find out more!




[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Polygon shaded area

2012-08-02 Thread Jose Narillos de Santos 
Many thanks Eik it works properly.

what I don´t know exactly is why you put
c(xv,rev(xv)),c(efinal,rev(efinal2)),col=red inside polygon. I see it
works but for the moment I don´t really see the meaning of c() and why is
needed to put twice and so on.

If I had a vector of dates associated with each row (imagine t.csv)

t-read.csv(t.csv)

tp-as.Date(t[,2], format=%d/%m/%Y)

I see that if I put

plot(efinal, tp. ylim=range(c(efinal,efinal2)),type=n,ylab=)
xv-seq_along(efinal)
polygon(c(xv,rev(xv)),c(efinal,rev(efinal2)),col=red)


It doesn´t work.

I can use xaxt=n but it will be ok to put associated date on x axis.

Sorry in advance if I only ask but it is difficoult to me, anyway many
thanks and I will keep on trying. Many people (with some original reason)
get ennoyed for some silly questions, so I send many thanks for read me and
try to help me.

Many, many thanks.

2012/8/2 Eik Vettorazzi e.vettora...@uke.de

 Hi Jose,
 this should work (but I think you need a deeper understanding, what
 plot(efinal) does, see ?plot):

 plot(efinal,ylim=range(c(efinal,efinal2)),type=n,ylab=)
 xv-seq_along(efinal)
 polygon(c(xv,rev(xv)),c(efinal,rev(efinal2)),col=red)

 cheers

 Am 02.08.2012 16:36, schrieb Jose Narillos de Santos:
  Hi I attach my function. No error message (it seems a line appears but
  nothing similar to examples(polygon))
 
 
 
  2012/8/2 Eik Vettorazzi e.vettora...@uke.de mailto:e.vettora...@uke.de
 
 
  Hi Jose,
  how about this
 
  example(polygon)
 
  I think the second one is pretty much what you want.
 
  cheers.
 
  Am 02.08.2012 14:33, schrieb Jose Narillos de Santos:
   Hi all,
  
   I have two vectors (columns) called efinal and efinal 2.
  
   I want to plot them on the same plot and draw a shaded area
  beween the
   two lines using function polygon
  
   I have tried all but I don ´t understand the polygon area, can you
  help me
   with examples?
  
   plot(efinal,type=l,ylim=range(min(efinal2),
   max(efinal)),ylab=,main=plot)
  
   par(new=T)
   plot(efinal2,type=l,ylim=range(min(efinal2),
 max(efinal)),ylab=)
  
   The efinal are two temporal series I attach?
  
  
  
   __
   R-help@r-project.org mailto:R-help@r-project.org mailing list
   https://stat.ethz.ch/mailman/listinfo/r-help
   PLEASE do read the posting guide
  http://www.R-project.org/posting-guide.html
   and provide commented, minimal, self-contained, reproducible code.
  
 
 
  --
  Eik Vettorazzi
 
  Department of Medical Biometry and Epidemiology
  University Medical Center Hamburg-Eppendorf
 
  Martinistr. 52
  20246 Hamburg
 
  T ++49/40/7410-58243 tel:%2B%2B49%2F40%2F7410-58243
  F ++49/40/7410-57790 tel:%2B%2B49%2F40%2F7410-57790
 
  --
  Pflichtangaben gemäß Gesetz über elektronische Handelsregister und
  Genossenschaftsregister sowie das Unternehmensregister (EHUG):
 
  Universitätsklinikum Hamburg-Eppendorf; Körperschaft des
  öffentlichen Rechts; Gerichtsstand: Hamburg
 
  Vorstandsmitglieder: Prof. Dr. Guido Sauter (Vertreter des
  Vorsitzenden), Dr. Alexander Kirstein, Joachim Prölß, Prof. Dr. Dr.
  Uwe Koch-Gromus
 
 


 --
 Eik Vettorazzi

 Department of Medical Biometry and Epidemiology
 University Medical Center Hamburg-Eppendorf

 Martinistr. 52
 20246 Hamburg

 T ++49/40/7410-58243
 F ++49/40/7410-57790

 --
 Pflichtangaben gemäß Gesetz über elektronische Handelsregister und
 Genossenschaftsregister sowie das Unternehmensregister (EHUG):

 Universitätsklinikum Hamburg-Eppendorf; Körperschaft des öffentlichen
 Rechts; Gerichtsstand: Hamburg

 Vorstandsmitglieder: Prof. Dr. Guido Sauter (Vertreter des Vorsitzenden),
 Dr. Alexander Kirstein, Joachim Prölß, Prof. Dr. Dr. Uwe Koch-Gromus



[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Fwd: Re: Graph color

2010-02-01 Thread Jose Narillos de Santos 
Hi Greg,

Many thanks¡¡¡

For the moment, as Jim suggested thigmophobe.labels in the plotrix package
worked properly¡¡¡

Many thanks¡¡¡



2010/2/1 Greg Snow greg.s...@imail.org

 What you are asking (making labels of points not overlap the points) is
 either very simple or very complicated, depending on your data and what you
 want the results to look like.

 It may be as simple as text(x, y-strheight('A'), labels).

 If that does not do what you want, then there is thigmophobe.labels in the
 plotrix package (already mentioned by Jim Lemon) which works great for some
 datasets.  Also spread.labels (plotrix package) and spread.labs
 (TeachingDemos package) work in different situations.  There may be some
 other automated attempts in other packages, but they are not coming to mind.
  A less automatic approach that gives you more control is the
 dynIdentify/TkIdentify functions (TeachingDemos package).

 If you want rectangles around the labels, then you may want the
 boxed.labels function (plotrix).  If you want to do your own rectangles then
 there are the rect and symbols functions.

 Hope this helps,

 --
 Gregory (Greg) L. Snow Ph.D.
 Statistical Data Center
 Intermountain Healthcare
 greg.s...@imail.org
 801.408.8111


  -Original Message-
  From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-
  project.org] On Behalf Of Jose Narillos de Santos
  Sent: Friday, January 29, 2010 4:30 PM
  To: Jim Lemon; r-help@r-project.org; baptiste auguie
  Subject: Re: [R] Fwd: Re: Graph color
 
   Hi Jim,
 
  Last question.
 
  I´m using a spanish version (there are some documents on how
  constructing
  good plots and I have found them althought not very intuitive...) I
  will
  read them in a next days.
 
  Only if you know the way.
 
  Imagine I have made a plot like plot(x,y)
 
  and I use labels (on each cross point appears a name) but they appear
  on the
  dot ¿Do you know some way to show the label below the dot? there is
  some way
  to indicate the program try to not to overlap labels (if they are very
  near?)
 
  Happy nice wekend all¡¡¡
 
  2010/1/29 Jim Lemon j...@bitwrit.com.au
 
   On 01/29/2010 10:08 AM, Jose Narillos de Santos wrote:
  
   Hi Jim your suggestion doesn´t work properly. I have find some
  documents
   on graphs so let me think till monday and if not I will detail where
  it
   fails.
   Sorry again...I feel very silly, really, it is not a joke but I will
   continue trying...
   I have a question also, in a general plot (please if you can help me
  it
   would be fantastic)
   Imagine again a plot
  
 x - rnorm(10)
  
 y - rnorm(10)
  
   If I plot(x,y)
  
   it appears a scatter plot.
  
   If you see y axis (the y axis on the left) has numbers. But the
  parallel
   (imaginary)  y axis on the right appears only as a line (without the
   numbers, the scale).
  
   Do you know how to show the scale the same numbers in both (left and
   right axis)? I think this way the graphs seem more simetrical.
  
   Hi Jose,
   Try this:
  
   par(mar=c(5,4,4,4))
   plot(rnorm(10),rnorm(10))
   axis(4)
  
   Jim
  
  
 
[[alternative HTML version deleted]]



[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Fwd: Re: Graph color

2010-01-30 Thread Jose Narillos de Santos 
Many thanks I will try to check it latter¡¡¡

One more think...

To add a box on a plot (and locate where you want (I think you will say
floating)) you know the function? Not a Lengend but something similar but
writting what you want inside to indicate wat you want.

2010/1/30 Jim Lemon j...@bitwrit.com.au

 On 01/30/2010 10:29 AM, Jose Narillos de Santos wrote:

 Hi Jim,
 Last question.
 I惴 using a spanish version (there are some documents on how

 constructing good plots and I have found them althought not very
 intuitive...) I will read them in a next days.
 Only if you know the way.
 Imagine I have made a plot like plot(x,y)
 and I use labels (on each cross point appears a name) but they appear on
 the dot æ¾³o you know some way to show the label below the dot? there is

 some way to indicate the program try to not to overlap labels (if they
 are very near?)

 Hi Jose,
 In fact, I can point you to the thigmophobe.labels function in the plotrix
 package, which attempts to avoid collisions between labels in just that
 manner.

 Jim



[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Fwd: Re: Graph color

2010-01-29 Thread Jose Narillos de Santos 
Hi Jim,

Last question.

I´m using a spanish version (there are some documents on how constructing
good plots and I have found them althought not very intuitive...) I will
read them in a next days.

Only if you know the way.

Imagine I have made a plot like plot(x,y)

and I use labels (on each cross point appears a name) but they appear on the
dot ¿Do you know some way to show the label below the dot? there is some way
to indicate the program try to not to overlap labels (if they are very
near?)

Happy nice wekend all¡¡¡

2010/1/29 Jim Lemon j...@bitwrit.com.au

 On 01/29/2010 10:08 AM, Jose Narillos de Santos wrote:

 Hi Jim your suggestion doesn´t work properly. I have find some documents
 on graphs so let me think till monday and if not I will detail where it
 fails.
 Sorry again...I feel very silly, really, it is not a joke but I will
 continue trying...
 I have a question also, in a general plot (please if you can help me it
 would be fantastic)
 Imagine again a plot

   x - rnorm(10)

   y - rnorm(10)

 If I plot(x,y)

 it appears a scatter plot.

 If you see y axis (the y axis on the left) has numbers. But the parallel
 (imaginary)  y axis on the right appears only as a line (without the
 numbers, the scale).

 Do you know how to show the scale the same numbers in both (left and
 right axis)? I think this way the graphs seem more simetrical.

 Hi Jose,
 Try this:

 par(mar=c(5,4,4,4))
 plot(rnorm(10),rnorm(10))
 axis(4)

 Jim



[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Fwd: Re: Graph color

2010-01-28 Thread Jose Narillos de Santos 
Hi Jim your suggestion doesn´t work properly. I have find some documents on
graphs so let me think till monday and if not I will detail where it fails.

Sorry again...I feel very silly, really, it is not a joke but I will
continue trying...

I have a question also, in a general plot (please if you can help me it
would be fantastic)

Imagine again a plot


 x - rnorm(10)

 y - rnorm(10)



If I plot(x,y)



it appears a scatter plot.

If you see y axis (the y axis on the left) has numbers. But the parallel
(imaginary)  y axis on the right appears only as a line (without the
numbers, the scale).

Do you know how to show the scale the same numbers in both (left and right
axis)? I think this way the graphs seem more simetrical.

Many thanks in advance.


2010/1/28 Jim Lemon j...@bitwrit.com.au

  On 01/28/2010 09:52 AM, Jose Narillos de Santos wrote:

 Finally I´m very near on the graph I want...
 The code is this (based on your guide):
 First I read this data on the M.txt file:
 Player  TYr Dec
 Jose20  14
 Pepe12  16
 Andres  15  12
 Guille  16  14
 Pedro   18  19
 Luis14  19
 Raul18  15
 Pepe7   5

 MC-read.table(MC.txt,header=T,sep=,dec=,)
 #I read the data
 attach(MC)

 par(bg=black)

 plot(x = MC$TYr, y = MC$Dec, xlab=Actual Goals,
 ylab=Last year Goals,col=white,col.axis=white)
 title(Goals on Game,font=4,col=white)
 lim-par(usr)
 rect(lim[1],lim[3],lim[2],lim[4],col=white,border=white)
 text(x = MC$TYr, y = MC$Dec, labels = MC$Player)
 grid()

 abline(1,1)

 WHAT IS MY PROBLEM?
 The main title and the axis names doesn´t appear I want to put them on
 white but the script doesn´t run. Can any one guide me?
 The other problem is that the border of the x and y axis doesn´t
 appears...

 Hi Jose,
 I think this will be close to what you want. The black outer background and
 the white inner background obscure almost everything, and so you may have to
 specify nearly everything in the plot, or keep changing par(fg) and par(bg)
 as you add bits.

 plot(x = MC$TYr, y = MC$Dec)

 lim-par(usr)
 rect(lim[1],lim[3],lim[2],lim[4],col=white,border=white)
 points(x = MC$TYr, y = MC$Dec,col=black)
 axis(1,col=white)
 mtext(Last year Goals,side=2,line=2,col=white)
 mtext(Actual Goals,side=1,line=2,col=white)
 mtext(seq(8,20,by=2),at=seq(8,20,by=2),side=1,line=1,col=white)
 axis(2,col=white)
 mtext(seq(6,18,by=2),at=seq(6,18,by=2),side=2,line=1,col=white)
 mtext(Goals on game,at=14,line=2,cex=1.5,col=white)
 grid()
 abline(1,1,col=black)
 box(col=white)

 Jim


[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Fwd: Re: Graph color

2010-01-27 Thread Jose Narillos de Santos 
Finally I´m very near on the graph I want...

The code is this (based on your guide):

First I read this data on the M.txt file:

Player TYr Dec Jose 20 14 Pepe 12 16 Andres 15 12 Guille 16 14 Pedro 18
19 Luis 14 19 Raul 18 15 Pepe 7 5

MC-read.table(MC.txt,header=T,sep=,dec=,)

#I read the data
attach(MC)

par(bg=black)

plot(x = MC$TYr, y = MC$Dec, xlab=Actual Goals,
ylab=Last year Goals,col=white,col.axis=white)
title(Goals on Game,font=4,col=white)

lim-par(usr)
rect(lim[1],lim[3],lim[2],lim[4],col=white,border=white)

text(x = MC$TYr, y = MC$Dec, labels = MC$Player)

grid()

abline(1,1)

WHAT IS MY PROBLEM?

The main title and the axis names doesn´t appear I want to put them on white
but the script doesn´t run. Can any one guide me?

The other problem is that the border of the x and y axis doesn´t appears...

Sorry about my silly questions...

2010/1/27 Jim Lemon j...@bitwrit.com.au

 On 01/27/2010 06:41 AM, narillosdesan...@gmail.com wrote:

 No mate,

 Sorry first of all about my indefinition (I´m Spanish, I´m improving
 everyday but a long road to the perfection). Sorry pleae.

 Second, also it is diffcoult sometimes to express what we try (sorry and
 many thanks just for reading of course for helping).

 Imagine you plot

 X=[2 4 6 8] front a Y=[6 5 8 7]

 When you plot it by default all is white what I want is to use
 par(br=gray) to make the graph gray but I want that the area (the
 imaginary square defined by the axis) not to be gray I want to deffine its
 colour by ie lightblue.


 So the image will be a square image outside gray and on the axis area (not
 the dots, points or bar plots) the area in lightblue.

 I don´t now if I have expressed well if not latter I will send an example,
 ok?

 Hi,
 You can make the background of the plot area a different color:

 # first set up the plot
 plot(X,Y,type=n,...)
 # get the coordinates of the edges of the plot
 xylim-par(usr)
 # then display a rectangle that fills it
 rect(xylim[1],xylim[3],xylim[2],xylim[4],
  col=lightblue,border=black)
 # then plot the points over the rectangle
 points(X,Y,type=b)

 Jim


[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] Graph color

2010-01-26 Thread Jose Narillos de Santos 
Hi all I want to apply different colors on a simple plot:

If I type par(br=gray) before a plot it puts all the image in gray but
(imagine I run a simple plot) want to let the centrall box (where the dots
are plotted) in white or image in lightblue.

Can anyone guide me to apply this second step (make the box where the series
are plotted in different colours).

Thanks in advance.

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] Quantmod error

2010-01-20 Thread Jose Narillos de Santos 
Hi all I have installed quantmod package but when I try to obtain GOOG data
appers this message: Can anyone inform why itappears?

I type getSymbols(GOOG,src=google)
Thanks and Best Regards for all

Error en download.file(paste(google.URL, q=, Symbols.name, startdate=,
:
  no fue posible abrir la URL '
http://finance.google.com/finance/historical?q=GOOGstartdate=Jan+01,+2007enddate=Jan+20,+2010output=csv
'
In download.file(paste(google.URL, q=, Symbols.name, startdate=,  :
  unable to resolve 'finance.google.com'

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] Two Easy questions

2009-12-24 Thread Jose Narillos de Santos 
Sorry all for these two easy questions:

First, I have a matrix with trhee columns:

A=
Name  Eight Puntuation
Pepe  1,85 10
Paco   1,7   7
Pablo   1,82  6


I want to scatter the two columns (I could use pairs or other functions...)
but the only doubt is that I cannot find the way to add in the associated
intersection (the point scattered) the label Pepe Paco and so on...So
next to point (1,8510) will appear Pepe.
Imagine I can get it (if the points are closer and the associated names
(labes) cross how can I modified them?
If someone can send me a link to investigate will be perfect¡¡¡

Can anyone help me?

Second, I have read that with R we can dowload directly stock market
historical information from google or yahoo. Can anyone guide me how to do
it or more easily where I can find information (a web link or something
similar)

Thanks for all¡¡¡

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] Data

2009-12-11 Thread Jose Narillos de Santos 
Hi all,

Imagine I have a matrix and the first colum is a list that repeats the same
names, I want to sum the second column on each unique name on first column.

Imagine this:

Pepe 2
Pepe 3
Pepe 4
Jose 2
Jose 5
Manuel 4
Manuel 2

I want to make a new matrix that calculates and recognizes that there are 3
different names ans sum second column. But a priori I don´t know the list of
the different names:

In my example

Pepe 9
Jose 7
Manuel 6

I´m trying to use something like sapply or apply but I can find the key...

Can anyone help or guide me ?

Thanks in advance¡¡¡

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] R download

2009-12-11 Thread Jose Narillos de Santos 
Hi all I want to make a copy about R in a external disk.

How many bytes will occupe if I could dowload all disposable libraries?

Is it possible? How should I proceed?

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

Re: [R] R download

2009-12-11 Thread Jose Narillos de Santos 
Sorry about the last question I ´m reading the solution. Sorry again.



2009/12/11 Jose Narillos de Santos narillosdesan...@gmail.com

 Hi all I want to make a copy about R in a external disk.

 How many bytes will occupe if I could dowload all disposable libraries?

 Is it possible? How should I proceed?


[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] Saving predict

2009-12-04 Thread Jose Narillos de Santos 
Hi all,,I´m using function arima()

I.e
series is my data

model-arima(series,c(1,0,0))
forecast-predict(model,80)
I want to create a variable:
b1-forecast$pred - 1.96*forecast$se
and save in a txt file

but using this:

save(b1, file= b1.txt)

creates afile butwith this  inside:

‹  ]Ò{H“Q ðï~Ÿß|¦›ùÊÊLJI³ÔiÍW*¥þ‘Í-l)˜%¤ 
)Šmæ#)­±,›
ÉйRIñ¸åœÈÊiSÂfµd›bҝôGuážß¹çr9p9œø´»4;‚ 
H‚´Å‘©‰¦­¥žL”#ÎR€ez´
ãÊÁ¹1ìy‡÷3pN8Ä®°{,IÚ6¡¢˜ÊW²–ížàôâ!ã“6éúžù=­à
êÍžó{·â6ƒ½l?øß×OõƒMw_ϐ¬û—¯•5ãëK÷ÖÝ©ÀZ+òÛ×
ô=é„ëæ ÉÊ(•YV·‘÷BçXùÔ(²E2 †uaÍz J
Yj±+P‘tSU[Pt­gíïoÆ...@¶,ŠËx�...@Þ)k¤$™TìÜ $/¼ÈA˜ 
dôz®‡p ÈÀù¢iþ
½Êw™�...@²räÖodœbë¤r@c¾ån€~ô™óW§ }û\M*g 
-¹w†ûšÛŸìj
hfEs! 4¡»Q‘h’Ë6%G ÒöJ 
mhdiÃ...@ã­§‹iÃ¥Â�...@êÐÇ/@£2Ôº èÜM³¡ ôV#
x=†Ý¥l8 h¤jgɨkrÂ¥Â...@õŽ|u=ö¿Ùæ ¡Ånº2
ûÔEÙTŒÍ©ËÔ¬cõꙩX§(Õø,
Á/ë2óM¬š°â°JIÄŠÛ°¬ºjÂÞ­î•~ÄŠ—]êDØ|¹°¿{9£tnË*‘âÿäÈýõ\lr—oö*6a’Ǧ±1:e¨{¢Îˆû'öî°Ü‡{ZÎl^Bb6ØËÌWbGŽ¤¯aåÆeKÿƒ‰5ß—°Ú®ü7™TacM*ŸØZ1…Â-£Wˆ?ëŸ'ô%ÁÅ‚œ0ÿžðBKeÓ²7–å'



Can anyone help me to do  it?

Do you know also a document wich expalin how works and calculates
modelpredictions?

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] Converting a Matrix in a colum vector

2009-12-04 Thread Jose Narillos de Santos 
Hi all,

Imagine I have a matrix G

with N rows

and M columns

So L=NxM is the number of different cells in my  matrix.

I want to create a column vector F whose size will be F(L,1)

So the fisrt row in F is G(1,1)
Second row in F is G(1,2)
When we arrive to a point M
the element M+1 will be G(2, 1)
Element M+2 will be G(2,2) and so on.

I´m trying but allways error

Easy Example:


G=
2 3 4
8 8 9


N=2
M=3
L=6

F=
2
3
4
8
8
9

Can anyone guide me?


Thanks in advance

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] polygon graph

2009-12-02 Thread Jose Narillos de Santos 
Hi all,

I have a matrix dd with dates and data. i WANT to create a grpah with shade
between the line and the zero axis. I´m trying to use polygon but something
doesn´ t work

Imagine.

I want to plot

g-read.table(dd.txt, col.names=c(fecha,DP))

g$fecha - as.Date(g$fecha, format=%d/%m/%Y)

t-g$fecha
st-length(g$DP)

ft-plot(t,g$DP,type=l,ylab=DP)

polygon(c(1, 1:st, st), c(0, g$USGDP, 0), col = blue)

abline(h = 0, lwd = 1, col = black)

If I ommit ploygon line the doc works properly (it plots a graph line).

But I want to colur the area below or over the line and the zero axis.

Can you guide or indicate because in this case polygon doesn´t work.

I attach the two files.



Thanks in advance for all.
31/03/1948  12.9
30/06/1948  24.9
30/09/1948  45.6
31/12/1948  24.2
31/03/1949  21.1
30/06/1949  -21.1
30/09/1949  -20.5
31/12/1949  -21.6
31/03/1950  23.8
30/06/1950  27.4
30/09/1950  10.4
31/12/1950  13.4
31/03/1951  10.3
30/06/1951  28.9
30/09/1951  26.8
31/12/1951  25.2
31/03/1952  24.9
30/06/1952  23.3
30/09/1952  22
31/12/1952  25.2
31/03/1953  26.1
30/06/1953  26.7
30/09/1953  25.4
31/12/1953  0.4
31/03/1954  -21.9
30/06/1954  -22.5
30/09/1954  -02.8
31/12/1954  22.8
g-read.table(PIB.txt, col.names=c(fecha,DP), sep=;,dec=,)

g$fecha - as.Date(g$fecha, format=%d/%m/%Y)

t-g$fecha
st-length(g$DP)

ft-plot(t,g$DP,type=l,ylab=US GDP, xlab=Tiempo,main=Evolución Histórica 
PIB US) 

#polygon(c(1, 1:st, st), c(0, g$DP, 0), col = blue)

grid()

abline(h = 0, lwd = 1, col = black)

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Scatter plot with margin distributions

2009-11-25 Thread Jose Narillos de Santos 
Finally I get a plot manual...so I got the solution

Sorry about inconveniences


2009/11/24, Jose Narillos de Santos narillosdesan...@gmail.com:

 Hi All,

 My doub I think is very simple. I hope it is. So you can again help, guide
 me.

 I´m trying to make a graph (scatter graph) about two variables, imagine I
 have a watter.txt file with two variables watter and hardness:

 This code extracted from:
 http://cran.r-project.org/web/packages/HSAUR/vignettes/Ch_simple_inference.pdf
 would make a plot similar I want I mean to make an scatterplot with
 marginal ditribution up and left...(in this case a boxplot on the left and
 also I omitt the location).


 layout(matrix(c(2, 0, 1, 3), 2, 2, byrow = TRUE),
 2 + c(2, 1), c(1, 2), TRUE)

 plot(mortality ~ hardness, data = water, pch = psymb)

 abline(lm(mortality ~ hardness, data = water))

 legend(topright, legend = levels(water$location), 7 + pch = c(1,2), bty
 = n)

 hist(water$hardness)

 boxplot(water$mortality)



 Can anyone explain what is the values in layout the inputs I mean, I have
 read the help but because I´m a begginer I ´m not able to comprehed why they
 put matrix c(2,0,1,3) and the other inputs?



 I need if someone can help me an easy example



 Thanks a lot.






[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] Plot and area below a line graph

2009-11-25 Thread Jose Narillos de Santos 
Imagine I have a variable X

I use plot (X, type=l).

I want to show with colour the area between the line of X and the Zero
Axis.

So that if X have negative values the colored area will be below zero.

I´m trying to make this with polygons() but I´m not able

Can you guide me to do it?


The other question is how can I show the zero axis in a plot?

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] Scatter plot with margin distributions

2009-11-24 Thread Jose Narillos de Santos 
Hi All,

My doub I think is very simple. I hope it is. So you can again help, guide
me.

I´m trying to make a graph (scatter graph) about two variables, imagine I
have a watter.txt file with two variables watter and hardness:

This code extracted from:
http://cran.r-project.org/web/packages/HSAUR/vignettes/Ch_simple_inference.pdf
would make a plot similar I want I mean to make an scatterplot with marginal
ditribution up and left...(in this case a boxplot on the left and also I
omitt the location).


layout(matrix(c(2, 0, 1, 3), 2, 2, byrow = TRUE),2 + c(2, 1), c(1, 2), TRUE)

plot(mortality ~ hardness, data = water, pch = psymb)

abline(lm(mortality ~ hardness, data = water))

legend(topright, legend = levels(water$location), 7 + pch = c(1,2), bty =
n)

hist(water$hardness)

boxplot(water$mortality)



Can anyone explain what is the values in layout the inputs I mean, I have
read the help but because I´m a begginer I ´m not able to comprehed why they
put matrix c(2,0,1,3) and the other inputs?



I need if someone can help me an easy example



Thanks a lot.

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] URGENT helo re-beggining with R

2009-10-22 Thread Jose Narillos de Santos 
Hi all,

I have re-begging to use R.

I need to using a matrix Y and X with the first row been the name to get a
ols regression and to plot a two elements graph...on the top
the scattergraph and the line representing the regressiónbelow the
resids...at the same time I want to plot with small lines  representing the
error or one desviation from the regressión.

I attach a graph...to get better understood.

Please if you writte me the code explain how to put names on both plots.
MAny Thanks¡¡¡

I saw a document explaining but I can´t find

Thanks in advance

Imagine you load on a directory (in example mydocuments) the data file and
that it is an xls or *.txt file.
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] Add a line in a Pairs2 and mark the axis length

2009-07-29 Thread Jose Narillos de Santos 
Hi,

I have finally installed TeachingDemos trough zip file and installed on
lbrary.

One new question:

I want to draw a line (like abline) on diagonal or the result of running a
ols.

How can I do it.

On the other hand, I want to mark the length on each sub plot y axis.

It is possible?

My function is


sca-function(){

z2-read.table(Ase.txt,header=T)

z3-read.table(Ase2.txt,header=T)

pairs2(z2,z3)


}





Ase.txt cointains





   3653 4617 4177 3907 3975 3651 3031 2912 3018





Ase2.txt contains

ant g t



 219390 8740 17220
301510 8530 17550
316970 8640 17650
 364220 9360 21420
 387390 9960 23410
  430180 11040 25820
 499930 12240 27620
595010 13800 31670
 661870 14760 37170


2009/7/28, Petr PIKAL petr.pi...@precheza.cz:

 r-help-boun...@r-project.org napsal dne 28.07.2009 15:39:03:

 
  Have you installed it first?
  First:
  install.packages(TeachingDemos)

 Or if you have problems with correct setting through corporate network
 rules (like myself) you can download a zip (for Windows) version and unzip
 it to library subdirectory.

  Then:
  library(TeachingDemos)

 shall be executed without problem

 Regards
 Petr


 
 
  --- On Tue, 7/28/09, Jose Narillos de Santos
 narillosdesan...@gmail.com wrote:
 
   From: Jose Narillos de Santos narillosdesan...@gmail.com
   Subject: Re: [R] pairs plot
   To: Petr PIKAL petr.pi...@precheza.cz, r-help@r-project.org,
 greg.s...@imail.org
   Received: Tuesday, July 28, 2009, 8:24 AM
   Hi,
  
   I tried to load typing library(TeachingDemos)
  
   But the message can´t find package TeachingDemos) occurs.
   I use versión
   R 2.9 on windows.
  
   Can you please guide me?
  
   Sorry¡¡¡
  
  
  
  
  
   2009/7/28, Petr PIKAL petr.pi...@precheza.cz:
   
Hi
   
r-help-boun...@r-project.org
   napsal dne 28.07.2009 09:55:11:
   
 Hi Greg I saw, read, the TeachingDemos you
   suggesttef but when run
pairs2
 function on my R module says Can´t find
   function pairs2

 How can I load the module or function pairs2?
   
Did you do
   
library(TeachingDemos)?
   
Regards
Petr
   
   

 Thanks in advance for your help.

 You are the best.

 2009/7/27, Greg Snow greg.s...@imail.org:
 
  Look at the pairs2 function in the
   TeachingDemos package.
 
  --
  Gregory (Greg) L. Snow Ph.D.
  Statistical Data Center
  Intermountain Healthcare
  greg.s...@imail.org
  801.408.8111
 
 
   -Original Message-
   From: r-help-boun...@r-project.org
   [mailto:r-help-boun...@r-
   project.org] On Behalf Of Jose Narillos
   de Santos
   Sent: Monday, July 27, 2009 9:02 AM
   To: r-help@r-project.org
   Subject: [R] pairs plot
  
   Hi all,
  
   I want to plot trough pairs() plot a
   matrix with 4 columns. I want
to
   make a
   trhee plot in a graph. Plotting pairs
   colum 2,3,4 on y axis and 1 on
X
   axis.
  
   You mean (a plot with three graphs)
   ommitting the first pair with
   itself.
   And only the pairs with colum 1 with
   the other not all pairs.
  
   I. e. this matrix
  
   4177 289390 8740 17220
   3907 301510 8530 17550
   3975 316970 8640 17650
   3651 364220 9360 21420
   3031 387390 9960 23410
   2912 430180 11040 25820
   3018 499930 12240 27620
   2685 595010 13800 31670
   2884 661870 14760 37170
  
   Thanks in advance.
  
  
  [[alternative HTML version deleted]]
  
  
   __
   R-help@r-project.org
   mailing list
   https://stat.ethz.ch/mailman/listinfo/r-help
   PLEASE do read the posting guide
 http://www.R-project.org/posting- http://www.r-project.org/posting-
   guide.html
   and provide commented, minimal,
   self-contained, reproducible code.
 

[[alternative HTML version
   deleted]]

 __
 R-help@r-project.org
   mailing list
 https://stat.ethz.ch/mailman/listinfo/r-help
 PLEASE do read the posting guide
http://www.R-project.org/posting-guide.htmlhttp://www.r-project.org/posting-guide.html
 and provide commented, minimal, self-contained,
   reproducible code.
   
   
  
   [[alternative HTML version deleted]]
  
  
   -Inline Attachment Follows-
  
   __
   R-help@r-project.org
   mailing list
   https://stat.ethz.ch/mailman/listinfo/r-help
   PLEASE do read the posting guide
 http://www.R-project.org/posting-guide.htmlhttp://www.r-project.org/posting-guide.html
   and provide commented, minimal, self-contained,
   reproducible code.
  
 
 
__
  Yahoo! Canada Toolbar: Search from anywhere on the web, and bookmark
 your
  favourite sites. Download it now
  http://ca.toolbar.yahoo.com

Re: [R] pairs plot

2009-07-28 Thread Jose Narillos de Santos 
Hi Greg I saw, read, the TeachingDemos you suggesttef but when run pairs2
function on my R module says Can´t find function pairs2

How can I load the module or function pairs2?

Thanks in advance for your help.

You are the best.

2009/7/27, Greg Snow greg.s...@imail.org:

 Look at the pairs2 function in the TeachingDemos package.

 --
 Gregory (Greg) L. Snow Ph.D.
 Statistical Data Center
 Intermountain Healthcare
 greg.s...@imail.org
 801.408.8111


  -Original Message-
  From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-
  project.org] On Behalf Of Jose Narillos de Santos
  Sent: Monday, July 27, 2009 9:02 AM
  To: r-help@r-project.org
  Subject: [R] pairs plot
 
  Hi all,
 
  I want to plot trough pairs() plot a matrix with 4 columns. I want to
  make a
  trhee plot in a graph. Plotting pairs colum 2,3,4 on y axis and 1 on X
  axis.
 
  You mean (a plot with three graphs) ommitting the first pair with
  itself.
  And only the pairs with colum 1 with the other not all pairs.
 
  I. e. this matrix
 
  4177 289390 8740 17220
  3907 301510 8530 17550
  3975 316970 8640 17650
  3651 364220 9360 21420
  3031 387390 9960 23410
  2912 430180 11040 25820
  3018 499930 12240 27620
  2685 595010 13800 31670
  2884 661870 14760 37170
 
  Thanks in advance.
 
[[alternative HTML version deleted]]
 
  __
  R-help@r-project.org mailing list
  https://stat.ethz.ch/mailman/listinfo/r-help
  PLEASE do read the posting guide http://www.R-project.org/posting-
  guide.html
  and provide commented, minimal, self-contained, reproducible code.


[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

Re: [R] pairs plot

2009-07-28 Thread Jose Narillos de Santos 
Hi,

I tried to load typing library(TeachingDemos)

But the message can´t find package TeachingDemos) occurs. I use versión
R 2.9 on windows.

Can you please guide me?

Sorry¡¡¡





2009/7/28, Petr PIKAL petr.pi...@precheza.cz:

 Hi

 r-help-boun...@r-project.org napsal dne 28.07.2009 09:55:11:

  Hi Greg I saw, read, the TeachingDemos you suggesttef but when run
 pairs2
  function on my R module says Can´t find function pairs2
 
  How can I load the module or function pairs2?

 Did you do

 library(TeachingDemos)?

 Regards
 Petr


 
  Thanks in advance for your help.
 
  You are the best.
 
  2009/7/27, Greg Snow greg.s...@imail.org:
  
   Look at the pairs2 function in the TeachingDemos package.
  
   --
   Gregory (Greg) L. Snow Ph.D.
   Statistical Data Center
   Intermountain Healthcare
   greg.s...@imail.org
   801.408.8111
  
  
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-
project.org] On Behalf Of Jose Narillos de Santos
Sent: Monday, July 27, 2009 9:02 AM
To: r-help@r-project.org
Subject: [R] pairs plot
   
Hi all,
   
I want to plot trough pairs() plot a matrix with 4 columns. I want
 to
make a
trhee plot in a graph. Plotting pairs colum 2,3,4 on y axis and 1 on
 X
axis.
   
You mean (a plot with three graphs) ommitting the first pair with
itself.
And only the pairs with colum 1 with the other not all pairs.
   
I. e. this matrix
   
4177 289390 8740 17220
3907 301510 8530 17550
3975 316970 8640 17650
3651 364220 9360 21420
3031 387390 9960 23410
2912 430180 11040 25820
3018 499930 12240 27620
2685 595010 13800 31670
2884 661870 14760 37170
   
Thanks in advance.
   
  [[alternative HTML version deleted]]
   
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-
guide.html
and provide commented, minimal, self-contained, reproducible code.
  
 
 [[alternative HTML version deleted]]
 
  __
  R-help@r-project.org mailing list
  https://stat.ethz.ch/mailman/listinfo/r-help
  PLEASE do read the posting guide
 http://www.R-project.org/posting-guide.html
  and provide commented, minimal, self-contained, reproducible code.



[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] pairs plot

2009-07-27 Thread Jose Narillos de Santos 
Hi all,

I want to plot trough pairs() plot a matrix with 4 columns. I want to make a
trhee plot in a graph. Plotting pairs colum 2,3,4 on y axis and 1 on X axis.

You mean (a plot with three graphs) ommitting the first pair with itself.
And only the pairs with colum 1 with the other not all pairs.

I. e. this matrix

4177 289390 8740 17220
3907 301510 8530 17550
3975 316970 8640 17650
3651 364220 9360 21420
3031 387390 9960 23410
2912 430180 11040 25820
3018 499930 12240 27620
2685 595010 13800 31670
2884 661870 14760 37170

Thanks in advance.

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] writte file doubt

2009-07-21 Thread Jose Narillos de Santos 
Hi I wrotte this function but when I get the tmp.xls file  it shows data
in a rare way. I mean not appears a matrix with 2000 rows and 100 columns.
Can anyone help me, guide me?

kim-function(){

tmp-randz-matrix(rnorm(20, mean=0,sd=0.01 ),2000,100);

dim(tmp)

write(tmp,file=tmp.xls)

 Thanks in advance.



On the other hand, everytime I execute a function that is locatd in my
documents I must open it source(file.choose()) , there is a folder where to
put my function to not necesessary run prevously source(file.choose()).

Thanks in advance.




}

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] Save results

2009-07-16 Thread Jose Narillos de Santos 
I imagine I make a function whose results are a Matrix Z

How cn I save in a txt or excel file the result of apply my function?

something similar to save Z.txt.

Thanks in advance.

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[R] rnorm

2009-07-16 Thread Jose Narillos de Santos 
Hi I want to simulate random numbers normal distributed with this size
(2000,1).

I tried this but my computer exhaust there is a fast way to make it?


randz-matrix(rnorm(200),2000,1)

[[alternative HTML version deleted]]

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.