Condional Density Plot from different data

[Doran, Harold]

I'm not certain I am using the lattice plot correctly here. Below is reproducible code. Suppose I have two data frames, such as:

set.seed(1234)
datA <- data.frame(condition = gl(3, 100), scores = c(rnorm(100), rnorm(100, 1,1), rnorm(100, 2,1)))
datB <- data.frame(condition = gl(3, 1000), scores = c(rnorm(1000, 3,1), rnorm(1000, 4,1), rnorm(1000, 5,1)))

I would like to plot the empirical conditional densities (conditional on the variable "condition") in a fashion such as:

library(lattice)
densityplot(~datA$scores + datB$scores|datA$condition)

However, I don't think this is doing what I think it should be doing. For instance, if I compare it to:

AA <- subset(datA, condition == '1')
BB <- subset(datB, condition == '1')
plot(density(AA$scores))
lines(density(BB$scores))

Things are clearly different. Can anyone identify my error in the trellis plot code?

Thank you,
Harold


> sessionInfo()
R version 2.12.0 (2010-10-15)
Platform: i386-pc-mingw32/i386 (32-bit)

locale:
[1] LC_COLLATE=English_United States.1252  LC_CTYPE=English_United States.1252    LC_MONETARY=English_United States.1252
[4] LC_NUMERIC=C                           LC_TIME=English_United States.1252    

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base    

other attached packages:
[1] lattice_0.19-13

loaded via a namespace (and not attached):
[1] grid_2.12.0

______________________________________________
[hidden email] 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.

[Doran, Harold]

Perhaps I found a solution as:

datA$type <- gl(1, nrow(datA), label = 'PopA')
datB$type <- gl(1, nrow(datB), label = 'PopB')
dat <- rbind(datA, datB)
densityplot(~scores|condition, group = type, dat)

> -----Original Message-----
> From: [hidden email] [mailto:[hidden email]] On
> Behalf Of Doran, Harold
> Sent: Thursday, December 09, 2010 12:40 PM
> To: [hidden email]
> Subject: [R] Condional Density Plot from different data
>
> I'm not certain I am using the lattice plot correctly here. Below is
> reproducible code. Suppose I have two data frames, such as:
>
> set.seed(1234)
> datA <- data.frame(condition = gl(3, 100), scores = c(rnorm(100), rnorm(100,
> 1,1), rnorm(100, 2,1)))
> datB <- data.frame(condition = gl(3, 1000), scores = c(rnorm(1000, 3,1),
> rnorm(1000, 4,1), rnorm(1000, 5,1)))
>
> I would like to plot the empirical conditional densities (conditional on the
> variable "condition") in a fashion such as:
>
> library(lattice)
> densityplot(~datA$scores + datB$scores|datA$condition)
>
> However, I don't think this is doing what I think it should be doing. For
> instance, if I compare it to:
>
> AA <- subset(datA, condition == '1')
> BB <- subset(datB, condition == '1')
> plot(density(AA$scores))
> lines(density(BB$scores))
>
> Things are clearly different. Can anyone identify my error in the trellis plot
> code?
>
> Thank you,
> Harold
>
>
> > sessionInfo()
> R version 2.12.0 (2010-10-15)
> Platform: i386-pc-mingw32/i386 (32-bit)
>
> locale:
> [1] LC_COLLATE=English_United States.1252  LC_CTYPE=English_United States.1252
> LC_MONETARY=English_United States.1252
> [4] LC_NUMERIC=C                           LC_TIME=English_United States.1252
>
> attached base packages:
> [1] stats     graphics  grDevices utils     datasets  methods   base
>
> other attached packages:
> [1] lattice_0.19-13
>
> loaded via a namespace (and not attached):
> [1] grid_2.12.0
>
> ______________________________________________
> [hidden email] 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.

______________________________________________
[hidden email] 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.

[Deepayan Sarkar]

On Thu, Dec 9, 2010 at 10:11 AM, Doran, Harold <[hidden email]> wrote:
> Perhaps I found a solution as:
>
> datA$type <- gl(1, nrow(datA), label = 'PopA')
> datB$type <- gl(1, nrow(datB), label = 'PopB')
> dat <- rbind(datA, datB)

Or, slightly shorter

dat <- make.groups(datA, datB)
densityplot(~scores|condition, groups = which, dat)

> [...]

>> library(lattice)
>> densityplot(~datA$scores + datB$scores|datA$condition)

The problem here is that datA$scores and datB$scores don't have the
same length. This requirement is implicit in the description of the
extended formula interface:

          'y1 + y2 ~ x | a * b' [...] would be taken to mean that the
user wants to plot
          both 'y1 ~ x | a * b' and 'y2 ~ x | a * b' [...] superposed
in each panel.

and the latter formulae would make sense only if x, a, b, and y1 (and
y2) have the same length.

-Deepayan

______________________________________________
[hidden email] 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.

[rstudent]

Tried this and received this error:

Error in hist.default(x = integer(0), plot = FALSE) :
  invalid number of 'breaks'

Edit: Nevermind, I restarted R and it works now.  Thank you!

[Uwe Ligges-3]

On 08.07.2011 18:54, rstudent wrote:
> Tried this

Tried what? Nothing cited .... Please cite the original examples and
answers so that we can follow up.

Best,
Uwe Ligges



 > and received this error:

>
> Error in hist.default(x = integer(0), plot = FALSE) :
>    invalid number of 'breaks'
>
> --
> View this message in context: http://r.789695.n4.nabble.com/Condional-Density-Plot-from-different-data-tp3080615p3654634.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> [hidden email] 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.

______________________________________________
[hidden email] 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.