[R] log-normal Centile

Peter Ehlers ehlers at ucalgary.ca
Thu Dec 2 01:08:33 CET 2010


On 2010-12-01 07:09, Robert Quinn wrote:
> I am having problems trying to get R to graph data input that is log-normal
> on the horizontal (x) axis.
>
> The data is log (base 10), and I am more interested in viewing the tails of
> the distribution.  The closest I can get with this is log on the vertical
> (y) axis and linear on the horizontal axis.  Note that the x-axis is Centile
> (0%-100%) and is at this time linear, however I want it to be exponential
> 0%-50% and reverse exponential from 50%-100%.  Meaning there is the most
> spread in the data from 0%-5% and 95%-100%, and very little spread 25%-75%.
>
>
>
>
>
> This is what I have so far:
>
>
>
> plot(x,y,type="l",
>
>
>
>        log = "y",
>
>
>
>        xlab="Centile",
>
>
>
>        ylab="INH MoMs",
>
>
>
>        xlim=c(1,100),
>
>
>
>        ylim=c(0.3,5),
>
>
>
>        col="green" )
>
>
>
>       I have tried inserting "lognormal = "x"," and other code that might
> work that I have found on the "R help", but nothing seems to work.  Thank
> you in advance for your help.
>
Your chances of a useful response would likely increase if your
question were clearer. You say your data is log (base 10). I have
no idea what that means; log of what?

You want the x-axis to be bi-exponential? I *think* I have an
inkling of what you mean, but I have no idea what you want to
plot. Perhaps if you could explain clearly how you would do this
"by hand", it might make more sense.

It would be *very* useful to have some sample data to look at.

Peter Ehlers

>
>
> Respectfully, Bob Quinn
>
>
>
>
>
>
> 	[[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at 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.



More information about the R-help mailing list