R help - Apr 2013 - Q-Q Plot for comparing two unequal data sets

Hello All,

Would anyone be able to help me understand how R computes a
quantile-quantile plot for comparing two data samples with unequal sample
sizes?  Normally, the procedure should be to rearrange the larger data
sample into n equally-spaced parts using interpolation, where n is the
sample size of the smaller sample, and then plot the matching data pairs.  I
tried using different plotting position formulas for the interpolation but
cannot reproduce what R is plotting.  Thanks in advance.

Regards
Janh

	[[alternative HTML version deleted]]

On Apr 16, 2013, at 20:12, Janh Anni <annijanh@gmail.com> wrote:
> Hello All,
> 
> Would anyone be able to help me understand how R computes a
> quantile-quantile plot for comparing two data samples with unequal sample
> sizes?  Normally, the procedure should be to rearrange the larger data
> sample into n equally-spaced parts using interpolation, where n is the
> sample size of the smaller sample, and then plot the matching data pairs. 
I
> tried using different plotting position formulas for the interpolation but
> cannot reproduce what R is plotting.  Thanks in advance.
If you type qqplot at the prompt you'll be given the code and can review it
for yourself. It's also available online for your viewing pleasure.

http://svn.r-project.org/R/trunk/src/library/stats/R/qqplot.R

It seems the key is the approx (linear interpolation) function, but you can work
out the details.

Michael

> 
> Regards
> Janh
> 
>    [[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]]