# [R] qq plot issue with ab line

Jim Lemon drj|m|emon @end|ng |rom gm@||@com
Sat Feb 29 00:08:37 CET 2020

```Hi Ana,
I should clarify what I wrote in the previous email. You are expecting
an approximately square plot with a line running at about an angle of
45 degrees from lower left to upper right. However, the range of x and
y values that you are plotting are not approximately equal. This means
that lines with a slope of 1 will not run from corner to corner or
even parallel such a line. I hope that explains it better.

Jim

On Sat, Feb 29, 2020 at 9:54 AM Jim Lemon <drjimlemon using gmail.com> wrote:
>
> Hi Ana,
> I'll do my best. In the attached image, I have placed two green disks
> at (0,0) and (1,1). These points are on a line with intercept 0 and
> slope 1 as are all the other points on that line. When you ask for an
> abline with two unnamed arguments, the first is the intercept and the
> second is the slope. The abline function them draws a line with these
> values across the plot. So it has done what you asked. If you specify
> xlim=c(0,1) in the initial plot, you will get what you expect, but you
> will leave all x values greater than 1.04 off the plot.
>
> Jim
>
> On Sat, Feb 29, 2020 at 8:41 AM Ana Marija <sokovic.anamarija using gmail.com> wrote:
> >
> > Hi Jim,
> >
> > I have in my code:
> > abline(0,1,col='red')
> >
> > can you please tell me how to change my code to have it indeed running
> > from 0 to 1?
> >
> > Thanks
> > Ana
> >
> > On Fri, Feb 28, 2020 at 3:34 PM Jim Lemon <drjimlemon using gmail.com> wrote:
> > >
> > > Hi Ana,
> > > Look carefully at that red line. It goes through (0,0) and scoots off
> > > the plot at (2.5,2.5). As you have specified that intercept and slope
> > > in your code, poor abline is doing the best it can. Do not punish it
> > > for doing what you request.
> > >
> > > Jim
> > >
> > > On Sat, Feb 29, 2020 at 6:10 AM Ana Marija <sokovic.anamarija using gmail.com> wrote:
> > > >
> > > > Hello,
> > > >
> > > > I made the plot in attach with this function:
> > > >
> > > > qqunif = function(p, BH=T, MAIN = " ", SUB=" ")
> > > > {
> > > >   nn = length(p)
> > > >   xx =  -log10((1:nn)/(nn+1))
> > > >   plot( xx,  -sort(log10(p)),
> > > >         main = MAIN, sub= SUB, cex.sub=1.3,
> > > >         xlab=expression(Expected~~-log[10](italic(p))),
> > > >         ylab=expression(Observed~~-log[10](italic(p))),
> > > >         cex.lab=1.0,mgp=c(2,1,0))
> > > >   abline(0,1,col='red')
> > > >   if(BH) ## BH = include Benjamini Hochberg FDR
> > > >   {
> > > >
> > > >     abline(-log10(0.05),1, col='black',lty=1)
> > > >     text(0.5,1.9 , "FDR=0.05", col = "gray60",srt=20, cex=1)
> > > >     abline(-log10(0.10),1, col='black',lty=1)
> > > >     text(0.5, 1.6, "FDR=0.10", col = "gray60",srt=20, cex=1)
> > > >     abline(-log10(0.25),1, col='black',lty=1)
> > > >     text(0.5, 1.2, "FDR=0.25", col = "gray60",srt=20, cex=1)
> > > >     #legend('topleft', c("FDR = 0.05","FDR = 0.10","FDR = 0.25"),
> > > >            #col=c('black','black','black'),lty=c(1,1,1), cex=0.8)
> > > >     if (BF)
> > > >     {
> > > >       abline(h=-log10(0.05/nn), col='black') ## bonferroni
> > > >     }
> > > >   }
> > > > }
> > > >
> > > >
> > > > qqunif(biob272\$V2)
> > > >
> > > >
> > > > > head(biob272)
> > > >          V1       V2
> > > > 1 rs2089177 0.581204
> > > > 2 rs4360974 0.418456
> > > > 3 rs6502526 0.416670
> > > > 4 rs8069906 0.568030
> > > > 5 rs9895995 0.266746
> > > > 6 rs9905280 0.510032
> > > >
> > > > But the red, abline doesn't look like it is 1:1 line.
> > > >
> > > >
> > > > Thanks
> > > > Ana
> > > > ______________________________________________
> > > > R-help using r-project.org mailing list -- To UNSUBSCRIBE and more, see
> > > > https://stat.ethz.ch/mailman/listinfo/r-help
> > > > and provide commented, minimal, self-contained, reproducible code.

```