I have tried to build a normal qq plot on my own, but it does not match with the implemented qqnorm in R. What am I missing? As You can see, the points do not match. qqnorm(c(-2.8,qnorm(seq(0,1,by=(1/200))[2:199],0,1),2.8)) points(qnorm(seq(0,1,by=(1/200))[2:199],0,1), qnorm(seq(0,1,by=(1/200))[2:199],0,1), col="red") The main issue is, that I would like to change the backgorund color auf my plot to be consitent with t other plots I have already produced. -- View this message in context: http://r.789695.n4.nabble.com/Building-normal-qq-plot-tp4633242.html Sent from the R help mailing list archive at Nabble.com.
> I have tried to build a normal qq plot on my own, > but it does not match with the implemented qqnorm in R. > > The main issue is, that I would like to change the backgorund > color auf my plot ...One thing you could try is setting the background colour using bar(bg="lightyellow") before calling qqnorm If you want to know what qqnorm is doing in some detail, type> qqnorm.defaultat the command line (_wthout_ brackets) and inspect the code. Two reasons for doing that. One is that you will find that it uses ppoints to generate its probability points, and it is that that you need to match. So you could use ppoints directly (in the same manner as qqnorm) to calculate your locations. The other reason is that you can now copy the code, paste it into an editor, call it my.qqnorm, add the background code you want, paste it back into R and run it instead of qqnorm. S Ellison ******************************************************************* This email and any attachments are confidential. Any use...{{dropped:8}}
Thank you very much. It was quite easy to adjust the code to get the background colour I have always used. I only tried to get the code using list(qqnorm). Thanks -- View this message in context: http://r.789695.n4.nabble.com/Building-normal-qq-plot-tp4633242p4633257.html Sent from the R help mailing list archive at Nabble.com.