tag:blogger.com,1999:blog-6232819486261696035.post8122570924942869959..comments2023-09-25T09:01:44.323-05:00Comments on Getting Genetics Done: Scatterplot matrices in RStephen Turnerhttp://www.blogger.com/profile/06656711316726116187noreply@blogger.comBlogger6125tag:blogger.com,1999:blog-6232819486261696035.post-4269167080211376642016-05-16T09:54:31.191-05:002016-05-16T09:54:31.191-05:00Very useful function!
An improvement would be:
r...Very useful function!<br /><br />An improvement would be:<br /><br />r <- cor(x, y) # remove abs()<br />text(0.5, 0.5, txt, cex = cex.cor * abs(r)) # and move to this line<br /><br /><br />In this way, we plot the real (positive or negative) value of the correlation coefficient and not only positive values. So, we also can draw higher sizes in strong negative correlation coefficients.Anonymoushttps://www.blogger.com/profile/11753214089319264691noreply@blogger.comtag:blogger.com,1999:blog-6232819486261696035.post-9476746201513958372015-09-13T15:03:19.211-05:002015-09-13T15:03:19.211-05:00Very useful, thank you.
You can get rid of the me...Very useful, thank you.<br /><br />You can get rid of the measures in the axis by using xaxt = 'n' and yaxt = 'n' inside the pairs functionJavier Ribalhttps://www.blogger.com/profile/10578908227249449251noreply@blogger.comtag:blogger.com,1999:blog-6232819486261696035.post-49892799305759825232011-08-25T15:39:53.653-05:002011-08-25T15:39:53.653-05:00Also, check out Zach Meyer's post on graphical...Also, check out Zach Meyer's post on <a href="http://moderntoolmaking.blogspot.com/2011/08/graphically-analyzing-variable.html" rel="nofollow">graphically analyzing variable interactions</a>, which shows even more advanced scatterplot matrix plots.Stephen Turnerhttps://www.blogger.com/profile/06656711316726116187noreply@blogger.comtag:blogger.com,1999:blog-6232819486261696035.post-57598680602242073662011-07-27T14:49:45.636-05:002011-07-27T14:49:45.636-05:00I appreciate the link to the psych package functio...I appreciate the link to the psych package function. pairs.panels() adds some nice functionality!Stephen Turnerhttps://www.blogger.com/profile/06656711316726116187noreply@blogger.comtag:blogger.com,1999:blog-6232819486261696035.post-19086445127366585232011-07-27T05:58:13.214-05:002011-07-27T05:58:13.214-05:00That would be the highly recommended pairs.panels(...That would be the highly recommended pairs.panels() function. It does also paint ellipses. Have a look at these examples:<br />http://www.oga-lab.net/RGM2/func.php?rd_id=psych:pairs.panelsAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-6232819486261696035.post-27684846142597440072011-07-27T02:10:28.390-05:002011-07-27T02:10:28.390-05:00There's also a function in the psych package (...There's also a function in the psych package (built on top of the two lattice functions you describe above) which has scatterplots in the upper triangle, loess fits on the lower and histograms on the diagonal.Disgruntled PhDhttps://www.blogger.com/profile/00926204336056169207noreply@blogger.com