Johannes Graumann
2010-Aug-14 20:33 UTC
[R] Relation 1.5*IQR/Percentile in case of a normal Distribution
Hi, can someone point me at material to understand how in http://upload.wikimedia.org/wikipedia/commons/8/89/Boxplot_vs_PDF.png the "fivenum"-corresponding percentages might be calculated? Thanks, Joh
Peter Dalgaard
2010-Aug-14 21:08 UTC
[R] Relation 1.5*IQR/Percentile in case of a normal Distribution
Johannes Graumann wrote:> Hi, > > can someone point me at material to understand how in > http://upload.wikimedia.org/wikipedia/commons/8/89/Boxplot_vs_PDF.png the > "fivenum"-corresponding percentages might be calculated?Looks like a pretty straightforward application of pnorm() and qnorm(). pnorm(4*qnorm(.75), lower=F) # Q3 + 1.5 IQR = 4 Q3 since IQR = 2 Q3 [1] 0.003488302 gives the tail probabilities of .35%, and the rest is by definition. -- Peter Dalgaard Center for Statistics, Copenhagen Business School Phone: (+45)38153501 Email: pd.mes at cbs.dk Priv: PDalgd at gmail.com
Johannes Graumann
2010-Aug-15 05:59 UTC
[R] Relation 1.5*IQR/Percentile in case of a normal Distribution
On Saturday 14 August 2010 23:08:31 Peter Dalgaard wrote:> Johannes Graumann wrote: > > Hi, > > > > can someone point me at material to understand how in > > http://upload.wikimedia.org/wikipedia/commons/8/89/Boxplot_vs_PDF.png the > > "fivenum"-corresponding percentages might be calculated? > > Looks like a pretty straightforward application of pnorm() and qnorm(). > > pnorm(4*qnorm(.75), lower=F) # Q3 + 1.5 IQR = 4 Q3 since IQR = 2 Q3 > > [1] 0.003488302 > > gives the tail probabilities of .35%, and the rest is by definition.Thanks a lot! Joh -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 836 bytes Desc: This is a digitally signed message part. URL: <https://stat.ethz.ch/pipermail/r-help/attachments/20100815/b16a0a82/attachment.bin>