To "demonstrate that [a variable] is normally distributed", have you considered normal probability plots (e.g., via qqnorm)? They are much more sensitive to departures from normality and much more informative on the nature of those departures, e.g., showing skewness, mixtures, outliers, ... .

hope this helps. spencer graves

Peter Dalgaard BSA wrote:
"Paul Meagher" <[EMAIL PROTECTED]> writes:


I am wanting to construct a probability distribution for height and then,
hopefully, visually and analytically demonstrate that it is normally
distributed.

These are the commands I have developed so far:

fat   <- read.table("fat.dat", header=TRUE)
mu    <- mean(fat$height)
sdev  <- sd(fat$height)
hist(fat$height, br=20, freq=FALSE, xlab="Male Height in Inches")
curve(dnorm(x, mu, sdev), from=64, to=78)

I do not know how to overlay the curve graphic on top of hist graphic.

I am hoping to show visually that the normal curve overlays the obtained
probability distribution when plotted on the same graph.  Unfortunately, I
an not sure how to overlay them. Can anyone point me in the right direction
or show me the code.


Using the "add" argument to curve gets you most of the way, but
getting the y axis right is a little tricky. You could take a look at
the scripts in the ISwR package (sec.1.3), or the book itself...


______________________________________________ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help

Reply via email to