R help - Jul 2010 - dnorm Line Plot Graphics

Hello,

1. I have a number of snow depth measurements (centimeters depth) that were
acquired in a row (linear transect).

A: I am trying to plot the probability density function (PDF) of these points.
When I use the "dnorm" command and line type = points, the PDF is
displayed correctly. When I change the line type = line, it displays the PDF
curve with numerous lines connecting multiple of the points together rather than
just one line connecting the points in sequence. I have noticed in some online
help tutorials the use of the "seq" command, but when I employ this it
simply flattens my PDF curve to a straight line at 0% probability. Is there
something I am missing?
> plot(Snow,dnorm(Snow,mean=26.61,sd=14.179),type="l")
B: The y-axis labels seem quite small to me. For example, I would expect the
first tick mark to be "0.05" indicating a 5% frequency, not
"0.005." Suggestions?

C. Is there a simple way of changing the y-axis labels to display percent (ex.
5%) rather than decimal (ex. 0.05) without having to manually type in all of the
new tick mark labels using the "axis" command?


2. I have meteorological weather station data acquired at 6 different locations
that I would like to compare. The data spans two months (time series).

A. Can you please direct me to an online tutorial or help guide that instructs
how to place all 6 locations on the same plot for easy comparison?

B. I would also like to "stack" these plots so, for example, there
would be three plots stacked vertically with each plot having an individual
y-axis, but then a single x-axis (date) along the bottom. Can you please direct
me towards instructions that would cover such a plot?

Thank you,
EdmAB

On 13-Jul-10 22:21:29, Melissa Peters wrote:
> Hello,
> 
> 1. I have a number of snow depth measurements (centimeters depth) that
> were acquired in a row (linear transect). 
> 
> A: I am trying to plot the probability density function (PDF) of these
> points. When I use the "dnorm" command and line type = points,
the PDF
> is displayed correctly. When I change the line type = line, it displays
> the PDF curve with numerous lines connecting multiple of the points
> together rather than just one line connecting the points in sequence. I
> have noticed in some online help tutorials the use of the "seq"
> command, but when I employ this it simply flattens my PDF curve to a
> straight line at 0% probability. Is there something I am missing?
> 
>> plot(Snow,dnorm(Snow,mean=26.61,sd=14.179),type="l")
On just this point: From your description, it seems likely that the
values in "Snow" are not in increasing order. Hence, when you plot
usinf type="l", ir will take the points in the order in which they
are found in "Snow" and so the lines connecting successive points
will jump about all over the place. You can cure this by sorting
"Snow" into increasing order:

  plot(sort(Snow),dnorm(sort(Snow),mean=26.61,sd=14.179),type="l")

should do it. However, this may not look as nice as you would like,
if the spacings between successive sorted values are very irregular.
It may look better if you plot "Snow" as points, and then add
lines drawn to a regular sequence. Hence something like

  S0 <- ((max(Snow) - min(Snow))/100)*(-0.05+(0:101))
 
plot(Snow,dnorm(Snow,mean=26.61,sd=14.179),pch="+",col="blue")
  lines(S0,dnorm(S0,mean=26.61,sd=14.179),col="green")

may look better.

Hoping this helps,
Ted.

--------------------------------------------------------------------
E-Mail: (Ted Harding) <Ted.Harding at manchester.ac.uk>
Fax-to-email: +44 (0)870 094 0861
Date: 14-Jul-10                                       Time: 00:08:32
------------------------------ XFMail ------------------------------