[R] Formula for normal distribution with know mean and standard error and n terms

[GlenB]

Steve_Friedman at nps.gov wrote:
> 
> I am searching for a method to calculate a normal distribution.
> 
> For example this equation is used to calculate the normal curve when the
> mean and standard deviation are know.
> p(x) = (1/σ*sqrt(2π)) x exp (- (x-μ)2/2σ2)
> 
> However, some of the literature I'm reading (I'm building an ecological
> niche model for vegetation along several ecological gradients) report the
> standard error instead and n sample size.  Is there an equivalent formula
> ?
> If so, how can I also normalize the p(x) term to be within the 0-1 range?
> 

What you have there (p) is a density rather than the distribution.

note that p(x) is NOT a probability, so it doesn't lie between 0 and 1 

(integrals of p(x).dx are probabilities and do lie between 0 and 1)

The function to compute p is dnorm. Try ?dnorm in R.

if you're given the standard error of a mean (which I'll call "se") and n, 
then sigma = sqrt(n)*se

(because se = sigma/sqrt(n) ).

If it's the standard error of something other than the mean you'll need to
give
more details.


-- 
View this message in context: http://n4.nabble.com/Formula-for-normal-distribution-with-know-mean-and-standard-error-and-n-terms-tp1013280p1013552.html
Sent from the R help mailing list archive at Nabble.com.