Got it, thanks!
baptiste
On 21 September 2010 22:38, Hans W Borchers wrote:
> baptiste auguie googlemail.com> writes:
>
>>
>> Thanks. I am having trouble getting adaptIntegrate to work with a
>> multivalued integrand though, and cannot find a working example.
>> Anyone had better luck with it?
baptiste auguie googlemail.com> writes:
>
> Thanks. I am having trouble getting adaptIntegrate to work with a
> multivalued integrand though, and cannot find a working example.
> Anyone had better luck with it?
The function to be integrated needs a vector as input:
f <- function(x) {
Thanks. I am having trouble getting adaptIntegrate to work with a
multivalued integrand though, and cannot find a working example.
Anyone had better luck with it?
library(cubature)
>
> f <- function(x, y) {
+ res <- 1 / (sqrt(x)*(1+x))
+ c(res, res/2, 2*res)
+ }
>
> adaptIntegrate(f, lowerLimi
baptiste auguie googlemail.com> writes:
>
> Thanks, adaptIntegrate() seems perfectly suited, I'll just need to
> figure a transformation rule for the infinite limit. The suggestion of
> x->1/x does not seem to work here because it also transforms 0 into
> -infinity. I think exp(pi* sinh(x)) coul
Thanks, adaptIntegrate() seems perfectly suited, I'll just need to
figure a transformation rule for the infinite limit. The suggestion of
x->1/x does not seem to work here because it also transforms 0 into
-infinity. I think exp(pi* sinh(x)) could be a better choice,
according to Numerical Recipes.
Hi,
thanks for the pointer to cubature (which i had probably dismissed too
quickly). Your tests with "f" should not work: the domain of f(x,.) is
restricted to positive reals, but this domain of integration is then
transformed in mixedrule() to map the semi-infinite range to a more
reasonable doma
baptiste auguie googlemail.com> writes:
>
> Dear list,
>
> I'm seeking some advice regarding a particular numerical integration I
> wish to perform.
>
> The integrand f takes two real arguments x and y and returns a vector
> of constant length N. The range of integration is [0, infty) for x an
Baptiste;
You should see if this meets your requirements:
help(adaptIntegrate, package=cubature)
(I got errors when I ran the code and NaN's when I looked at the
output of test function, "f".)
> vAverage(mixedrule, -4, 4, 0.0, 1, 20, f) - c(pi, pi/2, 2*pi)
Error: object 'mixedrule' not foun
Dear list,
I'm seeking some advice regarding a particular numerical integration I
wish to perform.
The integrand f takes two real arguments x and y and returns a vector
of constant length N. The range of integration is [0, infty) for x and
[a,b] (finite) for y. Since the integrand has values in R
9 matches
Mail list logo
