Displaying 1 result from an estimated 1 matches for "joint_likelihood".
2011 Oct 17
1
Best practices for handling very small numbers?
Greetings
I have been experimenting with sampling from posterior distributions using
R. Assume that I have the following observations from a normal distribution,
with an unscaled joint likelihood function:
normsamples = rnorm(1000,8,3)
joint_likelihood = function(observations, mean, sigma){
return((sigma ^ (-1 * length(observations))) * exp(-0.5 * sum(
((observations - mean ) ^ 2)) / (sigma ^ 2) ));
}
the joint likelihood omits the constant (1/(2Pi)^n), which is what I want,
because I've been experimenting with some crude sampling method...