Displaying 2 results from an estimated 2 matches for "conjugacy".
2011 Oct 17
1
Best practices for handling very small numbers?
...wanted to experiment with tens of thousands of observations, but without
an implementation of a transformation that can handle very small values, my
sampling algorithms would not work.
This is an attempt to use some sampling algorithms for Bayesian parameter
estimation. I do not want to resort to conjugacy, since I am developing this
to handle non conjugate scenarios, I just wanted to test it on a conjugate
scenario, but I've quickly realized that I'm in trouble due to likelihood
reaching 0 quickly.
Your feedback would be appreciated. It makes me wonder how JAGS/BUGS handles
this problem
Be...
2006 Dec 05
3
Comparing posterior and likelihood estimates for proportions (off topic)
...es should agree.
Specifically, I am asking the question, "What is the probability that
the true proportion of students passing a test is 50% when the observed
proportion for that school is only 38%?"
For my example, there are 100 students in the school and 38 of them
passed an exam. For conjugacy, if we choose a beta prior, then posterior
in this case is also a beta distribution. Now, I believe the a and b
parameters for a beta with a uniform prior is a=1 and b=1, or 1/(1+1)
Here is my R code for the posterior with a flat prior
n <- 100 # Total number of individuals
y <- 38 # Numbe...