Approximating the likelihood function
The first election poll is in! \(X\) = 6 of 10 polled voters plan to vote for you. You can use these data to build insight into your underlying support \(p\). To this end, you will use the likelihood_sim
data frame (in your workspace). This contains the values of \(X\) (poll_result
) simulated from each of 1,000 possible values of \(p\) between 0 to 1 (p_grid
).
This exercise is part of the course
Bayesian Modeling with RJAGS
Exercise instructions
The ggplot()
here constructs the distribution of \(p\) from which each possible outcome of \(X\) was generated. Modify this code, supplying a fill
condition in order to highlight the distribution which corresponds to your observed poll_result
, \(X=6\). This provides insight into which values of \(p\) are the most compatible with your observed poll data!
Note: do not wrap this condition in parentheses ()
.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Density plots of p_grid grouped by poll_result
ggplot(likelihood_sim, aes(x = p_grid, y = poll_result, group = poll_result, fill = ___)) +
geom_density_ridges()