Prior_lambda: Prior distribution on the incidence rate in the treated group
Description
Density, distribution function (see Details) and random generation for the prior distribution on
the rate in the treated group. The prior distribution on the incidence rate $\lambda$ is not to
be set by the user: it is induced by the user-specified prior on $\mu$
and $\phi$.
Usage
dprior_lambda(lambda, a, b, c, d, S, T)
rprior_lambda(n, a, b, c, d, S, T)
pprior_lambda(q, a, b, c, d, S, T, ...)
sprior_lambda(a, b, c, d, S, T, ...)
Arguments
lambda,q
vector of quantiles
a,b
non-negative shape and rate parameter of the Gamma prior distribution on $\mu$
c,d
non-negative shape parameters of the prior distribution on $\phi$
S,T
sample sizes in control group and treated group
n
number of observations to be simulated
...
other arguments passed to genhypergeo through pGB2,
such as series=FALSE to use the continued fraction expansion,
or passed to summary_GB2 (for sprior_lambda)
Value
dprior_lambda gives the density, pprior_lambda the distribution function
(see Details), rprior_lambda samples from the distribution, and
rprior_lambda gives a summary of the distribution.
Details
The pdf of the prior distribution on the incidence rate $\lambda$ involves
the Kummer confluent hypergeometric function of the second kind.
The cdf involves the generalized hypergeometric function. Its current implementation
does not work when a-c is an integer.