saddlepoint: Saddlepoint Approximation

In TobiasMadsen/ncdDetect2:

Description

Let X_1,X_2,… X_N be independent Bernouilli trials with X_i \sim p_i. We evaluate the probability

P(s_1X_1+s_2X_2… s_NX_N > t)

.

Usage

saddlepoint(t, dat, lattice = 1L, log = T)

Arguments

t	Point where tail probability is evaluated (note this function is not vectorized over t)
dat	A data.table with columns 'x', 'y', and 'probabilities'. Column 'x' is a numeric indicator unique for each random variable to be convoluted together. Column 'y' is the outcome value, and colum 'probabilities' contains the probability corresponding to each value of the 'y' column.
lattice	Lattice size in minimal lattice
log	Return log probability

Examples

saddlepoint(51, dat = data.table(x = rep(1:10000, each = 2),
                                 y = rep(c(1,0),10000),
                                 probability = rep(c(0.01,0.99), 100)))
pbinom(299, 10000, 0.01, lower.tail = F, log.p = T)

TobiasMadsen/ncdDetect2 documentation built on May 14, 2019, 11:11 a.m.