cpo {BGPhazard}

Conditional Predictive Ordinate (CPO) Statistic

Description

Makes the CPO Plot and calculates the logarithm of the Pseudomarginal likelihood (LPML).

Usage

cpo(res)

Arguments

res

tibble. The output from the *Res functions, where * could either be BeM, GaM, CGaM, CuM, CCuM

Details

Computes de CPO as a goodness of fit measure

Value

LPML

The value of the logarithm of the Pseudomarginal likelihood

plot

CPO Plot

References

See Geisser (1993); Gelfand, Dey, and Chang (1992); Dey, Chen, and Chang (1997); and Sinha and Dey (1997)

Examples

## Example 1
#  data(gehan)
#  timesG <- gehan$time[gehan$treat == "6-MP"]
#  deltaG <- gehan$cens[gehan$treat == "6-MP"]
#  GEX1 <- GaMRes(timesG, deltaG, K = 8, iterations = 3000)
#  cpo(GEX1)