When used on a PSA object, this function uses a polynomial regression metamodel to predict the
average outcome of a decision-analytic model as a function of a single input parameter.
When used on a DSA object, this function uses the DSA results directly to show how the selected outcome varies
as a function of the input parameter of interest. In the DSA context, this function is called
internally by run_owsa_det and should not be called by the user. In the PSA context,
the user must use this function to produce an owsa object.
owsa(
sa_obj,
params = NULL,
ranges = NULL,
nsamp = 100,
outcome = c("eff", "cost", "nhb", "nmb", "nhb_loss", "nmb_loss"),
wtp = NULL,
strategies = NULL,
poly.order = 2
)An object of class data.frame and owsa with the results of the sensitivity analysis.
Can be visualized with plot.owsa, owsa_tornado, and owsa_opt_strat
sensitivity analysis object;
either a probabilistic sensitivity analysis (make_psa_obj) or
a deterministic sensitivity analysis object (run_owsa_det)
string vector with the name(s) of the parameter of interest. Defaults to all.
a named list of the form c("param" = c(0, 1), ...)
that gives the ranges for the parameter of interest. If NULL,
parameter values from the middle 95
from this range is determined by nsamp.
number of samples to take from the ranges
either effectiveness ("eff"), cost ("cost"), net health benefit ("nhb"), net monetary benefit ("nmb"), or the opportunity loss in terms of NHB or NMB ("nhb_loss" and "nmb_loss", respectively). "nmb_loss_voi" and "nhb_loss_voi" are only used in internal function calls of metamodel within other VOI functions.
if outcome is NHB or NMB (or the associated loss), must provide the willingness-to-pay threshold
vector of strategies to consider. The default (NULL) is that all strategies are considered.
order of polynomial for the linear regression metamodel. Default: 2