Skip to contents

Package overview

dampack dampack-package
dampack: Decision-Analytic Modeling Package

Cost-effectiveness analysis and ICERs

Identify dominated and extendedly dominated strategies, compute incremental cost-effectiveness ratios (ICERs), and plot the cost-effectiveness frontier.

calculate_icers()
Calculate incremental cost-effectiveness ratios (ICERs)
calculate_icers_psa()
Calculate incremental cost-effectiveness ratios from a psa object.
print(<icers>)
Print the formatted CEA table
plot(<icers>)
Plot of ICERs

Probabilistic sensitivity analysis (PSA) objects

Build a psa object from the costs, effects, and parameter draws of any decision model, summarize it, and plot it on the cost-effectiveness plane.

make_psa_obj()
Create a PSA object
summary(<psa>)
summarize a psa object across all simulations
plot(<psa>)
Plot the psa object
print(<sa>)
print a psa object

Cost-effectiveness acceptability curves and expected loss

ceac()
Cost-Effectiveness Acceptability Curve (CEAC)
plot(<ceac>)
Plot of Cost-Effectiveness Acceptability Curves (CEAC)
summary(<ceac>)
Summarize a ceac
calc_exp_loss()
Calculate the expected loss at a range of willingness-to-pay thresholds
plot(<exp_loss>)
Plot of Expected Loss Curves (ELC)

Value of information

Expected value of perfect information (EVPI), of partial perfect information (EVPPI), and of sample information (EVSI).

calc_evpi()
Expected Value of Perfect Information (EVPI)
plot(<evpi>)
Plot of Expected Value of Perfect Information (EVPI)
calc_evppi()
Estimation of the Expected Value of Partial Perfect Information (EVPPI) using a linear regression metamodel approach
plot(<evppi>)
Plot of Expected Value of Partial Perfect Information (EVPPI)
calc_evsi()
Calculate Expected Value of Sample Information (EVSI)
plot(<evsi>)
Plot of Expected Value of Sample Information (EVSI)

Metamodeling

metamodel()
Linear regression metamodeling
predict(<metamodel>)
Predict from a one-way or two-way metamodel
print(<metamodel>)
Print metamodel
summary(<metamodel>)
Summary of metamodel

Deterministic sensitivity analysis

One-way and two-way sensitivity analyses, either run directly on a decision model or derived from a PSA through metamodeling.

run_owsa_det()
Run deterministic one-way sensitivity analysis (OWSA)
run_twsa_det()
Run deterministic two-way sensitivity analysis (TWSA)
create_dsa_oneway()
Create one-way deterministic sensitivity analysis object
create_dsa_twoway()
Create one-way deterministic sensitivity analysis object
owsa()
One-way sensitivity analysis
plot(<owsa>)
Plot a sensitivity analysis
owsa_tornado()
Tornado plot of a one-way sensitivity analysis
owsa_opt_strat()
plot the optimal strategy as the parameter values change
twsa()
Two-way sensitivity analysis using linear regression metamodeling
plot(<twsa>)
Two-way sensitivity analysis plot

Generating PSA samples and running a model

gen_psa_samp()
Generate PSA Sample
run_psa()
Calculate outcomes for a PSA using a user-defined function.
beta_params()
Calculate alpha and beta parameters of beta distribution.
gamma_params()
Calculate shape and scale (or rate) parameters of a gamma distribution.
lnorm_params()
Calculate location and scale parameters of a log-normal distribution.
dirichlet_params()
Calculate alpha parameters of Dirichlet distribution.
rdirichlet()
Random number generation for the Dirichlet distribution with parameter vector alpha.

Plotting helpers

number_ticks()
Number of ticks for ggplot2 plots

Example datasets

cancer_psa_data
PSA output from a model of three cancer treatments
df_example_psa_elc
Six-strategy PSA sample with a multiply-switching frontier
psa_cdiff
Sample PSA dataset
hund_strat
Simulated costs and QALYs for 100 strategies