Multi-option CEAC for option j

Counts the simulations in which option j has the highest net monetary benefit among all included options at threshold lambda, and divides the count by the number of simulations. Each option's net monetary benefit in a draw is lambda times its simulated effect minus its simulated cost. With mutually exclusive options and consistent tie handling, the values for all options sum to 1 at each threshold. Because no option can exceed the maximum, the indicator 1(NMB_ij >= NMBmax_i) equals 1 exactly when option j attains the highest net monetary benefit in draw i.

Signature

CEAC_j = (1/N) * sum_(i=1)^N [1(NMB_ij >= NMBmax_i)]
Inputs
InputsDefinitionUnit
NNumber of probabilistic simulations in which every option is evaluatedcount
NMB_ijSimulated health effect of option j valued at lambda minus its simulated cost in simulation i, listed across all simulationscurrency per person
NMBmax_iLargest net monetary benefit among all included options in simulation i, listed across all simulationscurrency per person
Output
CEAC_jProportion of simulations in which option j has the highest net monetary benefit at threshold lambdaprobability from 0 to 1

Function

Cost-effectiveness acceptability function

Maps the simulated costs and health effects of mutually exclusive options from a probabilistic sensitivity analysis, together with a threshold, to the probability that each option has the highest net monetary benefit at that threshold. Evaluated across a range of thresholds, it traces the cost-effectiveness acceptability curve.

Try this function

Implementations

  • Excel

    Share of draws won by one option

    With each option's net monetary benefit in adjacent columns B to D, one row per simulation, a helper column RowMax holds =MAX(B2:D2) filled down. The formula then returns the share of rows in which the option in the named range OptionNMB equals the row maximum.

    =SUMPRODUCT(--(OptionNMB=RowMax))/ROWS(OptionNMB)

Assumptions

  • Every option evaluated in the same simulations

    All options are run with the same parameter draw in each simulation, so NMBmax_i compares options under the same state of the world and the correlation between their net benefits is preserved.

  • Complete set of options

    The probabilities depend on every option included. Adding or removing an option can change every CEAC value, so all probabilities are recalculated whenever the set of options changes.

Worked examples

  • Two options with the most frequent winner not preferred

    At one stated threshold, option A has net monetary benefits of £10,000, £12,000, £9,000, £11,000 and £8,000 in five illustrative simulations, and option B has £10,200, £12,300, £9,100, £11,400 and £3,000. A has the highest value only in the fifth draw, so its CEAC is 0.2 and B's is 0.8. The figures match the article's worked example.

    N = 5; NMB_ij = [10000,12000,9000,11000,8000]; NMBmax_i = [10200,12300,9100,11400,8000]; CEAC_j = 0.2

Common errors

  • Building a multi-option curve from pairwise comparisons

    Comparing each option separately with one common baseline and plotting the pairwise probabilities gives values that can sum to more than 1 and do not answer which option is best. Each draw is credited to the single option with the highest net monetary benefit.

Sources

  • CEACs for several interventions

    Fenwick E, Claxton K, Sculpher M. Representing uncertainty: the role of cost-effectiveness acceptability curves. Health Economics. 2001;10(8):779-787.

    View source →

  • CEACs, the frontier and EVPI with multiple options

    Barton GR, Briggs AH, Fenwick EA. Optimal cost-effectiveness decisions: the role of the cost-effectiveness acceptability curve (CEAC), the cost-effectiveness acceptability frontier (CEAF), and the expected value of perfection information (EVPI). Value in Health. 2008;11(5):886-897.

    View source →

Canonical Identity

Stable URI · Machine-readable · Resolvable · CC BY 4.0

Multi-option CEAC for option j | HealthEconomics.wiki