Limitations to classic deterministic sensitivity analysis (DSA) methodologies may result in wrong conclusions regarding the effect of uncertainties in individual parameters on cost-effectiveness model outcomes.

Developments in DSA methodologies include stepwise DSA, distributional DSA based on parameter probability density functions and probabilistic DSA.

Probabilistic DSA provides the most accurate insight into marginal and non-linear effects, likelihood of outcomes and correlation between parameters. In some cases distributional DSA can be sufficient for decision making.

Decision makers must determine to which extent they will accept and implement these improved DSA methodologies and adjust guidelines accordingly.