Need for speed: an efficient algorithm for calculation of single-parameter expected value of partial perfect information

Authors: Sadatsafavi M, Bansback N, Zafari Z, Najafzadeh M, Marra C

The Expected Value of Partial Perfect Information (EVPPI) is a theoretically justifiable and informative measure of uncertainty in decision-analytic cost-effectiveness models, but its calculation is computationally intensive as it generally requires two-level Monte Carlo simulation. We introduce an efficient, one-level simulation method for calculation of single-parameter EVPPI. We show that under mild regularity assumptions, the expectation-maximization-expectation sequence in EVPPI calculation can be transformed into an expectation-maximization-maximization sequence. By doing so, calculations can be performed in a single-step expectation using data generated for probabilistic sensitivity analysis (PSA). The new method, though only applicable to single-parameter EVPPI, is fast, accurate, and easy to implement. Further research is needed to evaluate the performance of this method in more complex scenarios and to extend such a concept to similar measures of decision uncertainty.

Status: completed (Link to MEDLINE record)

Published article

Link to published article

Online EVPPI calculator

– The R function

The Excel Add-in as a stand-alone file (you will need to bring your PSA data into this file)

The Excel macro as add-in (to be embedded with your excel file containing PSA results)
Note: The excel add-in comes with an experimental p-value calculation method for each segmentation point. This feature is not part of the manuscript and hence its use is not recommended.

Code in JAVA (Thanks to David Stefan from UCL)


Keywords: EVPPI, EVPI, Excel