VOI Consulting is a big proponent of applying probabilistic forecasting techniques such as Monte Carlo analysis (MCA) to pharmaceutical industry decision making. In the last year alone we’ve used MCA to evaluate pipeline opportunities, find an optimal price for a new drug with multiple segments and price sensitivities, develop a wholesale bidding strategy for a generic manufacturer, establish the likelihood of competitors reaching market by certain dates, select clinical trial sites, and determine distributions of Medicare DRG payments based on hospital and patient characteristics.
Unfortunately, probabilistic forecasting is not nearly as widely known (or used) as it should be. Most likely the name implies a headache-inducing level math that most busy pharmaceutical executives simply don’t want to tackle. It’s actually much easier than that mainly because we are only asking clients to be intelligent consumers of the analytical results and this requires little more than the ability to understand a probability distribution chart or statements like “there’s an 85% chance of generating positive ROI on this marketing initiative.” It’s so much easier than people expect and so much more powerful than standard spreadsheet modeling that after reviewing the results of a Monte Carlo analysis on a recent pipeline licensing opportunity, one of our C-level clients stated, “I wish someone had explained this approach to me 20 years ago.”
With this in mind, we’re always glad to see Monte Carlo analysis promoted for pharmaceutical industry applications. One such instance is a webinar from Palisade Software, the makers of the @Risk suite of probabilistic modeling tools who recently hosted “Using @RISK in Evaluating Full (late stage) Compound Development in the Pharmaceutical Industry” by Venkat Raman of VR Advisors LLC. An archived version is available here.