Here are summaries of my recent research projects, which hopefully produce the following impression:
Modeling and analysis for innovative project portfolio management
You be the judge. You are an expert and know the field best. If an idea piques your interest, kindly contact me. Your concerns, thoughts, and ideas are the most important ones.
- Clinical trials: forecasted and achieved error rates: Do trials achieve the false-positive and false-negative rates they are sized to produce? Historical data suggests a disturbing answer: no. Using a technique from data analytics, you can measure trials' false-positive and false-negative rates, plus other key metrics, for clinical trials by phase and for therapeutic areas, small v. large molecules, NMEs v. nonNMEs, and other key categories.
- The optimizer's curse: overvaluing compounds and portfolios: Even when using unbiased data, project selection creates an optimistic bias that overestimates portfolio value and thus perpetually disappoints executives. Persistent underperformance is the optimizer's curse, and it affects all selection methods, including portfolio optimization and simulation optimization. Bayes' law can mitigate the damage.
- Multiple indications: estimating probabilities: To sequence the trials of compounds with multiple indications, decision analysis provides powerful tools for maximizing value, including decision trees, spreadsheet models, and Monte Carlo analysis. However, these techniques require conditional probabilities that describe the correlated results of trials. Here is a rigorous method of estimating these probabilities.
- Portfolio size, return and risk: almost stochastic dominance: So long as projects meet a minimum expected payoff, adding projects to a portfolio always improves a portfolio's risk and return characteristics in a manner called almost stochastic dominance. Partnering with other companies so you can have more compounds in your portfolio, exploits this property to produce greater returns with less risk.
- Clinical trials: risk management: If developed appropriately, common methods of managing risk, such as red-yellow-green scales, risk matrices, and scoring models identify some important risks but miss many others. Decision analysis offers more powerful tools for identifying, assessing, and managing risks, including framing (identifying facts, assumptions, hypotheses to test, risks, decisions, and alternatives) and analysis (decision trees, tornado diagrams, Monte Carlo analysis, the value of information, and the annealing of plans).
Fuzzy front-end analysis (nonpharma): How do you fill product development with high-value, big winner projects? The equation is:
Good Choices + Good Choosing = Profitable Projects
With new analytic techniques, you can estimate the quality of your project proposals (choices) and your project evaluations and selection (choosing). These new KPIs for the front-end of product development can identify your organization's strengths, find opportunities for improvement, and improve your ability to fill product development with high-value projects.