Uncertainty Quantification for Unobserved Variables in Dynamical Systems and Optimal Experimental Design

Abstract

Dynamical systems are frequently used to model biological systems. When these models are fit to data it is necessary to ascertain the uncertainty in the model fit. In our work, we present prediction deviation, a metric of uncertainty that determines the extent to which observed data have constrained the model's predictions. This is accomplished by solving an optimization problem that searches for a pair of models that each provide a good fit for the observed data, yet have maximally different predictions. We developed a method for estimating a priori the impact that additional experiments would have on the prediction deviation, allowing the experimenter to design a set of experiments that would most reduce uncertainty. We used prediction deviation to assess uncertainty in a model of interferon-alpha inhibition of HIV infection, and to select a sequence of experiments that reduces this uncertainty. Finally we proved a theoretical result which shows that prediction deviation provides bounds on the trajectories of the underlying true model. These results show that prediction deviation is a meaningful metric of uncertainty that can be used for optimal experimental design. (Joint work with Ben Letham, Portia Letham, and Edward P. Browne)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 27, 2017
Accession Number
AD1064351

Entities

People

  • Cynthia Rudin

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Abstracts
  • Agreements
  • Contractors
  • Department Of Defense
  • Differential Equations
  • Education
  • Engineering
  • Experimental Design
  • Hiv Infections
  • Information Operations
  • Mathematics
  • Military Research
  • Standards
  • Students
  • Systems Biology
  • Technology Transfer
  • Uncertainty

Fields of Study

  • Computer science

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Computational Modeling and Simulation
  • Regression Analysis.