Abstract #300542

This is the preliminary program for the 2003 Joint Statistical Meetings in San Francisco, California. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 2-5, 2003); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2003 Program page
JSM 2003 Abstract #300542
Activity Number: 465
Type: Topic Contributed
Date/Time: Thursday, August 7, 2003 : 10:30 AM to 12:20 PM
Sponsor: Section on Bayesian Stat. Sciences
Abstract - #300542
Title: Stochastic Deconvolution of Neuroendocrine Hormone Rhythms
Author(s): David P. Nguyen*+ and Christopher H. Schmid and Gail Adler and Elizabeth Klerman and Emery N. Brown
Companies: Massachusetts Institute of Technology and New England Medical Center and Brigham and Women's Hospital and Brigham and Women's Hospital and Massachusetts General Hospital
Address: Dept. of Brain & Cognitive Sciences, Cambridge, MA, 02142-1017,
Keywords: MCMC ; reversible jump ; point process ; cortisol ; neuroendocrine ; hormone
Abstract:

Neuroendocrine hormones regulate vital processes in the body. Many of these hormones are released in a pulsatile manner throughout the course of the day. Given a set of plasma concentration measurements for a particular hormone, a challenging data analysis problem is to resolve the dynamical properties of the hormone, determine the daily number of secretory events, and deconvolve the secretory events to obtain the hormone production signal. We model the pulsatile hormone activity using a linear stochastic differential equation with point process input. We use a hybrid MCMC algorithm to estimate the model parameters. The hallmark of our hybrid MCMC algorithm is a reversible-jump MCMC sampler that allows us to estimate the number of events in the production signal in the same process that estimates the event times, event amplitudes, and rate parameters. In the analysis of simulated cortisol data, the algorithm correctly estimated the number secretory events and estimated the model parameters with minimal error. In the analysis of real cortisol and growth hormone data, our algorithm produced traces very similar to the actual data without overfitting.

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2003 program

JSM 2003 For information, contact meetings@amstat.org or phone (703) 684-1221. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2003