|
Activity Number:
|
335
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 8, 2006 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
| Abstract - #306937 |
|
Title:
|
Analysis of Panic-Relevant Experimental Tidal Volume Curves: Wavelet-Based Functional Hypothesis Testing
|
|
Author(s):
|
Sang Han Lee*+ and Marina Vannucci and Eva Petkova and Maurice Preter and Donald Klein
|
|
Companies:
|
Texas A&M University and Texas A&M University and Columbia University and Columbia University and Columbia University
|
|
Address:
|
3143 TAMU, College Station, TX, 77843,
|
|
Keywords:
|
wavelets ; functional ANOVA ; one-degree of freedom test ; permutation test
|
|
Abstract:
|
We present results from statistical analysis designed for high-frequency tidal volume traces measured during an induced panic model. The hypothesis of the study is that impairing normal subjects' endogenous opioidergic system by naloxone makes them vulnerable to the respiratory effect of subsequent lactate paralleling the known effect of lactate specific to patient with panic disorder. The goal is testing if an opioidergin dysfunction may be the pathophysiological mechanism underlying panic disorder. We propose a functional hypothesis testing procedure to determine the significance of two curves with order restriction. One-degree of freedom test statistics summarizes the pointwise difference over the whole time lag. We use permutation to estimate the distribution of the test statistics concluding that there is a lactate effect which manifests itself as a steady tidal volume increase.
|
