NTRS - NASA Technical Reports Server

Back to Results
Bootstrap Prediction Intervals in Non-Parametric Regression with Applications to Anomaly DetectionPrediction intervals provide a measure of the probable interval in which the outputs of a regression model can be expected to occur. Subsequently, these prediction intervals can be used to determine if the observed output is anomalous or not, conditioned on the input. In this paper, a procedure for determining prediction intervals for outputs of nonparametric regression models using bootstrap methods is proposed. Bootstrap methods allow for a non-parametric approach to computing prediction intervals with no specific assumptions about the sampling distribution of the noise or the data. The asymptotic fidelity of the proposed prediction intervals is theoretically proved. Subsequently, the validity of the bootstrap based prediction intervals is illustrated via simulations. Finally, the bootstrap prediction intervals are applied to the problem of anomaly detection on aviation data.
Document ID
Document Type
Conference Paper
Kumar, Sricharan (Stinger Ghaffarian Technologies, Inc. (SGT, Inc.) Moffett Field, CA, United States)
Srivistava, Ashok N. (NASA Ames Research Center Moffett Field, CA, United States)
Date Acquired
August 27, 2013
Publication Date
August 12, 2012
Subject Category
Mathematical and Computer Sciences (General)
Report/Patent Number
Meeting Information
The 18th ACM SIGKDD Conference on Knowledge Discovery and Data Mining(Beijing)
Funding Number(s)
Distribution Limits
Public Use Permitted.

Available Downloads

NameType 20130014367.pdf STI