Granger Causality for Time-Series Anomaly Detection By Zhangzhou.

Slides:



Advertisements
Similar presentations
Maintaining Arc Consistency We have a constraint graph G of variables X 1,...X n, and constraint relations {X i  X j}, and each Xi has a value set V (X.
Advertisements

Uncertainty Representation. Gaussian Distribution variance Standard deviation.
Becoming Acquainted With Statistical Concepts CHAPTER CHAPTER 12.
Analysis of variance (ANOVA)-the General Linear Model (GLM)
 Once you know the correlation coefficient for your sample, you might want to determine whether this correlation occurred by chance.  Or does the relationship.
A Framework for Discovering Anomalous Regimes in Multivariate Time-Series Data with Local Models Stephen Bay Stanford University, and Institute for the.
Stat 301 – Day 15 Comparing Groups. Statistical Inference Making statements about the “world” based on observing a sample of data, with an indication.
Sample size computations Petter Mostad
T T Population Sampling Distribution Purpose Allows the analyst to determine the mean and standard deviation of a sampling distribution.
Chapter 3 Normal Curve, Probability, and Population Versus Sample Part 2.
Temporal Causal Modeling with Graphical Granger Methods
T T07-01 Sample Size Effect – Normal Distribution Purpose Allows the analyst to analyze the effect that sample size has on a sampling distribution.
11-3 Contingency Tables In this section we consider contingency tables (or two-way frequency tables), which include frequency counts for categorical data.
Slide 1 Detecting Outliers Outliers are cases that have an atypical score either for a single variable (univariate outliers) or for a combination of variables.
ETM 607 – Random Number and Random Variates
Aaker, Kumar, Day Ninth Edition Instructor’s Presentation Slides
Overview of Statistical Hypothesis Testing: The z-Test
Jump to first page HYPOTHESIS TESTING The use of sample data to make a decision either to accept or to reject a statement about a parameter value or about.
Means Tests Hypothesis Testing Assumptions Testing (Normality)
Copyright © 2010, 2007, 2004 Pearson Education, Inc Lecture Slides Elementary Statistics Eleventh Edition and the Triola Statistics Series by.
Introduction to Statistical Inference Probability & Statistics April 2014.
Statistical Decision Making. Almost all problems in statistics can be formulated as a problem of making a decision. That is given some data observed from.
Chapter P.4 Review Group E. Solving Equations Algebraically and Graphically When solving equations identify these points: - Conditional: Sometimes true,
Notes Over 6.7 Finding the Number of Solutions or Zeros
Basic Data Analysis Chapter 14. Overview  Descriptive Analysis.
Slide Copyright © 2008 Pearson Education, Inc. Chapter 11 Inferences for Population Proportions.
Usman Roshan Machine Learning, CS 698
Section Copyright © 2014, 2012, 2010 Pearson Education, Inc. Lecture Slides Elementary Statistics Twelfth Edition and the Triola Statistics Series.
Testing Hypothesis That Data Fit a Given Probability Distribution Problem: We have a sample of size n. Determine if the data fits a probability distribution.
Chapter 9 Introduction to the t Statistic. 9.1 Review Hypothesis Testing with z-Scores Sample mean (M) estimates (& approximates) population mean (μ)
Experimental Design Experimental Designs An Overview.
Chapter 14 – 1 Chapter 14: Analysis of Variance Understanding Analysis of Variance The Structure of Hypothesis Testing with ANOVA Decomposition of SST.
Academic Research Academic Research Dr Kishor Bhanushali M
LECTURE 5 HYPOTHESIS TESTING EPSY 640 Texas A&M University.
Section Copyright © 2014, 2012, 2010 Pearson Education, Inc. Lecture Slides Elementary Statistics Twelfth Edition and the Triola Statistics Series.
Logic and Vocabulary of Hypothesis Tests Chapter 13.
Appendix B: Statistical Methods. Statistical Methods: Graphing Data Frequency distribution Histogram Frequency polygon.
Psy 230 Jeopardy Related Samples t-test ANOVA shorthand ANOVA concepts Post hoc testsSurprise $100 $200$200 $300 $500 $400 $300 $400 $300 $400 $500 $400.
I271B QUANTITATIVE METHODS Regression and Diagnostics.
Ch8.2 Ch8.2 Population Mean Test Case I: A Normal Population With Known Null hypothesis: Test statistic value: Alternative Hypothesis Rejection Region.
Section Copyright © 2014, 2012, 2010 Pearson Education, Inc. Lecture Slides Elementary Statistics Twelfth Edition and the Triola Statistics Series.
Spectrum Sensing In Cognitive Radio Networks
4 In our case, the starting point should be the model with all the lagged variables. DYNAMIC MODEL SPECIFICATION General model with lagged variables Static.
September 28, 2000 Improved Simultaneous Data Reconciliation, Bias Detection and Identification Using Mixed Integer Optimization Methods Presented by:
Basic statistical concepts and techniques Mean and variance Probability distribution, and statistical significance Harmonic analysis and power spectrum.
Byron Gangnes Econ 427 lecture 18 slides Multivariate Modeling (cntd)
Copyright © 2010, 2007, 2004 Pearson Education, Inc Lecture Slides Elementary Statistics Eleventh Edition and the Triola Statistics Series by.
Chapter 3 Normal Curve, Probability, and Population Versus Sample Part 2 Aug. 28, 2014.
24 Nov 2007Data Management and Exploratory Data Analysis 1 Exploratory Data Analysis Exploratory Data Analysis (EDA) is an Approach that Employs a Variety.
Multivariate statistical methods. Multivariate methods multivariate dataset – group of n objects, m variables (as a rule n>m, if possible). confirmation.
Chapter 11: Categorical Data n Chi-square goodness of fit test allows us to examine a single distribution of a categorical variable in a population. n.
Chapter 22 Inferential Data Analysis: Part 2 PowerPoint presentation developed by: Jennifer L. Bellamy & Sarah E. Bledsoe.
Statistical Decision Making. Almost all problems in statistics can be formulated as a problem of making a decision. That is given some data observed from.
Financial Econometrics Lecture Notes 4
Dynamic Models, Autocorrelation and Forecasting
Effective Connectivity: Basics
CSE 4705 Artificial Intelligence
APPROACHES TO QUANTITATIVE DATA ANALYSIS
CHAPTER 16 ECONOMIC FORECASTING Damodar Gujarati
CHAPTER 22: Inference about a Population Proportion
Section 4.7 Forming Functions from Verbal Descriptions
Chapter 9: Hypothesis Tests Based on a Single Sample
A graphing calculator is required for some problems or parts of problems 2000.
AP STATISTICS LESSON 10 – 2 (DAY 3)
Power and Sample Size I HAVE THE POWER!!! Boulder 2006 Benjamin Neale.
C19: Unbiased Estimators
Introduction to the t Test
C19: Unbiased Estimators
Inference Concepts 1-Sample Z-Tests.
Hypothesis Testing for the mean. The general procedure.
Presentation transcript:

Granger Causality for Time-Series Anomaly Detection By Zhangzhou

Introduction&Background Time-Series Data Conception & Examples & Features

Time-Series Model Static model Y t = β 0 + β z t + μ t Finite Distributed Lag model,FDL gfr t = α 0 + ξ 0 pe t + ξ 1 pe t-1 + ξ 2 pe t-2 + μ t

Multivariate time series Vector Auto-Regression(VAR)

Granger Causality For a VAR(p)

Problem Definition There usually exist two types of anomalies in multivariate time-series data : “univariate anomaly” and “dependency anomaly” Solution : investigate Granger graphical models,which uncover the temporal dependencies between variables

The Lasso Granger Method λ is the penalty parameter, the Xi Granger causers Xj if at least one value in βis nonzero by statistical significant tests.

Granger Graphical Models for Anomaly Detection

Detection of dependency anomaly(GGM) Learning temporal causal graph of D(b) by regularization Computing the anomaly scores of D(b) using KL-divergence Determining anomaly by threshold cutoff

Learning temporal causal graphs Null hypothesis : the temporal causal graphs of reference set and test set are the same, we can use the temporal graphs as additional constraint in Lasso-Granger algorithm

Procedure Lasso-Granger(X,T)

Computing anomaly scores Kullback-Leibler(KL) divergence, for a particular time-series Xi, we can define its anomaly score as follows:

Determine anomaly by threshold cutoff and Slide a window through the reference data and calculate the anomaly scores for each window. Then use the scores to approximate the distribution of the anomaly scores and use the α-quantile of this distribution as threshold cutoff.

Experiments