Time Series Modelling and Kalman Filters
|
|
- Christian Campbell
- 7 years ago
- Views:
Transcription
1 1 / 24 Time Series Modelling and Kalman Filters Chris Williams School of Informatics, University of Edinburgh November 2010
2 2 / 24 Outline Stochastic processes AR, MA and ARMA models The Fourier view Parameter estimation for ARMA models Linear-Gaussian HMMs (Kalman filtering) Reading: Handout on Time Series Modelling: AR, MA, ARMA and All That Reading: Bishop 13.3 (but not , )
3 3 / 24 Example time series FTSE 100 Meteorology: temperature, pressure... Seismology Electrocardiogram (ECG)...
4 Stochastic Processes A stochastic process is a family of random variables X(t), t T indexed by a parameter t in an index set T We will consider discrete-time stochastic processes where T = Z (the integers) A time series is said to be strictly stationary if the joint distribution of X(t 1 ),..., X(t n ) is the same as the joint distribution of X(t 1 + τ),..., X(t n + τ) for all t 1,..., t n, τ A time series is said to be weakly stationary if its mean is constant and its autocovariance function depends only on the lag, i.e. E[X(t)] = µ Cov[X(t)X(t + τ)] = γ(τ) A Gaussian process is a family of random variables, any finite number of which have a joint Gaussian distribution The ARMA models we will study are stationary Gaussian processes t 4 / 24
5 Autoregressive (AR) Models 5 / 24 Example AR(1) where w t N(0, σ 2 ) x t = αx t 1 + w t By repeated substitution we get x t = w t + αw t 1 + α 2 w t Hence E[X(t)] = 0, and if α < 1 the process is stationary with Similarly Var[X(t)] = (1 + α 2 + α )σ 2 = σ2 1 α 2 Cov[X(t)X(t k)] = α k Var[X(t k)] = αk σ 2 1 α 2
6 α = / 24 α = 0.5
7 7 / 24 The general case is an AR(p) process x t = p α i x t i + w t i=1 Notice how x t is obtainied by a (linear) regression from x t 1,..., x t p, hence an autoregressive process Introduce the backward shift operator B, so that Bx t = x t 1, B 2 x t = x t 2 etc Then AR(p) model can be written as φ(b)x t = w t where φ(b) = (1 α 1 B... α p B p ) The condition for stationarity is that all the roots of φ(b) lie outside the unit circle
8 Yule-Walker Equations x t = x t x t k = p α i x t i + w t i=1 p α i x t i x t k + w t x t k i=1 Taking expectations (and exploiting stationarity) we obtain γ k = p α i γ k i k = 1,, 2,... i=1 Use p simultaneous equations to obtain the γ s from the α s. For inference, can solve a linear system to obtain the α s given estimates of the γ s Example: AR(1) process, γ k = α k γ 0 8 / 24
9 9 / 24 Graphical model illustrating an AR(2) process AR2: α 1 = 0.2, α 2 = 0.1 AR2: α 1 = 1.0, α 2 = 0.5
10 Vector AR processes 10 / 24 x t = p A i x t i + Gw t i=1 where the A i s and G are square matrices We can in general consider modelling multivariate (as opposed to univariate) time series An AR(2) process can be written as a vector AR(1) process: ( ) ( ) ( ) ( ) ( xt α1 α = 2 xt wt x t 1 x t 2 w t 1 ) In general an AR(p) process can be written as a vector AR(1) process with a p-dimensional state vector (cf ODEs)
11 11 / 24 Moving Average (MA) processes x t = q β j w t j j=0 (linear filter) = θ(b)w t with scaling so that β 0 = 1 and θ(b) = 1 + q j=1 β jb j Example: MA(1) process w s x s
12 12 / 24 We have E[X(t)] = 0, and Var[X(t)] = (1 + β β2 q)σ 2 Cov[X(t)X(t k)] = E[ = { q β j w t j, j=0 q β i w t k i ] i=0 Note that covariance cuts off for k > q σ 2 q k j=0 β j+kβ j for k = 0, 1,..., q 0 for k > q
13 13 / 24 ARMA(p,q) processes x t = p q α i x t i + β j w t j i=1 j=0 φ(b)x t = θ(b)w t Writing an AR(p) process as a MA( ) process φ(b)x t = w t x t = (1 α 1 B... α p B p ) 1 w t = (1 + β 1 B + β 2 B 2...)w t Similarly a MA(q) process can be written as a AR( ) process Utility of ARMA(p,q) is potential parsimony
14 14 / 24 The Fourier View ARMA models are linear time-invariant systems. Hence sinusoids are their eigenfunctions (Fourier analysis) This means it is natural to consider the power spectrum of the ARMA process. The power spectrum S(k) can be determined from the {α}, {β} coefficients Roughly speaking S(k) is the amount of power allocated on average to the eigenfunction e 2πikt This is a useful way to understand some properties of ARMA processes, but we will not pursue it further here If you want to know more, see e.g. Chatfield (1989) chapter 7 or Diggle (1990) chapter 4
15 15 / 24 Parameter Estimation Let the vector of observations x = (x(t 1 ),..., x(t n )) T Estimate and subtract constant offset ˆµ if this is non zero ARMA models driven by Gaussian noise are Gaussian processes. Thus the likelihood L(x; α, β) is a multivariate Gaussian, and we can optimize this wrt the parameters (e.g. by gradient ascent) AR(p) models, x t = p α i x t i + w t i=1 can be viewed as the linear regression of x t on the p previous time steps, α and σ 2 can be estimated using linear regression This viewpoint also enables the fitting of nonlinear AR models
16 16 / 24 Model Order Selection, References For a MA(q) process there should be a cut-off in the autocorrelation function for lags greater than q For general ARMA models this is model order selection problem, discussed in an upcoming lecture Some useful books: The Analysis of Time Series: An Introduction. C. Chatfield, Chapman and Hall, 4th edition, 1989 Time Series: A Biostatistical Introduction. P. J. Diggle, Clarendon Press, 1990
17 17 / 24 Linear-Gaussian HMMs HMM with continuous state-space and observations Filtering problem known as Kalman filtering
18 18 / 24 z 1 z2 z3 z N A A.. C C C C x x x x N Dynamical model z n+1 = Az n + w n+1 where w n+1 N(0, Γ) is Gaussian noise, i.e. p(z n+1 z n ) N(Az n, Γ)
19 19 / 24 Observation model x n = Cz n + v n where v n N(0, Σ) is Gaussian noise, i.e. p(x n z n ) N(Cz n, Σ) Initialization p(z 1 ) N(µ 0, V 0 )
20 Inference Problem filtering 20 / 24 As whole model is Gaussian, only need to compute means and variances p(z n x 1,..., x n ) N(µ n, V n ) µ n = E[z n x 1,..., x n ] V n = E[(z n µ n )(z n µ n ) T x 1,..., x n ] Recursive update split into two parts Time update p(z n x 1,..., x n ) p(z n+1 x 1,..., x n ) Measurement update p(z n+1 x 1,..., x n ) p(z n+1 x 1,..., x n, x n+1 )
21 21 / 24 Time update z n+1 = Az n + w n+1 thus E[z n+1 x 1,... x n ] = Aµ n cov(z n+1 x 1,... x n ) def = P n = AV n A T + Γ Measurement update (like posterior in Factor Analysis) µ n+1 = Aµ n + K n+1 (x n+1 CAµ n ) V n+1 = (I K n+1 C)P n where K n+1 = P n C T (CP n C T + Σ) 1 K n+1 is known as the Kalman gain matrix
22 Simple example 22 / 24 w n N(0, 1) v n N(0, 1) In the limit σ 2 we find z n+1 = z n + w n+1 x n = z n + v n p(z 1 ) N(0, σ 2 ) µ 3 = 5x 3 + 2x 2 + x 1 8 Notice how later data has more weight Compare z n+1 = z n (so that w n has zero variance); then µ 3 = x 3 + x 2 + x 1 3
23 23 / 24 Applications Much as a coffee filter serves to keep undesirable grounds out of your morning mug, the Kalman filter is designed to strip unwanted noise out of a stream of data. Barry Cipra, SIAM News 26(5) 1993 Navigational and guidance systems Radar tracking Sonar ranging Satellite orbit determination
24 24 / 24 Extensions Dealing with non-linearity The Extended Kalman Filter (EKF) If x n = f (z n ) + v n where f is a non-linear function, can linearize f, e.g. around E[z n x 1,... x n 1 ]. Works for weak non-linearities For very non-linear problems use sampling methods (known as particle filters). Example, work of Blake and Isard on tracking, see vdg/dynamics.html It is possible to train KFs using a forward-backward algorithm
Univariate and Multivariate Methods PEARSON. Addison Wesley
Time Series Analysis Univariate and Multivariate Methods SECOND EDITION William W. S. Wei Department of Statistics The Fox School of Business and Management Temple University PEARSON Addison Wesley Boston
More informationIntroduction to Time Series Analysis. Lecture 6.
Introduction to Time Series Analysis. Lecture 6. Peter Bartlett www.stat.berkeley.edu/ bartlett/courses/153-fall2010 Last lecture: 1. Causality 2. Invertibility 3. AR(p) models 4. ARMA(p,q) models 1 Introduction
More informationLecture 2: ARMA(p,q) models (part 3)
Lecture 2: ARMA(p,q) models (part 3) Florian Pelgrin University of Lausanne, École des HEC Department of mathematics (IMEA-Nice) Sept. 2011 - Jan. 2012 Florian Pelgrin (HEC) Univariate time series Sept.
More information1 Short Introduction to Time Series
ECONOMICS 7344, Spring 202 Bent E. Sørensen January 24, 202 Short Introduction to Time Series A time series is a collection of stochastic variables x,.., x t,.., x T indexed by an integer value t. The
More informationDiscrete Time Series Analysis with ARMA Models
Discrete Time Series Analysis with ARMA Models Veronica Sitsofe Ahiati (veronica@aims.ac.za) African Institute for Mathematical Sciences (AIMS) Supervised by Tina Marquardt Munich University of Technology,
More informationSome useful concepts in univariate time series analysis
Some useful concepts in univariate time series analysis Autoregressive moving average models Autocorrelation functions Model Estimation Diagnostic measure Model selection Forecasting Assumptions: 1. Non-seasonal
More informationSales forecasting # 2
Sales forecasting # 2 Arthur Charpentier arthur.charpentier@univ-rennes1.fr 1 Agenda Qualitative and quantitative methods, a very general introduction Series decomposition Short versus long term forecasting
More informationTime Series Analysis
Time Series Analysis Autoregressive, MA and ARMA processes Andrés M. Alonso Carolina García-Martos Universidad Carlos III de Madrid Universidad Politécnica de Madrid June July, 212 Alonso and García-Martos
More informationUnivariate Time Series Analysis; ARIMA Models
Econometrics 2 Spring 25 Univariate Time Series Analysis; ARIMA Models Heino Bohn Nielsen of4 Outline of the Lecture () Introduction to univariate time series analysis. (2) Stationarity. (3) Characterizing
More information11. Time series and dynamic linear models
11. Time series and dynamic linear models Objective To introduce the Bayesian approach to the modeling and forecasting of time series. Recommended reading West, M. and Harrison, J. (1997). models, (2 nd
More informationAdvanced Signal Processing and Digital Noise Reduction
Advanced Signal Processing and Digital Noise Reduction Saeed V. Vaseghi Queen's University of Belfast UK WILEY HTEUBNER A Partnership between John Wiley & Sons and B. G. Teubner Publishers Chichester New
More informationTime Series Analysis 1. Lecture 8: Time Series Analysis. Time Series Analysis MIT 18.S096. Dr. Kempthorne. Fall 2013 MIT 18.S096
Lecture 8: Time Series Analysis MIT 18.S096 Dr. Kempthorne Fall 2013 MIT 18.S096 Time Series Analysis 1 Outline Time Series Analysis 1 Time Series Analysis MIT 18.S096 Time Series Analysis 2 A stochastic
More informationEstimating an ARMA Process
Statistics 910, #12 1 Overview Estimating an ARMA Process 1. Main ideas 2. Fitting autoregressions 3. Fitting with moving average components 4. Standard errors 5. Examples 6. Appendix: Simple estimators
More informationUnderstanding and Applying Kalman Filtering
Understanding and Applying Kalman Filtering Lindsay Kleeman Department of Electrical and Computer Systems Engineering Monash University, Clayton 1 Introduction Objectives: 1. Provide a basic understanding
More informationUnivariate Time Series Analysis; ARIMA Models
Econometrics 2 Fall 25 Univariate Time Series Analysis; ARIMA Models Heino Bohn Nielsen of4 Univariate Time Series Analysis We consider a single time series, y,y 2,..., y T. We want to construct simple
More informationTime Series Analysis III
Lecture 12: Time Series Analysis III MIT 18.S096 Dr. Kempthorne Fall 2013 MIT 18.S096 Time Series Analysis III 1 Outline Time Series Analysis III 1 Time Series Analysis III MIT 18.S096 Time Series Analysis
More informationAnalysis and Computation for Finance Time Series - An Introduction
ECMM703 Analysis and Computation for Finance Time Series - An Introduction Alejandra González Harrison 161 Email: mag208@exeter.ac.uk Time Series - An Introduction A time series is a sequence of observations
More informationTrend and Seasonal Components
Chapter 2 Trend and Seasonal Components If the plot of a TS reveals an increase of the seasonal and noise fluctuations with the level of the process then some transformation may be necessary before doing
More informationTime Series Analysis of Aviation Data
Time Series Analysis of Aviation Data Dr. Richard Xie February, 2012 What is a Time Series A time series is a sequence of observations in chorological order, such as Daily closing price of stock MSFT in
More informationIntroduction to Kalman Filtering
Introduction to Kalman Filtering A set of two lectures Maria Isabel Ribeiro Associate Professor Instituto Superior écnico / Instituto de Sistemas e Robótica June All rights reserved INRODUCION O KALMAN
More informationITSM-R Reference Manual
ITSM-R Reference Manual George Weigt June 5, 2015 1 Contents 1 Introduction 3 1.1 Time series analysis in a nutshell............................... 3 1.2 White Noise Variance.....................................
More informationState Space Time Series Analysis
State Space Time Series Analysis p. 1 State Space Time Series Analysis Siem Jan Koopman http://staff.feweb.vu.nl/koopman Department of Econometrics VU University Amsterdam Tinbergen Institute 2011 State
More informationAR(p) + MA(q) = ARMA(p, q)
AR(p) + MA(q) = ARMA(p, q) Outline 1 3.4: ARMA(p, q) Model 2 Homework 3a Arthur Berg AR(p) + MA(q) = ARMA(p, q) 2/ 12 ARMA(p, q) Model Definition (ARMA(p, q) Model) A time series is ARMA(p, q) if it is
More informationLecture 4: Seasonal Time Series, Trend Analysis & Component Model Bus 41910, Time Series Analysis, Mr. R. Tsay
Lecture 4: Seasonal Time Series, Trend Analysis & Component Model Bus 41910, Time Series Analysis, Mr. R. Tsay Business cycle plays an important role in economics. In time series analysis, business cycle
More informationTime Series Analysis in Economics. Klaus Neusser
Time Series Analysis in Economics Klaus Neusser May 26, 2015 Contents I Univariate Time Series Analysis 3 1 Introduction 1 1.1 Some examples.......................... 2 1.2 Formal definitions.........................
More informationTime Series - ARIMA Models. Instructor: G. William Schwert
APS 425 Fall 25 Time Series : ARIMA Models Instructor: G. William Schwert 585-275-247 schwert@schwert.ssb.rochester.edu Topics Typical time series plot Pattern recognition in auto and partial autocorrelations
More informationLinear Threshold Units
Linear Threshold Units w x hx (... w n x n w We assume that each feature x j and each weight w j is a real number (we will relax this later) We will study three different algorithms for learning linear
More informationTime Series Analysis
Time Series Analysis Forecasting with ARIMA models Andrés M. Alonso Carolina García-Martos Universidad Carlos III de Madrid Universidad Politécnica de Madrid June July, 2012 Alonso and García-Martos (UC3M-UPM)
More informationStatistics and Probability Letters
Statistics and Probability Letters 79 (2009) 1884 1889 Contents lists available at ScienceDirect Statistics and Probability Letters journal homepage: www.elsevier.com/locate/stapro Discrete-valued ARMA
More informationLecture 8: Signal Detection and Noise Assumption
ECE 83 Fall Statistical Signal Processing instructor: R. Nowak, scribe: Feng Ju Lecture 8: Signal Detection and Noise Assumption Signal Detection : X = W H : X = S + W where W N(, σ I n n and S = [s, s,...,
More informationStatistics Graduate Courses
Statistics Graduate Courses STAT 7002--Topics in Statistics-Biological/Physical/Mathematics (cr.arr.).organized study of selected topics. Subjects and earnable credit may vary from semester to semester.
More informationTime Series Analysis
JUNE 2012 Time Series Analysis CONTENT A time series is a chronological sequence of observations on a particular variable. Usually the observations are taken at regular intervals (days, months, years),
More informationTime Series Analysis
Time Series Analysis hm@imm.dtu.dk Informatics and Mathematical Modelling Technical University of Denmark DK-2800 Kgs. Lyngby 1 Outline of the lecture Identification of univariate time series models, cont.:
More informationProbability and Random Variables. Generation of random variables (r.v.)
Probability and Random Variables Method for generating random variables with a specified probability distribution function. Gaussian And Markov Processes Characterization of Stationary Random Process Linearly
More informationCCNY. BME I5100: Biomedical Signal Processing. Linear Discrimination. Lucas C. Parra Biomedical Engineering Department City College of New York
BME I5100: Biomedical Signal Processing Linear Discrimination Lucas C. Parra Biomedical Engineering Department CCNY 1 Schedule Week 1: Introduction Linear, stationary, normal - the stuff biology is not
More informationGraphical Tools for Exploring and Analyzing Data From ARIMA Time Series Models
Graphical Tools for Exploring and Analyzing Data From ARIMA Time Series Models William Q. Meeker Department of Statistics Iowa State University Ames, IA 50011 January 13, 2001 Abstract S-plus is a highly
More informationCS229 Lecture notes. Andrew Ng
CS229 Lecture notes Andrew Ng Part X Factor analysis Whenwehavedatax (i) R n thatcomesfromamixtureofseveral Gaussians, the EM algorithm can be applied to fit a mixture model. In this setting, we usually
More informationTime Series HILARY TERM 2010 PROF. GESINE REINERT http://www.stats.ox.ac.uk/~reinert
Time Series HILARY TERM 2010 PROF. GESINE REINERT http://www.stats.ox.ac.uk/~reinert Overview Chapter 1: What are time series? Types of data, examples, objectives. Definitions, stationarity and autocovariances.
More information3.1 Stationary Processes and Mean Reversion
3. Univariate Time Series Models 3.1 Stationary Processes and Mean Reversion Definition 3.1: A time series y t, t = 1,..., T is called (covariance) stationary if (1) E[y t ] = µ, for all t Cov[y t, y t
More informationEE 570: Location and Navigation
EE 570: Location and Navigation On-Line Bayesian Tracking Aly El-Osery 1 Stephen Bruder 2 1 Electrical Engineering Department, New Mexico Tech Socorro, New Mexico, USA 2 Electrical and Computer Engineering
More informationMaster s thesis tutorial: part III
for the Autonomous Compliant Research group Tinne De Laet, Wilm Decré, Diederik Verscheure Katholieke Universiteit Leuven, Department of Mechanical Engineering, PMA Division 30 oktober 2006 Outline General
More informationIntroduction to General and Generalized Linear Models
Introduction to General and Generalized Linear Models General Linear Models - part I Henrik Madsen Poul Thyregod Informatics and Mathematical Modelling Technical University of Denmark DK-2800 Kgs. Lyngby
More informationQUALITY ENGINEERING PROGRAM
QUALITY ENGINEERING PROGRAM Production engineering deals with the practical engineering problems that occur in manufacturing planning, manufacturing processes and in the integration of the facilities and
More informationTIME SERIES ANALYSIS
TIME SERIES ANALYSIS L.M. BHAR AND V.K.SHARMA Indian Agricultural Statistics Research Institute Library Avenue, New Delhi-0 02 lmb@iasri.res.in. Introduction Time series (TS) data refers to observations
More informationForecasting model of electricity demand in the Nordic countries. Tone Pedersen
Forecasting model of electricity demand in the Nordic countries Tone Pedersen 3/19/2014 Abstract A model implemented in order to describe the electricity demand on hourly basis for the Nordic countries.
More informationTime Series Analysis
Time Series Analysis Andrea Beccarini Center for Quantitative Economics Winter 2013/2014 Andrea Beccarini (CQE) Time Series Analysis Winter 2013/2014 1 / 143 Introduction Objectives Time series are ubiquitous
More informationTime Series Analysis
Time Series 1 April 9, 2013 Time Series Analysis This chapter presents an introduction to the branch of statistics known as time series analysis. Often the data we collect in environmental studies is collected
More informationVector Time Series Model Representations and Analysis with XploRe
0-1 Vector Time Series Model Representations and Analysis with plore Julius Mungo CASE - Center for Applied Statistics and Economics Humboldt-Universität zu Berlin mungo@wiwi.hu-berlin.de plore MulTi Motivation
More informationSTA 4273H: Statistical Machine Learning
STA 4273H: Statistical Machine Learning Russ Salakhutdinov Department of Statistics! rsalakhu@utstat.toronto.edu! http://www.cs.toronto.edu/~rsalakhu/ Lecture 6 Three Approaches to Classification Construct
More informationTHE SVM APPROACH FOR BOX JENKINS MODELS
REVSTAT Statistical Journal Volume 7, Number 1, April 2009, 23 36 THE SVM APPROACH FOR BOX JENKINS MODELS Authors: Saeid Amiri Dep. of Energy and Technology, Swedish Univ. of Agriculture Sciences, P.O.Box
More informationAutocovariance and Autocorrelation
Chapter 3 Autocovariance and Autocorrelation If the {X n } process is weakly stationary, the covariance of X n and X n+k depends only on the lag k. This leads to the following definition of the autocovariance
More informationForecasting Geographic Data Michael Leonard and Renee Samy, SAS Institute Inc. Cary, NC, USA
Forecasting Geographic Data Michael Leonard and Renee Samy, SAS Institute Inc. Cary, NC, USA Abstract Virtually all businesses collect and use data that are associated with geographic locations, whether
More informationSoftware Review: ITSM 2000 Professional Version 6.0.
Lee, J. & Strazicich, M.C. (2002). Software Review: ITSM 2000 Professional Version 6.0. International Journal of Forecasting, 18(3): 455-459 (June 2002). Published by Elsevier (ISSN: 0169-2070). http://0-
More informationNAG C Library Chapter Introduction. g13 Time Series Analysis
g13 Time Series Analysis Introduction g13 NAG C Library Chapter Introduction g13 Time Series Analysis Contents 1 Scope of the Chapter... 3 2 Background to the Problems... 3 2.1 Univariate Analysis... 3
More informationLinear regression methods for large n and streaming data
Linear regression methods for large n and streaming data Large n and small or moderate p is a fairly simple problem. The sufficient statistic for β in OLS (and ridge) is: The concept of sufficiency is
More informationThe SAS Time Series Forecasting System
The SAS Time Series Forecasting System An Overview for Public Health Researchers Charles DiMaggio, PhD College of Physicians and Surgeons Departments of Anesthesiology and Epidemiology Columbia University
More informationLuciano Rispoli Department of Economics, Mathematics and Statistics Birkbeck College (University of London)
Luciano Rispoli Department of Economics, Mathematics and Statistics Birkbeck College (University of London) 1 Forecasting: definition Forecasting is the process of making statements about events whose
More information2x + y = 3. Since the second equation is precisely the same as the first equation, it is enough to find x and y satisfying the system
1. Systems of linear equations We are interested in the solutions to systems of linear equations. A linear equation is of the form 3x 5y + 2z + w = 3. The key thing is that we don t multiply the variables
More informationAnalysis of algorithms of time series analysis for forecasting sales
SAINT-PETERSBURG STATE UNIVERSITY Mathematics & Mechanics Faculty Chair of Analytical Information Systems Garipov Emil Analysis of algorithms of time series analysis for forecasting sales Course Work Scientific
More informationTime Series Analysis and Forecasting Methods for Temporal Mining of Interlinked Documents
Time Series Analysis and Forecasting Methods for Temporal Mining of Interlinked Documents Prasanna Desikan and Jaideep Srivastava Department of Computer Science University of Minnesota. @cs.umn.edu
More informationA FULLY INTEGRATED ENVIRONMENT FOR TIME-DEPENDENT DATA ANALYSIS
A FULLY INTEGRATED ENVIRONMENT FOR TIME-DEPENDENT DATA ANALYSIS Version 1.4 July 2007 First edition Intended for use with Mathematica 6 or higher Software and manual: Yu He, John Novak, Darren Glosemeyer
More informationTraffic Safety Facts. Research Note. Time Series Analysis and Forecast of Crash Fatalities during Six Holiday Periods Cejun Liu* and Chou-Lin Chen
Traffic Safety Facts Research Note March 2004 DOT HS 809 718 Time Series Analysis and Forecast of Crash Fatalities during Six Holiday Periods Cejun Liu* and Chou-Lin Chen Summary This research note uses
More informationDiscrete Frobenius-Perron Tracking
Discrete Frobenius-Perron Tracing Barend J. van Wy and Michaël A. van Wy French South-African Technical Institute in Electronics at the Tshwane University of Technology Staatsartillerie Road, Pretoria,
More informationPart 4 fitting with energy loss and multiple scattering non gaussian uncertainties outliers
Part 4 fitting with energy loss and multiple scattering non gaussian uncertainties outliers material intersections to treat material effects in track fit, locate material 'intersections' along particle
More informationFinancial TIme Series Analysis: Part II
Department of Mathematics and Statistics, University of Vaasa, Finland January 29 February 13, 2015 Feb 14, 2015 1 Univariate linear stochastic models: further topics Unobserved component model Signal
More informationAdaptive Demand-Forecasting Approach based on Principal Components Time-series an application of data-mining technique to detection of market movement
Adaptive Demand-Forecasting Approach based on Principal Components Time-series an application of data-mining technique to detection of market movement Toshio Sugihara Abstract In this study, an adaptive
More informationTIME SERIES ANALYSIS: AN OVERVIEW
Outline TIME SERIES ANALYSIS: AN OVERVIEW Hernando Ombao University of California at Irvine November 26, 2012 Outline OUTLINE OF TALK 1 TIME SERIES DATA 2 OVERVIEW OF TIME DOMAIN ANALYSIS 3 OVERVIEW SPECTRAL
More informationAPPLICATION OF THE VARMA MODEL FOR SALES FORECAST: CASE OF URMIA GRAY CEMENT FACTORY
APPLICATION OF THE VARMA MODEL FOR SALES FORECAST: CASE OF URMIA GRAY CEMENT FACTORY DOI: 10.2478/tjeb-2014-0005 Ramin Bashir KHODAPARASTI 1 Samad MOSLEHI 2 To forecast sales as reliably as possible is
More informationIntroduction to Mobile Robotics Bayes Filter Particle Filter and Monte Carlo Localization
Introduction to Mobile Robotics Bayes Filter Particle Filter and Monte Carlo Localization Wolfram Burgard, Maren Bennewitz, Diego Tipaldi, Luciano Spinello 1 Motivation Recall: Discrete filter Discretize
More informationMultivariate Normal Distribution
Multivariate Normal Distribution Lecture 4 July 21, 2011 Advanced Multivariate Statistical Methods ICPSR Summer Session #2 Lecture #4-7/21/2011 Slide 1 of 41 Last Time Matrices and vectors Eigenvalues
More informationPerforming Unit Root Tests in EViews. Unit Root Testing
Página 1 de 12 Unit Root Testing The theory behind ARMA estimation is based on stationary time series. A series is said to be (weakly or covariance) stationary if the mean and autocovariances of the series
More informationOverview of Violations of the Basic Assumptions in the Classical Normal Linear Regression Model
Overview of Violations of the Basic Assumptions in the Classical Normal Linear Regression Model 1 September 004 A. Introduction and assumptions The classical normal linear regression model can be written
More informationForecasting the US Dollar / Euro Exchange rate Using ARMA Models
Forecasting the US Dollar / Euro Exchange rate Using ARMA Models LIUWEI (9906360) - 1 - ABSTRACT...3 1. INTRODUCTION...4 2. DATA ANALYSIS...5 2.1 Stationary estimation...5 2.2 Dickey-Fuller Test...6 3.
More informationStudying Achievement
Journal of Business and Economics, ISSN 2155-7950, USA November 2014, Volume 5, No. 11, pp. 2052-2056 DOI: 10.15341/jbe(2155-7950)/11.05.2014/009 Academic Star Publishing Company, 2014 http://www.academicstar.us
More informationRob J Hyndman. Forecasting using. 11. Dynamic regression OTexts.com/fpp/9/1/ Forecasting using R 1
Rob J Hyndman Forecasting using 11. Dynamic regression OTexts.com/fpp/9/1/ Forecasting using R 1 Outline 1 Regression with ARIMA errors 2 Example: Japanese cars 3 Using Fourier terms for seasonality 4
More informationSystems of Linear Equations
Systems of Linear Equations Beifang Chen Systems of linear equations Linear systems A linear equation in variables x, x,, x n is an equation of the form a x + a x + + a n x n = b, where a, a,, a n and
More informationMaximum likelihood estimation of mean reverting processes
Maximum likelihood estimation of mean reverting processes José Carlos García Franco Onward, Inc. jcpollo@onwardinc.com Abstract Mean reverting processes are frequently used models in real options. For
More informationDo Electricity Prices Reflect Economic Fundamentals?: Evidence from the California ISO
Do Electricity Prices Reflect Economic Fundamentals?: Evidence from the California ISO Kevin F. Forbes and Ernest M. Zampelli Department of Business and Economics The Center for the Study of Energy and
More informationPrediction of Stock Price usingautoregressiveintegrated Moving AverageFilter Arima P,D,Q
Global Journal of Science Frontier Research Mathematics and Decision Sciences Volume 13 Issue 8 Version 1.0 Year Type : Double Blind Peer Reviewed International Research Journal Publisher: Global Journals
More informationPart 2: Analysis of Relationship Between Two Variables
Part 2: Analysis of Relationship Between Two Variables Linear Regression Linear correlation Significance Tests Multiple regression Linear Regression Y = a X + b Dependent Variable Independent Variable
More informationChapter 5. Analysis of Multiple Time Series. 5.1 Vector Autoregressions
Chapter 5 Analysis of Multiple Time Series Note: The primary references for these notes are chapters 5 and 6 in Enders (2004). An alternative, but more technical treatment can be found in chapters 10-11
More informationImpulse Response Functions
Impulse Response Functions Wouter J. Den Haan University of Amsterdam April 28, 2011 General definition IRFs The IRF gives the j th -period response when the system is shocked by a one-standard-deviation
More informationTime Series Analysis and Forecasting
Time Series Analysis and Forecasting Math 667 Al Nosedal Department of Mathematics Indiana University of Pennsylvania Time Series Analysis and Forecasting p. 1/11 Introduction Many decision-making applications
More informationIntroduction to Time Series Analysis. Lecture 1.
Introduction to Time Series Analysis. Lecture 1. Peter Bartlett 1. Organizational issues. 2. Objectives of time series analysis. Examples. 3. Overview of the course. 4. Time series models. 5. Time series
More informationSolving Systems of Linear Equations Using Matrices
Solving Systems of Linear Equations Using Matrices What is a Matrix? A matrix is a compact grid or array of numbers. It can be created from a system of equations and used to solve the system of equations.
More informationSystem Identification for Acoustic Comms.:
System Identification for Acoustic Comms.: New Insights and Approaches for Tracking Sparse and Rapidly Fluctuating Channels Weichang Li and James Preisig Woods Hole Oceanographic Institution The demodulation
More informationChapter 1. Vector autoregressions. 1.1 VARs and the identi cation problem
Chapter Vector autoregressions We begin by taking a look at the data of macroeconomics. A way to summarize the dynamics of macroeconomic data is to make use of vector autoregressions. VAR models have become
More informationContinued Fractions and the Euclidean Algorithm
Continued Fractions and the Euclidean Algorithm Lecture notes prepared for MATH 326, Spring 997 Department of Mathematics and Statistics University at Albany William F Hammond Table of Contents Introduction
More informationThe Engle-Granger representation theorem
The Engle-Granger representation theorem Reference note to lecture 10 in ECON 5101/9101, Time Series Econometrics Ragnar Nymoen March 29 2011 1 Introduction The Granger-Engle representation theorem is
More informationStatistical Machine Learning
Statistical Machine Learning UoC Stats 37700, Winter quarter Lecture 4: classical linear and quadratic discriminants. 1 / 25 Linear separation For two classes in R d : simple idea: separate the classes
More informationADVANCED FORECASTING MODELS USING SAS SOFTWARE
ADVANCED FORECASTING MODELS USING SAS SOFTWARE Girish Kumar Jha IARI, Pusa, New Delhi 110 012 gjha_eco@iari.res.in 1. Transfer Function Model Univariate ARIMA models are useful for analysis and forecasting
More information9th Russian Summer School in Information Retrieval Big Data Analytics with R
9th Russian Summer School in Information Retrieval Big Data Analytics with R Introduction to Time Series with R A. Karakitsiou A. Migdalas Industrial Logistics, ETS Institute Luleå University of Technology
More informationTime Series Analysis by Higher Order Crossings. Benjamin Kedem Department of Mathematics & ISR University of Maryland College Park, MD
Time Series Analysis by Higher Order Crossings Benjamin Kedem Department of Mathematics & ISR University of Maryland College Park, MD 1 Stochastic Process A stochastic or random process {Z t },, 1,0,1,,
More informationPATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 4: LINEAR MODELS FOR CLASSIFICATION
PATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 4: LINEAR MODELS FOR CLASSIFICATION Introduction In the previous chapter, we explored a class of regression models having particularly simple analytical
More informationDeterministic Sampling-based Switching Kalman Filtering for Vehicle Tracking
Proceedings of the IEEE ITSC 2006 2006 IEEE Intelligent Transportation Systems Conference Toronto, Canada, September 17-20, 2006 WA4.1 Deterministic Sampling-based Switching Kalman Filtering for Vehicle
More informationARMA, GARCH and Related Option Pricing Method
ARMA, GARCH and Related Option Pricing Method Author: Yiyang Yang Advisor: Pr. Xiaolin Li, Pr. Zari Rachev Department of Applied Mathematics and Statistics State University of New York at Stony Brook September
More informationAdvanced Forecasting Techniques and Models: ARIMA
Advanced Forecasting Techniques and Models: ARIMA Short Examples Series using Risk Simulator For more information please visit: www.realoptionsvaluation.com or contact us at: admin@realoptionsvaluation.com
More informationChapter 6: Multivariate Cointegration Analysis
Chapter 6: Multivariate Cointegration Analysis 1 Contents: Lehrstuhl für Department Empirische of Wirtschaftsforschung Empirical Research and und Econometrics Ökonometrie VI. Multivariate Cointegration
More informationChapter 9: Univariate Time Series Analysis
Chapter 9: Univariate Time Series Analysis In the last chapter we discussed models with only lags of explanatory variables. These can be misleading if: 1. The dependent variable Y t depends on lags of
More informationLeast Squares Estimation
Least Squares Estimation SARA A VAN DE GEER Volume 2, pp 1041 1045 in Encyclopedia of Statistics in Behavioral Science ISBN-13: 978-0-470-86080-9 ISBN-10: 0-470-86080-4 Editors Brian S Everitt & David
More information