DISTÀNCIES, LEVERAGE I OUTLIERS EN L ANÀLISI MULTIVARIANT

Size: px
Start display at page:

Download "DISTÀNCIES, LEVERAGE I OUTLIERS EN L ANÀLISI MULTIVARIANT"

Transcription

1 DISTÀNCIES, LEVERAGE I OUTLIERS EN L ANÀLISI MULTIVARIANT Anàlisi Multivariant, UPF, Tardor del 2012

2 1 Distància d ts entre dos punts, matriu D de distàncies 2

3 Distància entre punts distancia entre dos punts ordenades A (0.4, 0.4) C (0.6, 0.35) B (0.8, 0.7) abcisses

4 Distància Euclidiana Punts A i B de coordenades (x A 1,..., xa p ) i (x B 1,..., xb p ) p d AB = (xj A xj B)2 j=1 Donada una matriu de dades X(n p) podem considerar la matriu D(n n) amb elements d ts corresponents a la distància entre les files t i s.

5 Exemple: distància Euclídia, funció R: dist data=read.table(" satorra/dades/commaa.dat", header=t) X = as.matrix(data[, -1]) n= dim(x)[1] D = matrix(0,n,n) for (i in 1:n) { for (j in 1:n) { D[i,j] = sqrt(sum((x[i,]-x[j,])ˆ2))} } rownames(d)= data[,1] colnames(d)= data[,1] > D[1:4, 1:4] Andal Catal Madri Valen Andal Catal Madri Valen ### la funcio dist: D = as.matrix(dist(x, diag=t, upper=t)) rownames(d)= data[,1] colnames(d)= data[,1] D[1:5, 1:5] Andal Catal Madri Valen Casle Andal Catal Madri Valen Casle

6 Exemple: distància Minkowski, Manhattan (Eixample) D = dist(dadesr, method="minkowski", 1,diag=T, upper=t) D > D = dist(dadesr, method="manhattan",diag=t, upper=t) > D >

7 Tipus de Distàncies Objectes A : x A = (x A 1,..., xa p ), B : x B = (x B 1,..., xb p ) p 1 Euclídia d AB = j=1 (xa j xj B)2 = (x A x B ) (x A x B ) ( p ) 1/r 2 Minkowski d AB = j=1 xa j xj A r 3 Mahalanobis d AB = (x A x B ) S 1 (x A x B ), S la matriu de variàncies i covariàncies de les dades. És distància Euclídia de les dades transformades X = XS 1/2

8 Computing S 1/2 Since S 1/2 = (S 1/2 ) 1, the problem could be translated to computing S 1/2. Take ( ) 4 1 S = 1 4 Is S 1/2 = ( The answer is a resounding no, since ( ) ( ) ( We need the spectral representation of S as S = VΛV, V V = I 2 and Λ a diagonal matrix. It is easy to see that S α = VVΛ α V, the power α applying only to the diagonal elements of Λ. ) )

9 Computing S 1/2 (cont.) > S =matrix(c(4,1,1,4),2,2) > S [,1] [,2] [1,] 4 1 [2,] 1 4 > lambda= eigen(s)$values > V= eigen(s)$vectors > V%*%diag(lambda)%*%t(V) [,1] [,2] [1,] 4 1 [2,] 1 4 > Sqrt= V%*%diag(sqrt(lambda))%*%t(V) > Sqrt [,1] [,2] [1,] [2,] > Sqrt%*%Sqrt [,1] [,2] [1,] 4 1 [2,] 1 4 > > Sinsqrt= V%*%diag(1/sqrt(lambda))%*%t(V) > Sinsqrt [,1] [,2] [1,] [2,]

10 Exemple: distància Mahalanobis S = cov(x) V = eigen(s)$vectors lambda = eigen(s)$values insqrts = V%*%diag(1/sqrt(lambda)) %*%t(v) # Noteu que S%*% insqrts%*%insqrts la matriu identitad Xs = X%*%insqrtS ## Noteu que round(cov(xs),3) > round(cov(xs),3) [,1] [,2] [,3] [,4] [1,] [2,] [3,] [4,] La distancia de Mahalanobis serà: M= as.matrix(dist(xs, method="minkowski", 2,diag=T, upper=t)) round( M[1:5, 1:5],2)

11 Observacions atípiques multivariants Donada la matriu de dades X, interessa calibrar les observacions a tipiques, aquelles que s allunyen del centre del núvol de punts. Centrem les dades, considerem X c, la norma de Mahalanobis de cada fila és una mesura de la distància al centre de cada punt fila; d 2 i = x is 1 x i = (n 1)x i(x cx c ) 1 x i Els di 2 són els elements de la diagonal de la matriu (n 1)X c (X cx c ) 1 X c {di 2 } n i=1 = diag ( (n 1)X c (X cx c ) 1 X c ) S anomenen els leverage ( apalancaments ) de cada punt fila de X c.

12 funció R: leverage dades = read.table(" satorra/dades/amd1.txt", header=t) X = as.matrix(dades[,2:6]) n = dim(x)[1] Xc = scale(x, scale=f) lev = (n-1)*diag(xc%*%solve(t(xc)%*%xc)%*%t(xc)) plot(1:n, lev, type ="h", axes=t, lty = 2) axis(2) # points(1:n, lev,pch=16, col="red") abline(h=0, col="blue") text(1:n, lev+0.03,1:n, pch=2, col="red") Veure la funció leverage a la web de l assignatura.

13 7 lev :n Figure: Els leverages de les dades de CCAA

Discriminant Analysis

Discriminant Analysis Discriminant Analysis Albert Satorra Multivariate Analysis UPF, Tardor del 2015 Albert Satorra ( Multivariate Analysis UPF, Tardor del 2015 ) AD/E-GRAU Fall 2015 1 / 27 Table of contents 1 Separation among

More information

AMcur(Curs de la tardor 2006): The practic with R fast

AMcur(Curs de la tardor 2006): The practic with R fast AMcur(Curs de la tardor 2006): The practic with R fast Albert Satorra November 27, 2006 Contents 1 Introduction 1 2 Principal Component Analysis 1 2.0.1 Reading the function leverage (file: leverage.txt)..............

More information

k-means clustering mark = which(md == min(md)) nearest[i] = ifelse(mark <= 5, "blue", "orange")}

k-means clustering mark = which(md == min(md)) nearest[i] = ifelse(mark <= 5, blue, orange)} 1 / 16 k-means clustering km15 = kmeans(x[g==0,],5) km25 = kmeans(x[g==1,],5) for(i in 1:6831){ md = c(mydist(xnew[i,],km15$center[1,]),mydist(xnew[i,],km15$center[2, mydist(xnew[i,],km15$center[3,]),mydist(xnew[i,],km15$center[4,]),

More information

Additional Mathematics Lines and circles

Additional Mathematics Lines and circles Additional Mathematics Lines and circles Topic assessment 1 The points A and B have coordinates ( ) and (4 respectively. Calculate (i) The gradient of the line AB [1] The length of the line AB [] (iii)

More information

Simple Linear Regression: Introduction to Diagnostics

Simple Linear Regression: Introduction to Diagnostics Simple Linear Regression: Introduction to Diagnostics Anscombe Data Frame (1.973) A data frame proposed by Anscombe in 1.973 and composed by 4 sets of 11 (x,y) points. All of them provide the same estimates

More information

Nonlinear Models. What do you do when you don t have a line? What do you do when you don t have a line? A Quadratic Adventure

Nonlinear Models. What do you do when you don t have a line? What do you do when you don t have a line? A Quadratic Adventure What do you do when you don t have a line? Nonlinear Models Spores 0e+00 2e+06 4e+06 6e+06 8e+06 30 40 50 60 70 longevity What do you do when you don t have a line? A Quadratic Adventure 1. If nonlinear

More information

A note on inertial motion

A note on inertial motion Atmósfera (24) 183-19 A note on inertial motion A. WIIN-NIELSEN The Collstrop Foundation, H. C. Andersens Blvd. 37, 5th, DK 1553, Copenhagen V, Denmark Received January 13, 23; accepted January 1, 24 RESUMEN

More information

Absolute Value Equations and Inequalities. Use the distance definition of absolute value.

Absolute Value Equations and Inequalities. Use the distance definition of absolute value. Chapter 2 Section 7 2.7 Absolute Value Equations and Inequalities Objectives 1 2 3 4 5 6 Use the distance definition of absolute value. Solve equations of the form ax + b = k, for k > 0. Solve inequalities

More information

Math 2331 Linear Algebra

Math 2331 Linear Algebra 5. Eigenvectors & Eigenvalues Math 233 Linear Algebra 5. Eigenvectors & Eigenvalues Shang-Huan Chiu Department of Mathematics, University of Houston schiu@math.uh.edu math.uh.edu/ schiu/ Shang-Huan Chiu,

More information

5. Random Vectors. probabilities. characteristic function. cross correlation, cross covariance. Gaussian random vectors. functions of random vectors

5. Random Vectors. probabilities. characteristic function. cross correlation, cross covariance. Gaussian random vectors. functions of random vectors EE401 (Semester 1) 5. Random Vectors Jitkomut Songsiri probabilities characteristic function cross correlation, cross covariance Gaussian random vectors functions of random vectors 5-1 Random vectors we

More information

EDAMI DATA ANALYSIS II: TOOLS FOR MULTIVARIATE ANALYSIS

EDAMI DATA ANALYSIS II: TOOLS FOR MULTIVARIATE ANALYSIS EDAMI DATA ANALYSIS II: TOOLS FOR MULTIVARIATE ANALYSIS Mario Romanazzi October 4, 2017 1 Introduction Dependence structures underlie multidimensional data analysis. The reference model is stochastic independence,

More information

Nonstationary time series models

Nonstationary time series models 13 November, 2009 Goals Trends in economic data. Alternative models of time series trends: deterministic trend, and stochastic trend. Comparison of deterministic and stochastic trend models The statistical

More information

STAT 530, HW 1 Example solutions, Fall Problem 1:

STAT 530, HW 1 Example solutions, Fall Problem 1: STAT 530, HW 1 Example solutions, Fall 2018 Problem 1: my.s1

More information

DOCUMENTS DE TREBALL DE LA FACULTAT D ECONOMIA I EMPRESA. Col.lecció d Economia

DOCUMENTS DE TREBALL DE LA FACULTAT D ECONOMIA I EMPRESA. Col.lecció d Economia DOCUMENTS DE TREBALL DE LA FACULTAT D ECONOMIA I EMPRESA Col.lecció d Economia E11/262 The proportional distribution in a cooperative model with external opportunities Camilla Di Luca Università degli

More information

Chapter 4. Multivariate Distributions. Obviously, the marginal distributions may be obtained easily from the joint distribution:

Chapter 4. Multivariate Distributions. Obviously, the marginal distributions may be obtained easily from the joint distribution: 4.1 Bivariate Distributions. Chapter 4. Multivariate Distributions For a pair r.v.s (X,Y ), the Joint CDF is defined as F X,Y (x, y ) = P (X x,y y ). Obviously, the marginal distributions may be obtained

More information

Def. The euclidian distance between two points x = (x 1,...,x p ) t and y = (y 1,...,y p ) t in the p-dimensional space R p is defined as

Def. The euclidian distance between two points x = (x 1,...,x p ) t and y = (y 1,...,y p ) t in the p-dimensional space R p is defined as MAHALANOBIS DISTANCE Def. The euclidian distance between two points x = (x 1,...,x p ) t and y = (y 1,...,y p ) t in the p-dimensional space R p is defined as d E (x, y) = (x 1 y 1 ) 2 + +(x p y p ) 2

More information

Introduction to Regression

Introduction to Regression PSU Summer School in Statistics Regression Slide 1 Introduction to Regression Chad M. Schafer Department of Statistics & Data Science, Carnegie Mellon University cschafer@cmu.edu June 2018 PSU Summer School

More information

Subatomic particle location charge mass

Subatomic particle location charge mass verview of subatomic particles Subatomic particle location charge mass proton (p + ) nucleus 1+ 1 amu (g/mol) Neutron (n 0 ) nucleus 0 1 amu (g/mol) Electron (e - ) Electron could in energy levels 1-0

More information

x. Figure 1: Examples of univariate Gaussian pdfs N (x; µ, σ 2 ).

x. Figure 1: Examples of univariate Gaussian pdfs N (x; µ, σ 2 ). .8.6 µ =, σ = 1 µ = 1, σ = 1 / µ =, σ =.. 3 1 1 3 x Figure 1: Examples of univariate Gaussian pdfs N (x; µ, σ ). The Gaussian distribution Probably the most-important distribution in all of statistics

More information

Física de Partículas Experimental

Física de Partículas Experimental Física de Partículas Experimental 5a clase Luis Manuel Montaño Zetina Departamento de Física Cinvestav Departamento de Física USON Hermosillo Sonora 5-9 agosto 2013 ALICE @ LHC (i) Quarks and gluons in

More information

Part six: Numerical differentiation and numerical integration

Part six: Numerical differentiation and numerical integration Part six: Numerical differentiation and numerical integration Numerical integration formulas. Rectangle rule = = 21.1 Trapezoidal rule = 21.2 Simpson 1/3 = 21.2.3 Simpson 3/8 = =,,,, (21.3) (21.10) (21.15)

More information

Series 5.0 Serie 5.0 CLUTCH-BRAKES SERIES 5.0 FRENO-EMBRAGUES SERIE 5.0

Series 5.0 Serie 5.0 CLUTCH-BRAKES SERIES 5.0 FRENO-EMBRAGUES SERIE 5.0 F R E N O E M B R A G U E S N E U M Á T I C O S CLUTCHBRAKES SERIES.0 FRENOEMBRAGUES SERIE.0 Series.0 is the latest version of our traditional design of clutchbrakes assembled by pins that tighten both

More information

The F distribution and its relationship to the chi squared and t distributions

The F distribution and its relationship to the chi squared and t distributions The chemometrics column Published online in Wiley Online Library: 3 August 2015 (wileyonlinelibrary.com) DOI: 10.1002/cem.2734 The F distribution and its relationship to the chi squared and t distributions

More information

REVISTA INVESTIGACION OPERACIONAL VOL. 38, NO. 3, , 2017

REVISTA INVESTIGACION OPERACIONAL VOL. 38, NO. 3, , 2017 REVISTA INVESTIGACION OPERACIONAL VOL. 38, NO. 3, 247-251, 2017 LINEAR REGRESSION: AN ALTERNATIVE TO LOGISTIC REGRESSION THROUGH THE NON- PARAMETRIC REGRESSION Ernesto P. Menéndez*, Julia A. Montano**

More information

Regression Analysis. Simple Regression Multivariate Regression Stepwise Regression Replication and Prediction Error EE290H F05

Regression Analysis. Simple Regression Multivariate Regression Stepwise Regression Replication and Prediction Error EE290H F05 Regression Analysis Simple Regression Multivariate Regression Stepwise Regression Replication and Prediction Error 1 Regression Analysis In general, we "fit" a model by minimizing a metric that represents

More information

Atlas de anatomía palpatoria. Tomo 2. Miembro inferior (Spanish Edition)

Atlas de anatomía palpatoria. Tomo 2. Miembro inferior (Spanish Edition) Atlas de anatomía palpatoria. Tomo 2. Miembro inferior (Spanish Edition) Serge Tixa Click here if your download doesn"t start automatically Atlas de anatomía palpatoria. Tomo 2. Miembro inferior (Spanish

More information

STAT 514 Solutions to Assignment #6

STAT 514 Solutions to Assignment #6 STAT 514 Solutions to Assignment #6 Question 1: Suppose that X 1,..., X n are a simple random sample from a Weibull distribution with density function f θ x) = θcx c 1 exp{ θx c }I{x > 0} for some fixed

More information

Matrix exponential. R study group 2010

Matrix exponential. R study group 2010 Matrix exponential R study group 2010 Niels Richard Hansen University of Copenhagen August 11, 2010 The objective is to compute the matrix exponential e X for a square p p matrix efficiently and reliably

More information

Data Mining: Data. Lecture Notes for Chapter 2. Introduction to Data Mining

Data Mining: Data. Lecture Notes for Chapter 2. Introduction to Data Mining Data Mining: Data Lecture Notes for Chapter 2 Introduction to Data Mining by Tan, Steinbach, Kumar Similarity and Dissimilarity Similarity Numerical measure of how alike two data objects are. Is higher

More information

1.3. Principal coordinate analysis. Pierre Legendre Département de sciences biologiques Université de Montréal

1.3. Principal coordinate analysis. Pierre Legendre Département de sciences biologiques Université de Montréal 1.3. Pierre Legendre Département de sciences biologiques Université de Montréal http://www.numericalecology.com/ Pierre Legendre 2018 Definition of principal coordinate analysis (PCoA) An ordination method

More information

Regression diagnostics

Regression diagnostics Regression diagnostics Kerby Shedden Department of Statistics, University of Michigan November 5, 018 1 / 6 Motivation When working with a linear model with design matrix X, the conventional linear model

More information

Linear Regression. Furthermore, it is simple.

Linear Regression. Furthermore, it is simple. Linear Regression While linear regression has limited value in the classification problem, it is often very useful in predicting a numerical response, on a linear or ratio scale. Furthermore, it is simple.

More information

ENGI Parametric Vector Functions Page 5-01

ENGI Parametric Vector Functions Page 5-01 ENGI 3425 5. Parametric Vector Functions Page 5-01 5. Parametric Vector Functions Contents: 5.1 Arc Length (Cartesian parametric and plane polar) 5.2 Surfaces of Revolution 5.3 Area under a Parametric

More information

Linear Models in Statistics

Linear Models in Statistics Linear Models in Statistics ALVIN C. RENCHER Department of Statistics Brigham Young University Provo, Utah A Wiley-Interscience Publication JOHN WILEY & SONS, INC. New York Chichester Weinheim Brisbane

More information

R Library Functions for Multivariate Analysis

R Library Functions for Multivariate Analysis R Library Functions for Multivariate Analysis Psychology 312 Dr. Steiger The R Library Functions are in a file called Steiger R Library Functions.R, which you can download from the course website in the

More information

EDAMI DIMENSION REDUCTION BY PRINCIPAL COMPONENT ANALYSIS

EDAMI DIMENSION REDUCTION BY PRINCIPAL COMPONENT ANALYSIS EDAMI DIMENSION REDUCTION BY PRINCIPAL COMPONENT ANALYSIS Mario Romanazzi October 29, 2017 1 Introduction An important task in multidimensional data analysis is reduction in complexity. Recalling that

More information

TALLER DE ELECTRICIDAD Y MAGNETISMO 9º

TALLER DE ELECTRICIDAD Y MAGNETISMO 9º TALLER DE ELECTRICIDAD Y MAGNETISMO 9º MULTIPLE CHOICE. Choose the one alternative that best completes the statement or answers the question. 1) Compared to the resistance of two resistors connected in

More information

The nearby structure of the Local Arm

The nearby structure of the Local Arm Asociación Argentina de Astronomía BAAA, Vol. 48, 2005 E.M. Arnal, A. Brunini, J.J. Clariá Olmedo, J.C. Forte, D.O. Gómez, D. García Lambas, Z. López García, S. M. Malaroda, & G.E. Romero, eds. COMUNICACIÓN

More information

Multivariate Analysis of Variance

Multivariate Analysis of Variance Chapter 15 Multivariate Analysis of Variance Jolicouer and Mosimann studied the relationship between the size and shape of painted turtles. The table below gives the length, width, and height (all in mm)

More information

EE482: Digital Signal Processing Applications

EE482: Digital Signal Processing Applications Professor Brendan Morris, SEB 3216, brendan.morris@unlv.edu EE482: Digital Signal Processing Applications Spring 2014 TTh 14:30-15:45 CBC C222 Lecture 11 Adaptive Filtering 14/03/04 http://www.ee.unlv.edu/~b1morris/ee482/

More information

Nonlinear Regression. Summary. Sample StatFolio: nonlinear reg.sgp

Nonlinear Regression. Summary. Sample StatFolio: nonlinear reg.sgp Nonlinear Regression Summary... 1 Analysis Summary... 4 Plot of Fitted Model... 6 Response Surface Plots... 7 Analysis Options... 10 Reports... 11 Correlation Matrix... 12 Observed versus Predicted...

More information

Machine Learning. Theory of Classification and Nonparametric Classifier. Lecture 2, January 16, What is theoretically the best classifier

Machine Learning. Theory of Classification and Nonparametric Classifier. Lecture 2, January 16, What is theoretically the best classifier Machine Learning 10-701/15 701/15-781, 781, Spring 2008 Theory of Classification and Nonparametric Classifier Eric Xing Lecture 2, January 16, 2006 Reading: Chap. 2,5 CB and handouts Outline What is theoretically

More information

Stat 8053, Chapter 9, rev March 7, 2014

Stat 8053, Chapter 9, rev March 7, 2014 Stat 8053, Chapter 9, rev March 7, 2014 Principal Components with p = 2 Suppose x is 2 1 with mean µ and covariance matrix Σ. Case I Suppose Σ is in correlation form, Σ(1, ρ) = ( 1 ρ ρ 1 If ρ 0, then the

More information

Examples of fitting various piecewise-continuous functions to data, using basis functions in doing the regressions.

Examples of fitting various piecewise-continuous functions to data, using basis functions in doing the regressions. Examples of fitting various piecewise-continuous functions to data, using basis functions in doing the regressions. David. Boore These examples in this document used R to do the regression. See also Notes_on_piecewise_continuous_regression.doc

More information

Section 9.7 and 9.10: Taylor Polynomials and Approximations/Taylor and Maclaurin Series

Section 9.7 and 9.10: Taylor Polynomials and Approximations/Taylor and Maclaurin Series Section 9.7 and 9.10: Taylor Polynomials and Approximations/Taylor and Maclaurin Series Power Series for Functions We can create a Power Series (or polynomial series) that can approximate a function around

More information

Econ 2148, fall 2017 Gaussian process priors, reproducing kernel Hilbert spaces, and Splines

Econ 2148, fall 2017 Gaussian process priors, reproducing kernel Hilbert spaces, and Splines Econ 2148, fall 2017 Gaussian process priors, reproducing kernel Hilbert spaces, and Splines Maximilian Kasy Department of Economics, Harvard University 1 / 37 Agenda 6 equivalent representations of the

More information

BIOS 2083 Linear Models Abdus S. Wahed. Chapter 2 84

BIOS 2083 Linear Models Abdus S. Wahed. Chapter 2 84 Chapter 2 84 Chapter 3 Random Vectors and Multivariate Normal Distributions 3.1 Random vectors Definition 3.1.1. Random vector. Random vectors are vectors of random variables. For instance, X = X 1 X 2.

More information

6.001 SICP September? Procedural abstraction example: sqrt (define try (lambda (guess x) (if (good-enuf? guess x) guess (try (improve guess x) x))))

6.001 SICP September? Procedural abstraction example: sqrt (define try (lambda (guess x) (if (good-enuf? guess x) guess (try (improve guess x) x)))) September? 600-Introduction Trevor Darrell trevor@csail.mit.edu -D5 6.00 web page: http://sicp.csail.mit.edu/ section web page: http://www.csail.mit.edu/~trevor/600/ Abstractions Pairs and lists Common

More information

Algorithmen zur digitalen Bildverarbeitung I

Algorithmen zur digitalen Bildverarbeitung I ALBERT-LUDWIGS-UNIVERSITÄT FREIBURG INSTITUT FÜR INFORMATIK Lehrstuhl für Mustererkennung und Bildverarbeitung Prof. Dr.-Ing. Hans Burkhardt Georges-Köhler-Allee Geb. 05, Zi 01-09 D-79110 Freiburg Tel.

More information

Eigenvalues and Eigenvectors

Eigenvalues and Eigenvectors /88 Chia-Ping Chen Department of Computer Science and Engineering National Sun Yat-sen University Linear Algebra Eigenvalue Problem /88 Eigenvalue Equation By definition, the eigenvalue equation for matrix

More information

Regression and Statistical Inference

Regression and Statistical Inference Regression and Statistical Inference Walid Mnif wmnif@uwo.ca Department of Applied Mathematics The University of Western Ontario, London, Canada 1 Elements of Probability 2 Elements of Probability CDF&PDF

More information

Sidon sets and C 4 -saturated graphs

Sidon sets and C 4 -saturated graphs Sidon sets and C 4 -saturated graphs arxiv:1810.056v1 [math.co] 11 Oct 018 David F. Daza Carlos A. Trujillo Universidad del Cauca, A.A. 755, Colombia. davidaza@unicauca.edu.co - trujillo@unicauca.edu.co

More information

PRACTICE PAPER -- III

PRACTICE PAPER -- III . PRACTICE PAPER -- III. z + z :::.0, if and only if (a) Re (z) ::: O (b) Im z) = 0 (c) z = 0 (d) none of these 2. zz = 0, if and only if (a) Re(z) = O (b) Im (z) = 0 (c) z = 0 (d) none of these 3. (3

More information

Jacobi s Iterative Method for Solving Linear Equations and the Simulation of Linear CNN

Jacobi s Iterative Method for Solving Linear Equations and the Simulation of Linear CNN Jacobi s Iterative Method for Solving Linear Equations and the Simulation of Linear CNN Vedat Tavsanoglu Yildiz Technical University 9 August 006 1 Paper Outline Raster simulation is an image scanning-processing

More information

Stationary Graph Processes: Nonparametric Spectral Estimation

Stationary Graph Processes: Nonparametric Spectral Estimation Stationary Graph Processes: Nonparametric Spectral Estimation Santiago Segarra, Antonio G. Marques, Geert Leus, and Alejandro Ribeiro Dept. of Signal Theory and Communications King Juan Carlos University

More information

NOTES ON OCT 4, 2012

NOTES ON OCT 4, 2012 NOTES ON OCT 4, 0 MIKE ZABROCKI I had planned a midterm on Oct I can t be there that day I am canceling my office hours that day and I will be available on Tuesday Oct 9 from 4-pm instead I am tempted

More information

Extreme Point Linear Fractional Functional Programming

Extreme Point Linear Fractional Functional Programming Zeitschrift fiir Operations Research, Band 18, 1974, Seite 131-139. Physica-Verlag, Wiirzbur9. Extreme Point Linear Fractional Functional Programming By M. C. Puri 1) and K. Swarup2), India Eingegangen

More information

1. Introduction to Multivariate Analysis

1. Introduction to Multivariate Analysis 1. Introduction to Multivariate Analysis Isabel M. Rodrigues 1 / 44 1.1 Overview of multivariate methods and main objectives. WHY MULTIVARIATE ANALYSIS? Multivariate statistical analysis is concerned with

More information

Factor model shrinkage for linear instrumental variable analysis with many instruments

Factor model shrinkage for linear instrumental variable analysis with many instruments Factor model shrinkage for linear instrumental variable analysis with many instruments P. Richard Hahn Booth School of Business University of Chicago Joint work with Hedibert Lopes 1 My goals for this

More information

Stochastic processes, the Poisson process. Javier Campos Universidad de Zaragoza

Stochastic processes, the Poisson process. Javier Campos Universidad de Zaragoza Stochastic processes, the oisson process Javier Campos Universidad de Zaragoa http://webdiis.uniar.es/~jcampos/ Outline Why stochastic processes? The oisson process Exponential distribution roperties of

More information

Introduction to Data Mining

Introduction to Data Mining Introduction to Data Mining Ho Chi Minh City - October 2016 Xavier Gendre Introduction to Data Mining Ho Chi Minh City - October 2016 Xavier Gendre This work is licensed under a Creative Commons Attribution

More information

Dimension Reduction in Abundant High Dimensional Regressions

Dimension Reduction in Abundant High Dimensional Regressions Dimension Reduction in Abundant High Dimensional Regressions Dennis Cook University of Minnesota 8th Purdue Symposium June 2012 In collaboration with Liliana Forzani & Adam Rothman, Annals of Statistics,

More information

AM - Further Mathematics

AM - Further Mathematics Coordinating unit: Teaching unit: Academic year: Degree: ECTS credits: 2018 300 - EETAC - Castelldefels School of Telecommunications and Aerospace Engineering 749 - MAT - Department of Mathematics BACHELOR'S

More information

1 Motivation for Newton interpolation

1 Motivation for Newton interpolation cs412: introduction to numerical analysis 09/30/10 Lecture 7: Newton Interpolation Instructor: Professor Amos Ron Scribes: Yunpeng Li, Mark Cowlishaw, Nathanael Fillmore 1 Motivation for Newton interpolation

More information

Principal Components Analysis

Principal Components Analysis Principal Components Analysis Nathaniel E. Helwig Assistant Professor of Psychology and Statistics University of Minnesota (Twin Cities) Updated 16-Mar-2017 Nathaniel E. Helwig (U of Minnesota) Principal

More information

Statistics Assignment 2 HET551 Design and Development Project 1

Statistics Assignment 2 HET551 Design and Development Project 1 Statistics Assignment HET Design and Development Project Michael Allwright - 74634 Haddon O Neill 7396 Monday, 3 June Simple Stochastic Processes Mean, Variance and Covariance Derivation The following

More information

Short Answer Questions: Answer on your separate blank paper. Points are given in parentheses.

Short Answer Questions: Answer on your separate blank paper. Points are given in parentheses. ISQS 6348 Final exam solutions. Name: Open book and notes, but no electronic devices. Answer short answer questions on separate blank paper. Answer multiple choice on this exam sheet. Put your name on

More information

Stable Process. 2. Multivariate Stable Distributions. July, 2006

Stable Process. 2. Multivariate Stable Distributions. July, 2006 Stable Process 2. Multivariate Stable Distributions July, 2006 1. Stable random vectors. 2. Characteristic functions. 3. Strictly stable and symmetric stable random vectors. 4. Sub-Gaussian random vectors.

More information

Methods for Marsh Futures Area of Interest (AOI) Elevation Zone Delineation

Methods for Marsh Futures Area of Interest (AOI) Elevation Zone Delineation PARTNERSHIP FOR THE DELAWARE ESTUARY Science Group Methods for Marsh Futures Area of Interest (AOI) Elevation Zone Delineation Date Prepared: 07/30/2015 Prepared By: Joshua Moody Suggested Citation: Moody,

More information

Two remarks on normality preserving Borel automorphisms of R n

Two remarks on normality preserving Borel automorphisms of R n Proc. Indian Acad. Sci. (Math. Sci.) Vol. 3, No., February 3, pp. 75 84. c Indian Academy of Sciences Two remarks on normality preserving Borel automorphisms of R n K R PARTHASARATHY Theoretical Statistics

More information

An Automated Approach for Evaluating Spatial Correlation in Mixed Signal Designs Using Synopsys HSpice

An Automated Approach for Evaluating Spatial Correlation in Mixed Signal Designs Using Synopsys HSpice Spatial Correlation in Mixed Signal Designs Using Synopsys HSpice Omid Kavehei, Said F. Al-Sarawi, Derek Abbott School of Electrical and Electronic Engineering The University of Adelaide Adelaide, SA 5005,

More information

American Standard Code for Information Interchange. Atmospheric Trace MOlecule Spectroscopy. Commission Internationale de l Eclairage

American Standard Code for Information Interchange. Atmospheric Trace MOlecule Spectroscopy. Commission Internationale de l Eclairage Apèndix A Llista d acrònims AEDOS AOT ASCII ATMOS CIE CLAES CMF CFC COST DISORT DOAS DWD ECMWF ERS Advanced Earth Observing Satellite Aerosol Optical Thickness American Standard Code for Information Interchange

More information

Stat 206: Sampling theory, sample moments, mahalanobis

Stat 206: Sampling theory, sample moments, mahalanobis Stat 206: Sampling theory, sample moments, mahalanobis topology James Johndrow (adapted from Iain Johnstone s notes) 2016-11-02 Notation My notation is different from the book s. This is partly because

More information

Lecture 3. Probability - Part 2. Luigi Freda. ALCOR Lab DIAG University of Rome La Sapienza. October 19, 2016

Lecture 3. Probability - Part 2. Luigi Freda. ALCOR Lab DIAG University of Rome La Sapienza. October 19, 2016 Lecture 3 Probability - Part 2 Luigi Freda ALCOR Lab DIAG University of Rome La Sapienza October 19, 2016 Luigi Freda ( La Sapienza University) Lecture 3 October 19, 2016 1 / 46 Outline 1 Common Continuous

More information

Week 6: Differential geometry I

Week 6: Differential geometry I Week 6: Differential geometry I Tensor algebra Covariant and contravariant tensors Consider two n dimensional coordinate systems x and x and assume that we can express the x i as functions of the x i,

More information

STA 302f16 Assignment Five 1

STA 302f16 Assignment Five 1 STA 30f16 Assignment Five 1 Except for Problem??, these problems are preparation for the quiz in tutorial on Thursday October 0th, and are not to be handed in As usual, at times you may be asked to prove

More information

A simple dynamic model of labor market

A simple dynamic model of labor market 1 A simple dynamic model of labor market Let e t be the number of employed workers, u t be the number of unemployed worker. An employed worker has probability of 0.8 to be employed in the next period,

More information

Primal-Dual Interior-Point Methods for Linear Programming based on Newton s Method

Primal-Dual Interior-Point Methods for Linear Programming based on Newton s Method Primal-Dual Interior-Point Methods for Linear Programming based on Newton s Method Robert M. Freund March, 2004 2004 Massachusetts Institute of Technology. The Problem The logarithmic barrier approach

More information

APPENDIX : PARTIAL FRACTIONS

APPENDIX : PARTIAL FRACTIONS APPENDIX : PARTIAL FRACTIONS Appendix : Partial Fractions Given the expression x 2 and asked to find its integral, x + you can use work from Section. to give x 2 =ln( x 2) ln( x + )+c x + = ln k x 2 x+

More information

Passing from generating functions to recursion relations

Passing from generating functions to recursion relations Passing from generating functions to recursion relations D Klain last updated December 8, 2012 Comments and corrections are welcome In the textbook you are given a method for finding the generating function

More information

2. Matrix Algebra and Random Vectors

2. Matrix Algebra and Random Vectors 2. Matrix Algebra and Random Vectors 2.1 Introduction Multivariate data can be conveniently display as array of numbers. In general, a rectangular array of numbers with, for instance, n rows and p columns

More information

Lidskii aditivo y multiplicativo con igualdades

Lidskii aditivo y multiplicativo con igualdades Lidsii aditivo y multiplicativo con igualdades Seminario IAM 26 / 10 / 2012 1 Submajorization and log-majorization Next we briefly describe majorization and log-majorization, two notions from matrix analysis

More information

(4-S1-C1) Observe, ask questions, and make predictions. (4-S1-C2) Participate in planning and conducting investigations, and recording data.

(4-S1-C1) Observe, ask questions, and make predictions. (4-S1-C2) Participate in planning and conducting investigations, and recording data. CUARTO GRADO ESTRUCTURAS DE VIDA- ALINEACIÓN DE ESTÁNDARES Investigation 1: Origin of Seeds Part 1: Seed Search Where do seeds come from? Where are seeds found on plants? De dónde vienen las semillas?

More information

TWO COLOR OFF-DIAGONAL RADO-TYPE NUMBERS

TWO COLOR OFF-DIAGONAL RADO-TYPE NUMBERS TWO COLOR OFF-DIAGONAL RADO-TYPE NUMBERS Kellen Myers 1 and Aaron Robertson Department of Mathematics, Colgate University, Hamilton, NY 13346 aaron@math.colgate.edu Abstract We show that for any two linear

More information

THE PRODUCT OF A LINDELÖF SPACE WITH THE SPACE OF IRRATIONALS UNDER MARTIN'S AXIOM

THE PRODUCT OF A LINDELÖF SPACE WITH THE SPACE OF IRRATIONALS UNDER MARTIN'S AXIOM proceedings of the american mathematical society Volume 110, Number 2, October 1990 THE PRODUCT OF A LINDELÖF SPACE WITH THE SPACE OF IRRATIONALS UNDER MARTIN'S AXIOM K. ALSTER (Communicated by Dennis

More information

Linear Estimation of Y given X:

Linear Estimation of Y given X: Problem: Given measurement Y, estimate X. Linear Estimation of Y given X: Why? You want to know something that is difficult to measure, such as engine thrust. You estimate this based upon something that

More information

Scatter Matrices and Independent Component Analysis

Scatter Matrices and Independent Component Analysis AUSTRIAN JOURNAL OF STATISTICS Volume 35 (2006), Number 2&3, 175 189 Scatter Matrices and Independent Component Analysis Hannu Oja 1, Seija Sirkiä 2, and Jan Eriksson 3 1 University of Tampere, Finland

More information

ROBUST PARTIAL LEAST SQUARES REGRESSION AND OUTLIER DETECTION USING REPEATED MINIMUM COVARIANCE DETERMINANT METHOD AND A RESAMPLING METHOD

ROBUST PARTIAL LEAST SQUARES REGRESSION AND OUTLIER DETECTION USING REPEATED MINIMUM COVARIANCE DETERMINANT METHOD AND A RESAMPLING METHOD ROBUST PARTIAL LEAST SQUARES REGRESSION AND OUTLIER DETECTION USING REPEATED MINIMUM COVARIANCE DETERMINANT METHOD AND A RESAMPLING METHOD by Dilrukshika Manori Singhabahu BS, Information Technology, Slippery

More information

CLASSROOM SIMULATION: THE MARGIN OF ERROR IN A PUBLIC OPINION POLL

CLASSROOM SIMULATION: THE MARGIN OF ERROR IN A PUBLIC OPINION POLL Draft of paper for presentation at Joint Statistics Meetings, August 2005, Minneapolis 1 CLASSROOM SIMULATION: THE MARGIN OF ERROR IN A PUBLIC OPINION POLL Bruce E. TRUMBO, Eric A. SUESS, and Shuhei OKUMURA;

More information

Decorrelation in Statistics: The Mahalanobis Transformation Added material to Data Compression: The Complete Reference

Decorrelation in Statistics: The Mahalanobis Transformation Added material to Data Compression: The Complete Reference Decorrelation in Statistics: The Mahalanobis Transformation dded material to Data Compression: The Complete Reference n image can be compressed if, and only if, its pixels are correlated. This is mentioned

More information

CHARACTERIZATIONS OF HARDLY e-open FUNCTIONS

CHARACTERIZATIONS OF HARDLY e-open FUNCTIONS CHARACTERIZATIONS OF HARDLY e-open FUNCTIONS Miguel Caldas 1 April, 2011 Abstract A function is defined to be hardly e-open provided that the inverse image of each e-dense subset of the codomain that is

More information

Dept of Mechanical Engineering MIT Nanoengineering group

Dept of Mechanical Engineering MIT Nanoengineering group 1 Dept of Mechanical Engineering MIT Nanoengineering group » Recap of HK theorems and KS equations» The physical meaning of the XC energy» Solution of a one-particle Schroedinger equation» Pseudo Potentials»

More information

I.G.C.S.E. Matrices and Transformations. You can access the solutions from the end of each question

I.G.C.S.E. Matrices and Transformations. You can access the solutions from the end of each question I.G..S.E. Matrices and Transformations Index: Please click on the question number you want Question 1 Question 2 Question 3 Question 4 Question 5 Question 6 You can access the solutions from the end of

More information

Linear Regression 9/23/17. Simple linear regression. Advertising sales: Variance changes based on # of TVs. Advertising sales: Normal error?

Linear Regression 9/23/17. Simple linear regression. Advertising sales: Variance changes based on # of TVs. Advertising sales: Normal error? Simple linear regression Linear Regression Nicole Beckage y " = β % + β ' x " + ε so y* " = β+ % + β+ ' x " Method to assess and evaluate the correlation between two (continuous) variables. The slope of

More information

Electricity and Magnetism

Electricity and Magnetism Electricity and Magnetism Electricity and magnetism have been known for thousands of years The ancient Greeks knew that a piece of amber rubbed with fur would attract small, light objects The word for

More information

Markov Random Fields

Markov Random Fields Markov Random Fields 1. Markov property The Markov property of a stochastic sequence {X n } n 0 implies that for all n 1, X n is independent of (X k : k / {n 1, n, n + 1}), given (X n 1, X n+1 ). Another

More information

Multivariate distance Fall

Multivariate distance Fall Multivariate distance 2017 Fall Contents Euclidean Distance Definitions Standardization Population Distance Population mean and variance Definitions proportions presence-absence data Multivariate distance

More information

Solar activity and climate in Central America

Solar activity and climate in Central America Geofísica Internacional (), ol., 39, Num. 1, pp. 97-11 Solar activity and climate in Central America Esteban Araya, Javier Bonatti and Walter Fernández Laboratory for Atmospheric and Planetary Research,

More information

Lecture 6: Selection on Multiple Traits

Lecture 6: Selection on Multiple Traits Lecture 6: Selection on Multiple Traits Bruce Walsh lecture notes Introduction to Quantitative Genetics SISG, Seattle 16 18 July 2018 1 Genetic vs. Phenotypic correlations Within an individual, trait values

More information

High Dimensional Covariance and Precision Matrix Estimation

High Dimensional Covariance and Precision Matrix Estimation High Dimensional Covariance and Precision Matrix Estimation Wei Wang Washington University in St. Louis Thursday 23 rd February, 2017 Wei Wang (Washington University in St. Louis) High Dimensional Covariance

More information