t-test of judge bias

Size: px
Start display at page:

Download "t-test of judge bias"

Transcription

1 t-test of judge bias Xiaoqian Yang Goal: conduct a linear regression to fit the fodel: with constraints for each j, and s j,i = λ i µ j β j,c(i) ɛ j,i (1) µ j = 0 (2) j β j,c = 0 (3) c β j,c = 0 (4) j for each c. In the code below, a model matrix is constructed. The related coefficients and p-values are obtained with the function lsfit(). (Only those of the interactions are taken because that is what we are interested in.) Then the coefficients and p-values are put in two matrices where the rows stand for judges and the columns stand for countries. > ### function to get the model matrix > getcontrasts <- function(x, quality = FALSE, jtend = FALSE, r = 7) { n <- nrow(x) var1 <- names(x)[1] # how to use these variables? var2 <- names(x)[2] levels1 <- levels(x[,1]) levels2 <- levels(x[,2]) n1 <- length(levels1) # number of judges n2 <- length(levels2) # number of countries xmis <- table(x[,1], x[,2]) == 0 # subset is/not null xcon <- xmis # whether accessible by contrast for (i in 1:nrow(xmis)) xcon[i, max(which(!xmis[i,]))] <- "r" for (i in 1:ncol(xmis)) xcon[max(which(!xmis[,i])), i] <- "c" xcon[xcon!="c" & xcon!="r"] <- "" p <- sum(!xmis & xcon == "") # number of parameters to estimate 1

2 betapos <- matrix(0, n1, n2) # what are the parameters num <- table(x[,1], x[,2]) # number of data for each group k <- 1 for (i in 1:n1) for (j in 1:n2) { if (!xmis[i,j] & xcon[i,j] == "") { betapos[i,j] <- k k <- k1 rx <- array(0, dim = c(n1, n2, p)) # rows in the model matrix that correspond to a specific judge and country ans <- matrix(0, n, p) # model matrix colnames(ans) <- rep('', p) for (i in 1:n1) { for (j in 1:n2) { if (!xmis[i,j]) { if (xcon[i,j] == "") { rx[i,j,][betapos[i,j]] <- 1 ans[x[,1] == levels1[i] & x[,2] == levels2[j], ] <- matrix(rep(rx[i,j,], num[i,j]), ncol = p, byrow = T) else { if (xcon[i,j] == "r") { rx[i,j,] <- -colsums(rx[i,1:(j-1),]) ans[x[,1] == levels1[i] & x[,2] == levels2[j], ] <- matrix(rep(rx[i,j,], num[i,j]), ncol = p, byrow = T) else { rx[i,j,] <- -colsums(rx[1:(i-1),j,]) ans[x[,1] == levels1[i] & x[,2] == levels2[j], ] <- matrix(rep(rx[i,j,], num[i,j]), ncol = p, byrow = T) colnames(ans)[betapos[i,j]] <- paste(levels1[i], levels2[j], sep = '/') if (quality) { ans1 <- matrix(0, n, round(n/r)) # add the quality for each dive colnames(ans1) <- rep('', round(n/r)) for (i in 1:round(n/r)) { # do this without loop? ans1[(r*i-r1):(r*i),i] <- 1 colnames(ans1)[i] <- paste('d', i, sep = '') 2

3 ans <- cbind(ans, ans1) if (jtend) { ans1 <- matrix(0, n, n1-1) # add each judge's score tendency colnames(ans1) <- levels1[1:(n1-1)] for (i in 1:(n1-1)) { ans1[,i] <- (x$judge == levels1[i])-(x$judge == levels1[n1]) ans <- cbind(ans, ans1) pval <- matrix(na, n1, n2) # store the pvalues in Judge*Country ma bias <- matrix(na, n1, n2) lsbase <- ls.print(lsfit(ans, y, intercept = FALSE), print.it = F) k <- 1 for (i in 1:n1) for (j in 1:n2) { if (!xmis[i,j] & xcon[i,j] == "") { bias[i,j] <- lsbase$coef[[1]][k,1] pval[i,j] <- lsbase$coef[[1]][k,4] k <- k1 rownames(pval) <- levels1 colnames(pval) <- levels2 rownames(bias) <- levels1 colnames(bias) <- levels2 return(list("mm" = ans, "p-value" = pval, 'bias' = bias)) Next apply the function above to the diving data. Eight countries had to be removed from the dataset to eliminate colinearity. Here is results of the linear regression: > x <- read.csv(" as.is=true) > x <- x[x$country!= 'ARG',] > x <- x[x$country!= 'GEO',] > x <- x[x$country!= 'ARM',] > x <- x[x$country!= 'AZE',] > x <- x[x$country!= 'CZE',] > x <- x[x$country!= 'HKG',] > x <- x[x$country!= 'ZIM',] 3

4 > x <- x[x$country!= 'FIN',] > y <- x$jscore > theinput <- data.frame(judge=factor(x$judge), Country=factor(x$Country)) > res <- getcontrasts(theinput, quality = T, jtend = T) > J <- unique(x$judge) > JC <- rep(na, length(j)) > pown <- rep(na, length(j)) > for (i in 1:length(J)) { if (sum(x$judge == J[i] & x$jcountry == x$country)>0) { JC[i] <- unique(x[x$judge == J[i], ]$JCountry) pown[i] <- res$p[j[i], JC[i]] > pres <- data.frame(judge = J, Jcountry = JC, P_value = pown) > pres <- pres[!is.na(pres$p_value),] > pres <- pres[order(pres$jc),] > pres Judge Jcountry P_value 14 BARNETT Madeleine AUS e HUBER Peter AUT e-03 3 BOYS Beverley CAN e SEAMAN Kathy CAN e-01 8 WANG Facheng CHN e XU Yiming CHN e-02 1 RUIZ-PEDREGUERA Rolando CUB e-02 7 CRUZ Julia ESP e-03 5 BOUSSARD Michel FRA e BOOTHROYD Sydney GBR e-03 9 ALT Walter GER e BURK Hans-Peter GER e MENA Jesus MEX e-04 6 CALDERON Felix PUR e GEISSBUHLER Michael SUI e McFARLAND Steve USA e-03 Output is the p-values of the 17 interactions that stand for the bias of judges toward divers from their countries. These results coincide with results of the paper Assessing Judging Bias: An Example From the 2000 Olympic Games. Next try to replicate Figure 1 from the paper. Successfully replicated the figure. The correctness of the model matrix is verified. Note: Also tried implementing Yu s Lagrange optimization algorithm to check that the two algorithms are equivalent. If qualities of each dive is added to the regression as variables, this algorithm cannot be applied to the big dataset (at least not for my computer) since it 4

5 1 AUS AUT BLR BRA CAN CHN COL CUB ESP FRA GBR GER GRE HUN INA JPN ITA KAZ KOR MAS MEX PER PHI PRK PUR STEWART Anthea McFARLAND Steve LINDBERG Mathz GEISSBUHLER Michael ZAITSEV Oleg CALDERON Felix HOOD Robin GEAR Dennis JOHNSON Bente MENA Jesus KELEMEN Ildiko BURK Hans Peter ALT Walter BOOTHROYD Sydney BOUSSARD Michel CRUZ Julia HOOD Robin CERMAKOVA Maria RUIZ PEDREGUERA Rolando XU Yiming WANG Facheng SEAMAN Kathy BOYS Beverley HUBER Peter BARNETT Madeleine 1 5

6 requires huge space allocation for the matrix operations. (How do the functions lm/lsfit avoid that matrix multiplication?) So only the toy data is used. Here is the implementation: > getbeta <- function(x) { n <- nrow(x) var1 <- names(x)[1] var2 <- names(x)[2] levels1 <- levels(x[,1]) levels2 <- levels(x[,2]) n1 <- length(levels1) n2 <- length(levels2) ans <- matrix(0, n, n1) # model matrix for (i in 1:n1) { ans[x[,1] == levels1[i], i] <- 1 ans1 <- matrix(0, n, n1*n2) for (i in 1:n1) { for (j in 1:n2) { ans1[x[,1] == levels1[i] & x[,2] == levels2[j], (i-1)*n2j] <- 1 ans <- cbind(ans, ans1) ans1 <- matrix(0, n, n/3) for (i in 1:(n/3)) { ans1[(3*i-2):(3*i),i] <- 1 ans <- cbind(ans, ans1) xmis <- table(x[,1], x[,2]) == 0 # construct matrix H H <- matrix(0, n1n2sum(xmis), n1n1*n2n/3) H[1, 1:n1] <- 1 for (i in 1:n1) { H[i1, (n1(i-1)*n21):(n1(i-1)*n2n2)] <- 1 for (i in 1:(n2-1)) { H[1n1i, seq(n11i-1, n1n1*n2i-n2, by = n2)] <- 1 for (i in 1:length(which(t(xmis)))) { H[1n1(n2-1)i, n1which(t(xmis))[i]] <- 1 X <- ans H <- t(h) 6

7 A1 <- cbind(t(x)%*%x, H) A2 <- cbind(t(h), matrix(0,ncol(h),ncol(h))) A <- rbind(a1,a2) b <- rbind(t(x)%*%y, matrix(0, ncol(h), 1)) beta <- solve(a, b) bias <- matrix(beta[(n11):(n1n1*n2)], nrow=n1, byrow=true) colnames(bias) <- levels1 rownames(bias) <- levels2 return(bias) > x <- read.csv(" as.is=true) > theinput <- data.frame(judge=factor(x$judge), Country=factor(x$Country)) > y <- x$jscore > bias1 <- getbeta(theinput) > bias1 BOUSSARD Michel CALDERON Felix McFARLAND Steve MENA Jesus CHN e e MEX e e PUR e e USA e e > bias2 <- getcontrasts(theinput, quality = T, jtend = T, r = 3)$bias > bias2 CHN MEX PUR USA BOUSSARD Michel NA NA CALDERON Felix NA McFARLAND Steve NA NA NA MENA Jesus NA NA NA NA The results are identical, the algorithms are both correct approaches to fit our linear model. One problem with Lagrange optimization approach is that it is not as simple as in contrast sum linear model to work out the p-values (need to deduct distribution of ˆβ theoretically). 7

AGE GROUPS UNIFORMS UPDATED ON

AGE GROUPS UNIFORMS UPDATED ON AGE GROUPS UNIFORMS UPDATED ON 2018-05-25 ARG OPTION 1 Approved by the ITU Uniform Panel, 17 February 2014 MEN WOMEN ARG OPTION 2 Approved by the ITU Uniform Panel, 29 June 2017 AUS OPTION 1 Approved by

More information

ELITE TRIATHLON UNIFORMS UPDATED ON

ELITE TRIATHLON UNIFORMS UPDATED ON ELITE TRIATHLON UNIFORMS UPDATED ON 2018-01-31 ARG OPTION 1 MEN Approved by the ITU Uniform Panel, 6 April 2016 This uniform is approved under the condition that Sponsor Space C is available only on the

More information

ELITE TRIATHLON UNIFORMS UPDATED ON

ELITE TRIATHLON UNIFORMS UPDATED ON ELITE TRIATHLON UNIFORMS UPDATED ON 2018-07-05 ARG Approved by the ITU Uniform Panel, 13 June 2018 AUS MEN Approved by the ITU Uniform Panel, 10 May 2018 AUS WOMEN Approved by the ITU Uniform Panel, 10

More information

ELITE MULTISPORT UNIFORMS UPDATED ON

ELITE MULTISPORT UNIFORMS UPDATED ON ELITE MULTISPORT UNIFORMS UPDATED ON 2018-11-20 ARG Approved by the ITU Uniform Panel, 13 June 2018 AUS Approved by the ITU Uniform Panel, 25 January 2017 AUT Approved by ITU Uniform Panel, 17 March 2011

More information

ELITE MULTISPORT UNIFORMS UPDATED ON

ELITE MULTISPORT UNIFORMS UPDATED ON ELITE MULTISPORT UNIFORMS UPDATED ON 2018-04-25 ARG OPTION 1 Approved by ITU Uniform Panel, 17 February 2014 MEN WOMEN ARG OPTION 2 Approved by ITU Uniform Panel, 25 August 2011 The colours and design

More information

Cisco HCS Country Dial Plans

Cisco HCS Country Dial Plans Introduction to Country Dial Plans for Cisco Unified Communications Domain Manager 8.1(x), page 1 Guidelines for Deploying Country Dial Plans, page 4 Load a Country-Specific Dial Plan, page 4 Introduction

More information

IMPARTIALITY IN DIVING EVIDENCE FROM THE EUROPEAN CHAMPIONSHIPS

IMPARTIALITY IN DIVING EVIDENCE FROM THE EUROPEAN CHAMPIONSHIPS d j D dd δz l ik ik cp ik ik d ik l jik Dcp dd Z Figure 1 Table 1 Nationality n ctype n AUT 32 m1 144 AZE 6 m10 72 BLR 52 m10synchro 36 CRO 32 m3 130 ESP 55 m3synchro 66 FIN 30 w1 110 FRA 20 w10

More information

FIS FREESTYLE WORLD SKI CHAMPIONSHIPS 2017 OVERALL RESULTS Men's Moguls SIERRA NEVADA (ESP) WED 8 MAR 2017 Start Time: 15:20

FIS FREESTYLE WORLD SKI CHAMPIONSHIPS 2017 OVERALL RESULTS Men's Moguls SIERRA NEVADA (ESP) WED 8 MAR 2017 Start Time: 15:20 FREESTYLE WORLD SKI CHAMPIONSHIPS 2017 WED 8 MAR 2017 Start : 15:20 Jury Course Data Technical Delegate: KITOV Oleg RUS Course Name: Visera Head Judge: MUELLER Juerg SUI Length: 245.0m Chief of Competition:

More information

FIS SNOWBOARD WORLD CHAMPIONSHIPS 2017 RESULTS Men's Snowboard Big Air SIERRA NEVADA (ESP) FRI 17 MAR 2017 Start Time: 19:30

FIS SNOWBOARD WORLD CHAMPIONSHIPS 2017 RESULTS Men's Snowboard Big Air SIERRA NEVADA (ESP) FRI 17 MAR 2017 Start Time: 19:30 Jury Course Data Technical Delegate: DVORAKOVA Lenka CZE Course Name: Sierra Nevada Big Air Head Judge: JENNINGS Matthew USA In-Run Length / Pitch: 60m / 33 Chief of Competition: CRUZ Enrique ESP Take-off

More information

II.Matrix. Creates matrix, takes a vector argument and turns it into a matrix matrix(data, nrow, ncol, byrow = F)

II.Matrix. Creates matrix, takes a vector argument and turns it into a matrix matrix(data, nrow, ncol, byrow = F) II.Matrix A matrix is a two dimensional array, it consists of elements of the same type and displayed in rectangular form. The first index denotes the row; the second index denotes the column of the specified

More information

ISU World Junior Figure Skating Championships 2018

ISU World Junior Figure Skating Championships 2018 (factored) 1 Anastasia SKOPTCOVA / Kirill ALESHIN RUS 27 66.44 34.68 31.76 0.00 1 CuLi4 4.50 1.46 2 3 3 3 1 2 2 3 2 s of 2 STw4 6.60 1.37 3 2 2 2 2 3 3 2 2 7.97 3 1CC3+kpTYY 4.40 0.94 2 1 2 2 0 2 1 2 1

More information

An Introduction to R

An Introduction to R http://www.stat.yale.edu/~jay/ Associate Professor of Statistics, Yale University (Professor Emerson prefers to be called Jay ) These slides complement the talk; they may be a useful reference, but may

More information

RACE ANALYSIS QUALIFICATION

RACE ANALYSIS QUALIFICATION Number of Competitors: 50, Number of s: 18 1 20 SOMMARIVA Lorenzo ITA Run 1: Int 1: 19.09 (1) 0.00 I1-Fin: 20.43 (2) Fin: 39.52 (1) 0.00 61.49 2 10 BERG Paul GER Run 1: 3 9 ROBANSKE Christopher CAN Run

More information

Practice for Learning R and Learning Latex

Practice for Learning R and Learning Latex Practice for Learning R and Learning Latex Jennifer Pan August, 2011 Latex Environments A) Try to create the following equations: 1. 5+6 α = β2 2. P r( 1.96 Z 1.96) = 0.95 ( ) ( ) sy 1 r 2 3. ˆβx = r xy

More information

ISU World Junior Figure Skating Championships 2017

ISU World Junior Figure Skating Championships 2017 (factored) 1 Alla LOBODA / Pavel DROZD RUS 31 67.59 3 32.66 0.00 6.60 1.11 2 2 2 2 2 1 2 2 0 s of 2 1BL4+kpYYY 5.00 0.94 1 1 2 1 2 1 2 2 2 5.94 3 2BL4+kpYYY 5.00 1.11 2 2 3 1 2 1 2 2 2 6.11 4 SlLi4 4.50

More information

World Championships 2019

World Championships 2019 (factored) 1 Evgenia TARASOVA / Vladimir MOROZOV RUS 17 81.21 44.14 37.07 Info Base GOE J1 J2 J3 J4 J5 J6 J7 J8 J9 Ref s of s 1 3Tw4 6.00 2.66 4 4 4 5 5 4 4 5 5 8.66 2 3T 4.20 1.20 2 3 1 4 3 4 3 3 2 5.40

More information

Underground economy. Economics of Security and Privacy (BMEVIHIAV15) Mark Felegyhazi. assistant professor CrySyS Lab.

Underground economy. Economics of Security and Privacy (BMEVIHIAV15) Mark Felegyhazi. assistant professor CrySyS Lab. Underground economy Economics of Security and Privacy (BMEVIHIAV15) Mark Felegyhazi assistant professor CrySyS Lab. Underground economy BME Department of Telecommunications (Híradástechnikai Tanszék) mfelegyhazi(atat)crysys(dot)hu

More information

Lecture 3: Basics of R Programming

Lecture 3: Basics of R Programming Lecture 3: Basics of R Programming This lecture introduces you to how to do more things with R beyond simple commands. Outline: 1. R as a programming language 2. Grouping, loops and conditional execution

More information

PARTS REFERENCE LIST MODEL: 1034D/1034DAV/2034D 1134DW/1134D DZ1234/1334D 734D/355D 1634D

PARTS REFERENCE LIST MODEL: 1034D/1034DAV/2034D 1134DW/1134D DZ1234/1334D 734D/355D 1634D Home Sewing Machine PARTS REFERENCE LIST MODEL: 1034D/1034DAV/2034D 1134DW/1134D DZ1234/1334D 734D/355D 1634D Published: Nov.,2000 Revised: Sep.,2017 MODEL LIST Model Countries (Added Date) 1134DW USA

More information

FIS FREESTYLE SKI WORLD CUP 2018 Results - Overall Men's Moguls DEER VALLEY (USA) WED 10 JAN 2018 Start Time: 19:50

FIS FREESTYLE SKI WORLD CUP 2018 Results - Overall Men's Moguls DEER VALLEY (USA) WED 10 JAN 2018 Start Time: 19:50 FREESTYLE SKI WORLD CUP 2018 WED 10 JAN 2018 Start : 19:50 Jury Course Data Technical Delegate SAGAN Dave CAN Course Name Champion Head Judge LOUNSBURY Scott USA Length 252m Chief of Competition ROTERMUND

More information

FIS FREESTYLE SKI WORLD CUP 2018 Results - Overall Men's Moguls DEER VALLEY (USA) THU 11 JAN 2018 Start Time: 19:50

FIS FREESTYLE SKI WORLD CUP 2018 Results - Overall Men's Moguls DEER VALLEY (USA) THU 11 JAN 2018 Start Time: 19:50 FREESTYLE SKI WORLD CUP 2018 Jury Course Data Technical Delegate SAGAN Dave CAN Course Name Champion Head Judge LOUNSBURY Scott USA Length 252m Chief of Competition ROTERMUND Konrad USA Course / Gate Width

More information

FIS SNOWBOARD WORLD CUP 2017 RESULTS Men's Snowboard Big Air QUEBEC CITY (CAN) SAT 11 FEB 2017 Start Time: 17:00

FIS SNOWBOARD WORLD CUP 2017 RESULTS Men's Snowboard Big Air QUEBEC CITY (CAN) SAT 11 FEB 2017 Start Time: 17:00 Jury Course Data Technical Delegate: GRELL Jeffrey USA Course Name: Jamboree Big Air Head Judge: CENTURIONE Marcello CAN In-Run Length / Pitch: 57m / 40 Chief of Competition: LANGELIER Dominique CAN Take-off

More information

The webinar will begin shortly

The webinar will begin shortly The webinar will begin shortly Towards Green Growth? Official Launch of the OECD's Tracking Progress Report 27 July 2015 Need technical support? Email: contact@ggkp.org Supported by: Towards Green Growth?

More information

Lecture 3: Basics of R Programming

Lecture 3: Basics of R Programming Lecture 3: Basics of R Programming This lecture introduces how to do things with R beyond simple commands. We will explore programming in R. What is programming? It is the act of instructing a computer

More information

Econ 430 Lecture 3: Significance and Structural Properties of N

Econ 430 Lecture 3: Significance and Structural Properties of N Econ 430 Lecture 3: Significance and Structural Properties of Networks Alper Duman Izmir University Economics, March 8, 2013 Prevalence of Networks Networks are everywhere! Even in this class. We can classify

More information

Package mgc. April 13, 2018

Package mgc. April 13, 2018 Type Package Title Multiscale Graph Correlation Version 1.0.1 Date 2018-04-12 Package mgc April 13, 2018 Maintainer Multiscale Graph Correlation (MGC) is a framework developed by Shen

More information

2018 Autumn Classic International

2018 Autumn Classic International (factored) 1 Junhwan CHA KOR 17 169.22 87.62 81.60 0.00 1 4T 9.50 3.04 2 2 3 4 4 4 3 s of 2 4S< < 7.28-2.47-4 -4-4 -1-1 -4-4 4.81 3 3Lz+3Lo 10.80 2.01 2 4 2 3 4 4 4 12.81 4 StSq4 3.90 1.25 3 3 3 3 4 4

More information

Module 2: Extend Data Model relationships using Excel, Power Pivot, and DAX... 19

Module 2: Extend Data Model relationships using Excel, Power Pivot, and DAX... 19 EXCEL POWERPIVOT Contents Module 1: Import Data into Excel, and Create a Data Model... 3 The sections in this module are the following:... 3 Import data from a database... 4 Import data from a spreadsheet...

More information

36-402/608 HW #1 Solutions 1/21/2010

36-402/608 HW #1 Solutions 1/21/2010 36-402/608 HW #1 Solutions 1/21/2010 1. t-test (20 points) Use fullbumpus.r to set up the data from fullbumpus.txt (both at Blackboard/Assignments). For this problem, analyze the full dataset together

More information

Relational data. Peter Hoff. 567 Social network analysis. Statistics, University of Washington /20

Relational data. Peter Hoff. 567 Social network analysis. Statistics, University of Washington /20 /20 Relational data 567 Social network analysis Peter Hoff Statistics, University of Washington 2/20 Defining characteristics of network data Relational data are data that include a set of objects, and

More information

NONPARAMETRIC REGRESSION SPLINES FOR GENERALIZED LINEAR MODELS IN THE PRESENCE OF MEASUREMENT ERROR

NONPARAMETRIC REGRESSION SPLINES FOR GENERALIZED LINEAR MODELS IN THE PRESENCE OF MEASUREMENT ERROR NONPARAMETRIC REGRESSION SPLINES FOR GENERALIZED LINEAR MODELS IN THE PRESENCE OF MEASUREMENT ERROR J. D. Maca July 1, 1997 Abstract The purpose of this manual is to demonstrate the usage of software for

More information

FIS FREESTYLE SKI WORLD CUP 2017 RESULTS - QUALIFICATION Men's Ski Slopestyle SILVAPLANA (SUI) THU 2 MAR 2017 Start Time: 09:00

FIS FREESTYLE SKI WORLD CUP 2017 RESULTS - QUALIFICATION Men's Ski Slopestyle SILVAPLANA (SUI) THU 2 MAR 2017 Start Time: 09:00 Jury Course Data Technical Delegate: BEHOUNEK Christoph GER Course Name: Corvatsch Park Head Judge: ROYER Charly FRA Start / Finish Altitude: 2675m / 2530m Chief of Competition: LAFATA Paolo SUI Vertical

More information

Package SSLASSO. August 28, 2018

Package SSLASSO. August 28, 2018 Package SSLASSO August 28, 2018 Version 1.2-1 Date 2018-08-28 Title The Spike-and-Slab LASSO Author Veronika Rockova [aut,cre], Gemma Moran [aut] Maintainer Gemma Moran Description

More information

FIS FREESTYLE SKI WORLD CUP 2017 RESULTS Men's Ski Slopestyle SEISER ALM (ITA) SAT 28 JAN 2017 Start Time: 11:30

FIS FREESTYLE SKI WORLD CUP 2017 RESULTS Men's Ski Slopestyle SEISER ALM (ITA) SAT 28 JAN 2017 Start Time: 11:30 Jury Course Data Technical Delegate: MALSINER Markus ITA Course Name: Seiser Alm Legends Proline Head Judge: ALLEN Dan USA Start / Finish Altitude: 1941m / 1770m Chief of Competition: SCHENK Matthias ITA

More information

The grplasso Package

The grplasso Package The grplasso Package June 27, 2007 Type Package Title Fitting user specified models with Group Lasso penalty Version 0.2-1 Date 2007-06-27 Author Lukas Meier Maintainer Lukas Meier

More information

Introduction to R, Github and Gitlab

Introduction to R, Github and Gitlab Introduction to R, Github and Gitlab 27/11/2018 Pierpaolo Maisano Delser mail: maisanop@tcd.ie ; pm604@cam.ac.uk Outline: Why R? What can R do? Basic commands and operations Data analysis in R Github and

More information

The R.huge Package. September 1, 2007

The R.huge Package. September 1, 2007 The R.huge Package September 1, 2007 Version 0.1.5 Date 2006-08-29 Title Methods for accessing huge amounts of data Author Henrik Bengtsson Maintainer Henrik Bengtsson

More information

MACAU User Manual. Xiang Zhou. March 15, 2017

MACAU User Manual. Xiang Zhou. March 15, 2017 MACAU User Manual Xiang Zhou March 15, 2017 Contents 1 Introduction 2 1.1 What is MACAU...................................... 2 1.2 How to Cite MACAU................................... 2 1.3 The Model.........................................

More information

Problems 1 and 5 were graded by Amin Sorkhei, Problems 2 and 3 by Johannes Verwijnen and Problem 4 by Jyrki Kivinen. Entropy(D) = Gini(D) = 1

Problems 1 and 5 were graded by Amin Sorkhei, Problems 2 and 3 by Johannes Verwijnen and Problem 4 by Jyrki Kivinen. Entropy(D) = Gini(D) = 1 Problems and were graded by Amin Sorkhei, Problems and 3 by Johannes Verwijnen and Problem by Jyrki Kivinen.. [ points] (a) Gini index and Entropy are impurity measures which can be used in order to measure

More information

Package HMRFBayesHiC

Package HMRFBayesHiC Package HMRFBayesHiC February 3, 2015 Type Package Title HMRFBayesHiC conduct Hidden Markov Random Field (HMRF) Bayes Peak Calling Method on HiC Data Version 1.0 Date 2015-01-30 Author Zheng Xu Maintainer

More information

Introduction to the R Language

Introduction to the R Language Introduction to the R Language Data Types and Basic Operations Starting Up Windows: Double-click on R Mac OS X: Click on R Unix: Type R Objects R has five basic or atomic classes of objects: character

More information

Package pa. February 15, 2013

Package pa. February 15, 2013 Package pa February 15, 2013 Type Package Title Performance Attribution for Equity Portfolios Version 1.2 Date 2013-01-05 Author Yang Lu and David Kane Maintainer Yang Lu Depends

More information

Installation Guide of Hikvision LPR cameras

Installation Guide of Hikvision LPR cameras Installation Guide of Hikvision LPR cameras Property in copyright belongs to Hikvision. 1 1 Overview To obtain the maximum license plate recognition accuracy, you need to install the LPR camera in the

More information

Multinomial Logit Models with R

Multinomial Logit Models with R Multinomial Logit Models with R > rm(list=ls()); options(scipen=999) # To avoid scientific notation > # install.packages("mlogit", dependencies=true) # Only need to do this once > library(mlogit) # Load

More information

Introduction to R. Nishant Gopalakrishnan, Martin Morgan January, Fred Hutchinson Cancer Research Center

Introduction to R. Nishant Gopalakrishnan, Martin Morgan January, Fred Hutchinson Cancer Research Center Introduction to R Nishant Gopalakrishnan, Martin Morgan Fred Hutchinson Cancer Research Center 19-21 January, 2011 Getting Started Atomic Data structures Creating vectors Subsetting vectors Factors Matrices

More information

1 Matrices and Vectors and Lists

1 Matrices and Vectors and Lists University of Wollongong School of Mathematics and Applied Statistics STAT231 Probability and Random Variables 2014 Second Lab - Week 4 If you can t finish the log-book questions in lab, proceed at home.

More information

Sub-setting Data. Tzu L. Phang

Sub-setting Data. Tzu L. Phang Sub-setting Data Tzu L. Phang 2016-10-13 Subsetting in R Let s start with a (dummy) vectors. x

More information

Lecture 13: Model selection and regularization

Lecture 13: Model selection and regularization Lecture 13: Model selection and regularization Reading: Sections 6.1-6.2.1 STATS 202: Data mining and analysis October 23, 2017 1 / 17 What do we know so far In linear regression, adding predictors always

More information

Package esabcv. May 29, 2015

Package esabcv. May 29, 2015 Package esabcv May 29, 2015 Title Estimate Number of Latent Factors and Factor Matrix for Factor Analysis Version 1.2.1 These functions estimate the latent factors of a given matrix, no matter it is highdimensional

More information

STENO Introductory R-Workshop: Loading a Data Set Tommi Suvitaival, Steno Diabetes Center June 11, 2015

STENO Introductory R-Workshop: Loading a Data Set Tommi Suvitaival, Steno Diabetes Center June 11, 2015 STENO Introductory R-Workshop: Loading a Data Set Tommi Suvitaival, tsvv@steno.dk, Steno Diabetes Center June 11, 2015 Contents 1 Introduction 1 2 Recap: Variables 2 3 Data Containers 2 3.1 Vectors................................................

More information

## In the comments below, cp refers to the change point, w/ is "with", w/o is "without".

## In the comments below, cp refers to the change point, w/ is with, w/o is without. ############################################ ### INSTRUCTIONS ############################################ ## In the comments below, cp refers to the change point, w/ is "with", w/o is "without". ## Data

More information

Package xwf. July 12, 2018

Package xwf. July 12, 2018 Package xwf July 12, 2018 Version 0.2-2 Date 2018-07-12 Title Extrema-Weighted Feature Extraction Author Willem van den Boom [aut, cre] Maintainer Willem van den Boom Extrema-weighted

More information

Paths and connectivity

Paths and connectivity /55 Paths and connectivity 57 Statistical analysis of social networks Peter Hoff Statistics, University of Washington /55 Network connectivity Density (or average degree) is a very coarse description of

More information

Package pomdp. January 3, 2019

Package pomdp. January 3, 2019 Package pomdp January 3, 2019 Title Solver for Partially Observable Markov Decision Processes (POMDP) Version 0.9.1 Date 2019-01-02 Provides an interface to pomdp-solve, a solver for Partially Observable

More information

Sample Questions - Solutions

Sample Questions - Solutions Sample Questions - Solutions This document contains multiple choice questions that have a similar format to the multiple choice questions on the 2018 STA130 final exam. The sample questions are published

More information

CS&s/STAT 566 Class Lab 3 January 22, 2016

CS&s/STAT 566 Class Lab 3 January 22, 2016 CS&s/STAT 566 Class Lab 3 January 22, 2016 (1) Fisher s randomization test; continuous response rm(list=ls()) #data trt

More information

Standard Errors in OLS Luke Sonnet

Standard Errors in OLS Luke Sonnet Standard Errors in OLS Luke Sonnet Contents Variance-Covariance of ˆβ 1 Standard Estimation (Spherical Errors) 2 Robust Estimation (Heteroskedasticity Constistent Errors) 4 Cluster Robust Estimation 7

More information

Package ordinalnet. December 5, 2017

Package ordinalnet. December 5, 2017 Type Package Title Penalized Ordinal Regression Version 2.4 Package ordinalnet December 5, 2017 Fits ordinal regression models with elastic net penalty. Supported model families include cumulative probability,

More information

Package SMAT. January 29, 2013

Package SMAT. January 29, 2013 Package SMAT January 29, 2013 Type Package Title Scaled Multiple-phenotype Association Test Version 0.98 Date 2013-01-26 Author Lin Li, Ph.D.; Elizabeth D. Schifano, Ph.D. Maintainer Lin Li ;

More information

Lasso.jl Documentation

Lasso.jl Documentation Lasso.jl Documentation Release 0.0.1 Simon Kornblith Jan 07, 2018 Contents 1 Lasso paths 3 2 Fused Lasso and trend filtering 7 3 Indices and tables 9 i ii Lasso.jl Documentation, Release 0.0.1 Contents:

More information

Package blockmatrix. February 19, 2015

Package blockmatrix. February 19, 2015 Package blockmatrix February 19, 2015 aintainer License GPL (>= 2) Title blockmatrix: Tools to solve algebraic systems with partitioned matrices Type Package Author Some elementary

More information

GOV 2001/ 1002/ E-2001 Section 1 1 Monte Carlo Simulation

GOV 2001/ 1002/ E-2001 Section 1 1 Monte Carlo Simulation GOV 2001/ 1002/ E-2001 Section 1 1 Monte Carlo Simulation Anton Strezhnev Harvard University January 27, 2016 1 These notes and accompanying code draw on the notes from TF s from previous years. 1 / 33

More information

Lecture 25: Review I

Lecture 25: Review I Lecture 25: Review I Reading: Up to chapter 5 in ISLR. STATS 202: Data mining and analysis Jonathan Taylor 1 / 18 Unsupervised learning In unsupervised learning, all the variables are on equal standing,

More information

Learning to Match. Jun Xu, Zhengdong Lu, Tianqi Chen, Hang Li

Learning to Match. Jun Xu, Zhengdong Lu, Tianqi Chen, Hang Li Learning to Match Jun Xu, Zhengdong Lu, Tianqi Chen, Hang Li 1. Introduction The main tasks in many applications can be formalized as matching between heterogeneous objects, including search, recommendation,

More information

CSC 411: Lecture 02: Linear Regression

CSC 411: Lecture 02: Linear Regression CSC 411: Lecture 02: Linear Regression Raquel Urtasun & Rich Zemel University of Toronto Sep 16, 2015 Urtasun & Zemel (UofT) CSC 411: 02-Regression Sep 16, 2015 1 / 16 Today Linear regression problem continuous

More information

Customer specific dial plan

Customer specific dial plan Prerequisites, page 1 Dial Plan workflow, page 2 Determine customer specific dial plan requirements, page 2 Prerequisites Note This section of the document starts the planning part that is repeated with

More information

FIS SNOWBOARD WORLD CUP 2018 Results - Qualification Men's Snowboard Big Air COPPER MOUNTAIN RESORT (USA) FRI 8 DEC 2017 Start Time: 12:45

FIS SNOWBOARD WORLD CUP 2018 Results - Qualification Men's Snowboard Big Air COPPER MOUNTAIN RESORT (USA) FRI 8 DEC 2017 Start Time: 12:45 Jury Course Data FIS Technical Delegate O BRIEN Tim CAN Course Name Main Vein Chief of Competition MONNAVILLE Robb USA In-Run Length / Pitch 137m / 22 FIS Contest Director MORESI Roberto FIS Take-off to

More information

Package rferns. November 15, 2017

Package rferns. November 15, 2017 Package rferns November 15, 2017 Type Package Title Random Ferns Classifier Version 2.0.3 Author Miron B. Kursa Maintainer Miron B. Kursa Description An R implementation of the random

More information

Lasso. November 14, 2017

Lasso. November 14, 2017 Lasso November 14, 2017 Contents 1 Case Study: Least Absolute Shrinkage and Selection Operator (LASSO) 1 1.1 The Lasso Estimator.................................... 1 1.2 Computation of the Lasso Solution............................

More information

Package mfbvar. December 28, Type Package Title Mixed-Frequency Bayesian VAR Models Version Date

Package mfbvar. December 28, Type Package Title Mixed-Frequency Bayesian VAR Models Version Date Type Package Title Mied-Frequency Bayesian VAR Models Version 0.4.0 Date 2018-12-17 Package mfbvar December 28, 2018 Estimation of mied-frequency Bayesian vector autoregressive (VAR) models with Minnesota

More information

Mentor Torun Cup 2019

Mentor Torun Cup 2019 (factored) 1 Kerry BRENDAN AUS 10 79.99 44.57 35.42 s 1 4T+3T 13.70 1.27 2 1 2 1 0 s of 2 3S 4.30 0.86 1 3 3 1 2 5.16 3 CCSp3 2.80 0.37 1 2 3 1 1 3.17 4 3A 8.80 x 0.53 1 1 2 0 0 9.33 5 StSq4 3.90 1.04

More information

Computer Graphics. Coordinate Systems and Change of Frames. Based on slides by Dianna Xu, Bryn Mawr College

Computer Graphics. Coordinate Systems and Change of Frames. Based on slides by Dianna Xu, Bryn Mawr College Computer Graphics Coordinate Systems and Change of Frames Based on slides by Dianna Xu, Bryn Mawr College Linear Independence A set of vectors independent if is linearly If a set of vectors is linearly

More information

Lecture 7: Linear Regression (continued)

Lecture 7: Linear Regression (continued) Lecture 7: Linear Regression (continued) Reading: Chapter 3 STATS 2: Data mining and analysis Jonathan Taylor, 10/8 Slide credits: Sergio Bacallado 1 / 14 Potential issues in linear regression 1. Interactions

More information

Package filematrix. R topics documented: February 27, Type Package

Package filematrix. R topics documented: February 27, Type Package Type Package Package filematrix February 27, 2018 Title File-Backed Matrix Class with Convenient Read and Write Access Version 1.3 Date 2018-02-26 Description Interface for working with large matrices

More information

Package bacon. October 31, 2018

Package bacon. October 31, 2018 Type Package Package October 31, 2018 Title Controlling bias and inflation in association studies using the empirical null distribution Version 1.10.0 Author Maarten van Iterson [aut, cre], Erik van Zwet

More information

How to use the DEGseq Package

How to use the DEGseq Package How to use the DEGseq Package Likun Wang 1,2 and Xi Wang 1. October 30, 2018 1 MOE Key Laboratory of Bioinformatics and Bioinformatics Division, TNLIST /Department of Automation, Tsinghua University. 2

More information

A Worked Example of Goldberg s Bass Ackwards Method

A Worked Example of Goldberg s Bass Ackwards Method A Worked Example of Goldberg s Bass Ackwards Method Niels Waller Department of Psychology University of Minnesota nwaller@umn.edu May 10, 2006 This document presents a worked example for Goldberg s Bass

More information

A Brief Introduction to R

A Brief Introduction to R A Brief Introduction to R Babak Shahbaba Department of Statistics, University of California, Irvine, USA Chapter 1 Introduction to R 1.1 Installing R To install R, follow these steps: 1. Go to http://www.r-project.org/.

More information

1) Give a set-theoretic description of the given points as a subset W of R 3. a) The points on the plane x + y 2z = 0.

1) Give a set-theoretic description of the given points as a subset W of R 3. a) The points on the plane x + y 2z = 0. ) Give a set-theoretic description of the given points as a subset W of R. a) The points on the plane x + y z =. x Solution: W = {x: x = [ x ], x + x x = }. x b) The points in the yz-plane. Solution: W

More information

Model selection. Peter Hoff STAT 423. Applied Regression and Analysis of Variance. University of Washington /53

Model selection. Peter Hoff STAT 423. Applied Regression and Analysis of Variance. University of Washington /53 /53 Model selection Peter Hoff STAT 423 Applied Regression and Analysis of Variance University of Washington Diabetes example: y = diabetes progression x 1 = age x 2 = sex. dim(x) ## [1] 442 64 colnames(x)

More information

Introduction to R. UCLA Statistical Consulting Center R Bootcamp. Irina Kukuyeva September 20, 2010

Introduction to R. UCLA Statistical Consulting Center R Bootcamp. Irina Kukuyeva September 20, 2010 UCLA Statistical Consulting Center R Bootcamp Irina Kukuyeva ikukuyeva@stat.ucla.edu September 20, 2010 Outline 1 Introduction 2 Preliminaries 3 Working with Vectors and Matrices 4 Data Sets in R 5 Overview

More information

Search and Optimization

Search and Optimization Search and Optimization Search, Optimization and Game-Playing The goal is to find one or more optimal or sub-optimal solutions in a given search space. We can either be interested in finding any one solution

More information

Package vbmp. March 3, 2018

Package vbmp. March 3, 2018 Type Package Package vbmp March 3, 2018 Title Variational Bayesian Multinomial Probit Regression Version 1.47.0 Author Nicola Lama , Mark Girolami Maintainer

More information

Package R.huge. February 22, 2015

Package R.huge. February 22, 2015 Version 0.9.0 Depends R (>= 2.10.0) Package R.huge February 22, 2015 Imports R.methodsS3 (>= 1.7.0), R.oo (>= 1.18.0), R.utils (>= 1.34.0) Date 2015-02-22 Title Methods for Accessing Huge Amounts of Data

More information

CS 112 Introduction to Computing II. Wayne Snyder Computer Science Department Boston University

CS 112 Introduction to Computing II. Wayne Snyder Computer Science Department Boston University 9/5/6 CS Introduction to Computing II Wayne Snyder Department Boston University Today: Arrays (D and D) Methods Program structure Fields vs local variables Next time: Program structure continued: Classes

More information

Model selection and validation 1: Cross-validation

Model selection and validation 1: Cross-validation Model selection and validation 1: Cross-validation Ryan Tibshirani Data Mining: 36-462/36-662 March 26 2013 Optional reading: ISL 2.2, 5.1, ESL 7.4, 7.10 1 Reminder: modern regression techniques Over the

More information

Statistical Programming Camp: An Introduction to R

Statistical Programming Camp: An Introduction to R Statistical Programming Camp: An Introduction to R Handout 5: Loops and Conditional Statements Fox Chapter 2, 8 In this handout, we cover the following new materials: Using loops for(i in X){ to repeat

More information

Contents 1 Admin 2 Testing hypotheses tests 4 Simulation 5 Parallelization Admin

Contents 1 Admin 2 Testing hypotheses tests 4 Simulation 5 Parallelization Admin magrittr t F F .. NA library(pacman) p_load(dplyr) x % as_tibble() ## # A tibble: 5 x 2 ## a b ## ## 1 1.. ## 2 2 1 ## 3 3 2 ##

More information

Poisson Regression and Model Checking

Poisson Regression and Model Checking Poisson Regression and Model Checking Readings GH Chapter 6-8 September 27, 2017 HIV & Risk Behaviour Study The variables couples and women_alone code the intervention: control - no counselling (both 0)

More information

ISU World Junior Figure Skating Championships 2017

ISU World Junior Figure Skating Championships 2017 (factored) 1 Rachel PARSONS / Michael PARSONS USA 19 97.54 47.27 50.27 0.00 6.60 1.46 3 2 2 3 2 2 2 3 3 s of 2 CiSt4 8.60 2.36 2 1 2 3 2 3 2 2 2 10.96 3 SlLi4 4.50 1.46 2 1 2 3 2 3 2 3 3 5.96 4 CoSp4 5.60

More information

Risk Management Using R, SoSe 2013

Risk Management Using R, SoSe 2013 1. Problem (vectors and factors) a) Create a vector containing the numbers 1 to 10. In this vector, replace all numbers greater than 4 with 5. b) Create a sequence of length 5 starting at 0 with an increment

More information

Installing the Dialogic NaturalAccess Development Environment R9.x

Installing the Dialogic NaturalAccess Development Environment R9.x Installing the Dialogic NaturalAccess Development Environment R9.x October 2010 64-0469-03 Rev A www.dialogic.com Copyright and legal notices Copyright 2000-2010 Dialogic Corporation. All Rights Reserved.

More information

Package Ridit. February 19, 2015

Package Ridit. February 19, 2015 Package Ridit February 19, 2015 Type Package Title Ridit Analysis (An extension of the Kruskal-Wallis Test.) Version 1.1 Date 2012-10-15 Author SeyedMahmood TaghaviShahri Maintainer SeyedMahmood TaghaviShahri

More information

Intermediate Programming in R Session 4: Avoiding Loops. Olivia Lau, PhD

Intermediate Programming in R Session 4: Avoiding Loops. Olivia Lau, PhD Intermediate Programming in R Session 4: Avoiding Loops Olivia Lau, PhD Outline Thinking in Parallel Vectorization Avoiding Loops with Homogenous Data Structures Avoiding Loops with Heterogenous Data Structures

More information

Regression Analysis and Linear Regression Models

Regression Analysis and Linear Regression Models Regression Analysis and Linear Regression Models University of Trento - FBK 2 March, 2015 (UNITN-FBK) Regression Analysis and Linear Regression Models 2 March, 2015 1 / 33 Relationship between numerical

More information

Package genderizer. July 5, 2015

Package genderizer. July 5, 2015 Type Package Title Gender Prediction Based on First Names Version 1.2.0 Date 2015-07-03 Package genderizer July 5, 2015 Utilizes the 'genderize.io' API to predict gender from first names extracted from

More information

Iteratively Re-weighted Least Squares for Sums of Convex Functions

Iteratively Re-weighted Least Squares for Sums of Convex Functions Iteratively Re-weighted Least Squares for Sums of Convex Functions James Burke University of Washington Jiashan Wang LinkedIn Frank Curtis Lehigh University Hao Wang Shanghai Tech University Daiwei He

More information

Package ThreeArmedTrials

Package ThreeArmedTrials Type Package Package ThreeArmedTrials August 29, 2016 Title Design and Analysis of Clinical Non-Inferiority or Superiority Trials with Active and Placebo Control Version 1.0-0 Date 2016-05-11 Author Tobias

More information

Union of Learned Sparsifying Transforms Based Low-Dose 3D CT Image Reconstruction

Union of Learned Sparsifying Transforms Based Low-Dose 3D CT Image Reconstruction Union of Learned Sparsifying Transforms Based Low-Dose 3D CT Image Reconstruction Xuehang Zheng 1, Saiprasad Ravishankar 2, Yong Long 1, Jeff Fessler 2 1 University of Michigan - Shanghai Jiao Tong University

More information

Package InformativeCensoring

Package InformativeCensoring Package InformativeCensoring August 29, 2016 Type Package Title Multiple Imputation for Informative Censoring Version 0.3.4 Maintainer Jonathan Bartlett Author David

More information