A Relationship Between the One-Way MANOVA Test Statistic and the Hotelling Lawley Trace Test Statistic
|
|
- Neal Houston
- 5 years ago
- Views:
Transcription
1 Iteratioal Joural of Statistics ad Probability Vol 7, No 6; 2018 A Relatioship Betwee the Oe-Way MANOVA Test Statistic ad the Hotellig Lawley Trace Test Statistic Hasthika S Rupasighe Arachchige Do Correspodece: Hasthika S Rupasighe Arachchige Do, Departmet of Mathematical Scieces, Appalachia State Uiversity, Booe, NC, 28607, USA Received: August 23, 2018 Accepted: September 28, 2018 Olie Published: October 15, 2018 doi:105539/ijspv76p124 URL: Abstract The Oe-Way MANOVA model is a special case of the multivariate liear model, ad this paper shows that the Oe-Way MANOVA test statistic ad the Hotellig Lawley trace test statistic are equivalet if the desig matrix is carefully chose Keywords: ANOVA, Liear Moldel 1 Itroductio We wat to show that the Oe-Way MANOVA test statistic ad the Hotellig Lawley trace test statistic are equivalet for a carefully chose full rak desig matrix First we will describe the MANOVA model, ad the the Oe-Way MANOVA model The otatio i this paper follows that used i Olive (2017) ad closely follows Rupasighe Arachchige Do (2017) 11 MANOVA Multivariate aalysis of variace (MANOVA) is aalogous to a ANOVA, but there is more tha oe depedet variable ANOVA tests for the differece i meas betwee two or more groups, while MANOVA tests for the differece i two or more vectors of meas The multivariate aalysis of variace (MANOVA) model y i = B T x i + ϵ i for i = 1,, has m 2 respose variables Y 1, Y m ad p predictor variables x 1, x 2,, x p The ith case is (x T i, yt i ) = (x i1,, x ip, Y i1,, Y im ) If a costat x i1 = 1 is i the model, the x i1 could be omitted from the case For the MANOVA model predictors are idicator variables Sometimes the trivial predictor 1 is also i the model The MANOVA model i matrix form is Z = XB + E ad has E(ϵ k ) = 0 ad Cov(ϵ k ) = Σϵ = (σ i j ) for k = 1,, Also E(e i ) = 0 while Cov(e i, e j ) = σ i j I for i, j = 1,, m The B ad Σϵ are ukow matrices to be estimated Z = Y 1,1 Y 1,2 Y 1,m Y 2,1 Y 2,2 Y 2,m Y,1 Y,2 Y,m = ( ) Y 1 Y 2 Y m = y T 1 y T The p matrix X is ot ecessarily of full rak p, ad where ofte v 1 = 1 X = x 1,1 x 1,2 x 1,p x 2,1 x 2,2 x 2,p x,1 x,2 x,p = ( ) v 1 v 2 v p = x T 1 x T The p m coefficiet matrix is B = β 1,1 β 1,2 β 1,m β 2,1 β 2,2 β 2,m β p,1 β p,2 β p,m = ( ) β 1 β 2 β m The m error matrix is 124
2 Iteratioal Joural of Statistics ad Probability Vol 7, No 6; 2018 ϵ 1,1 ϵ 1,2 ϵ 1,m ϵ 2,1 ϵ 2,2 ϵ 2,m ϵ,1 ϵ,2 ϵ,m E = = ( ) e 1 e 2 e m = ϵ T 1 ϵ T Each respose variable i a MANOVA model follows a ANOVA model Y j = Xβ j + e j for j = 1,, m, where it is assumed that E(e j ) = 0 ad Cov(e j ) = σ j j I MANOVA models are ofte fit by least squares The least squares estimator ˆB of B is ˆB = ( X T X ) X T Z = ( ˆβ 1 ˆβ 2 ˆβ m ) where ( X T X ) is a geeralized iverse of X T X If X has a full rak the ( X T X ) = ( X T X ) 1 ad ˆB is uique The predicted values or fitted values are Ẑ = X ˆB = ( ) Ŷ 1 Ŷ 2 Ŷ m = Ŷ 1,1 Ŷ 1,2 Ŷ 1,m Ŷ 2,1 Ŷ 2,2 Ŷ 2,m Ŷ,1 Ŷ,2 Ŷ,m The residuals are Ê = Z Ẑ = Z X ˆB Fially, ˆΣϵ = (Z Ẑ)T (Z Ẑ) p = ÊT Ê p 12 Oe Way MANOVA Assume that there are idepedet radom samples of size i from p differet populatios, or i cases are radomly assiged to p treatmet groups Let = p i be the total sample size Also assume that m respose variables y i j = (Y i j1,, Y i jm ) T are measured for the ith treatmet group ad the jth case Assume E(y i j ) = µ i ad Cov(y i j ) = Σϵ The oe way MANOVA is used to test H 0 : µ 1 = µ 2 = = µ p Note that if m = 1 the oe way MANOVA model becomes the oe way ANOVA model Oe might thik that performig m ANOVA tests is sufficiet to test the above hypotheses But the separate ANOVA tests would ot take the correlatio betwee the m variables ito accout O the other had the MANOVA test will take the correlatio ito accout i Let ȳ = p y i j/ be the overall mea Let ȳ i = i y i j/ i Several m m matrices will be useful Let S i be the sample covariace matrix correspodig to the ith treatmet group The the withi sum of squares ad cross products matrix is W = ( 1 1)S ( p 1)S p = p i (y i j y i )(y i j y i ) T The ˆΣϵ = W/( p) The treatmet or betwee sum of squares ad cross products matrix is B T = i (y i y)(y i y) T The total corrected (for the mea) sum of squares ad cross products matrix is T = B T + W = p i (y i j y)(y i j y) T Note that S = T/( 1) is the usual sample covariace matrix of the y i j if it is assumed that all of the y i j are iid so that the µ i µ for i = 1,, p The oe way MANOVA model is y i j = µ i + ϵ i j where ϵ i j are iid with E(ϵ i j ) = 0 ad Cov(ϵ i j ) = Σϵ The summary oe way MANOVA table is show bellow Source matrix df Treatmet or Betwee B T p 1 Residual or Error or Withi W p Total (Corrected) T 1 There are three commoly used test statistics to test the above hypotheses Namely, 125
3 Iteratioal Joural of Statistics ad Probability Vol 7, No 6; Hotellig Lawley trace statistic: U = tr(b T W 1 ) = tr(w 1 B T ) 2 Wilks lambda: Λ = W B T + W 3 Pillai s trace statistic: V = tr(b T T 1 ) = tr(t 1 B T ) If the y i j µ j are iid with commo covariace matrix Σϵ, ad if H 0 is true, the uder regularity coditios Fujikoshi (2002) showed 1 ( m p 1)U D χ 2 m(p 1), 2 [ 05(m + p 2)]log(Λ) D χ 2 m(p 1), ad 3 ( 1)V D χ 2 m(p 1) Note that the commo covariace matrix assumptio implies that each of the p treatmet groups or populatios has the same covariace matrix Σ i = Σϵ for i = 1,, p, a extremely strog assumptio Kakizawa (2009) ad Olive et al (2015) show that similar results hold for the multivariate liear model The commo covariace matrix assumptio, Cov(ϵ k ) = Σϵ for k = 1,,, is ofte reasoable for the multivariate liear regressio model 13 Hotellig Lawley Trace Test Hotellig Lawley trace test statistic Hotellig (1951); Lawley (1938), ad the asymptotic distributio ( m p 1)U D χ 2 m(p 1) by Fujikoshi (2002) are widely used Olive et al (2015) explais the large sample theory of the Wilks Λ, Pillai s trace, ad Hotellig Lawley trace test statistics ad gives two theorems to show that the Hotellig Lawley test geeralizes the usual partial F test for m = 1 respose variable to m 1 respose variables 2 Method 21 A Relatioship Betwee the Oe-Way MANOVA Test ad the Hotellig Lawley Trace Test A alterative method for Oe-Way MANOVA is to use the model Z = XB + E where Y i j = Y i j1 Y i jm = µ i + e i j, ad E[Y ij ] = µ i = for i = 1,, p ad j = 1,, i The X is a full rak where the ith colum of X is a idicator for group i 1 for i = 2,, p X = µ i j1 µ i jm, (1) 126
4 Iteratioal Joural of Statistics ad Probability Vol 7, No 6; 2018 B = The µ T p (µ 1 µ p ) T (µ p 1 µ p ) T ad let L = ( 0 I p 1 ) Note that Y T i j = µ T i + e T i j 1 2 p X T X = p 2 0 p 2 0 p p 1 (2) ad ( X T X ) 1 = 1 p p p p p p 1 (3) The the least squares estimator ˆB of B, ˆB = ȳ T p (ȳ 1 ȳ p ) T (ȳ p 1 ȳ p ) T, ad L ˆB = (ȳ 1 ȳ p ) T (ȳ 2 ȳ p ) T (ȳ p 1 ȳ p ) T The L ( X T X ) 1 L T becomes L ( X T X ) 1 L T = 1 p 1 + p p p p 1 (4) It ca be show that the iverse of the above matrix is [ L ( X T X ) ] 1 1 L T 1 = [ For coveiece, write L ( X T X ) ] 1 1 L T = 1 ( 1 ) p ( 2 ) p 1 1 p 1 2 p 1 p 1 ( p 1 ) p p 1 1 p 1 2 p 1 2 p p 1 The 127
5 Iteratioal Joural of Statistics ad Probability Vol 7, No 6; 2018 ( L ˆB ) [ T L ( X T X ) ] 1 1 ( L T L ˆB ) = 1 p 1 p 1 p 1 i j (ȳ i ȳ p )(ȳ j ȳ p ) T + i (ȳ i ȳ p )(ȳ i ȳ p ) T = H Let X be as i (1) The the multivariate liear regressio Hotellig Lawley test statistic for testig H 0 : LB = 0 versus H 0 : LB 0 has U = tr(w 1 H) Oe-Way MANOVA is used to test H 0 : µ 1 = µ 2 = = µ p The Oe-Way MANOVA Hotellig Lawley test statistic for testig for above hypotheses is U = tr(w 1 B T ) where W = ( p) ˆΣϵ ad B T = i (ȳ i ȳ)(ȳ i ȳ) T Theorem 1 The Oe-Way MANOVA ad the multivariate liear regressio Hotellig Lawley trace test statistics are the same for the desig matrix as i (1) To show that the above two test statistics are equal, it is sufficiet to prove that H = B T First we will prove two special cases ad the give the proof for the theorem Proof Special case I: p = 2 (Two group case) Cosider H H = (ȳ 1 ȳ 2 )(ȳ 1 ȳ 2 ) T + 1 (ȳ 1 ȳ 2 )(ȳ 1 ȳ 2 ) T Sice = 1 + 2, H = 1 ( )(ȳ 1 ȳ 2 )(ȳ 1 ȳ 2 ) T + 1 (ȳ 1 ȳ 2 )(ȳ 1 ȳ 2 ) T H = 1 (ȳ 1 ȳ 2 )(ȳ 1 ȳ 2 ) T (ȳ 1 ȳ 2 )(ȳ 1 ȳ 2 ) T + 1 (ȳ 1 ȳ 2 )(ȳ 1 ȳ 2 ) T H = 1 2 (ȳ 1 ȳ 2 )(ȳ 1 ȳ 2 ) T Now cosider B T with p = 2 Note that ȳ = ( 1 ȳ ȳ 2 )/ ad B T = 1 (ȳ 1 ȳ)(ȳ 1 ȳ) T + 2 (ȳ 2 ȳ)(ȳ 2 ȳ) T B T = 1 (ȳ ȳ 1 2 ȳ 2 )(ȳ 1 1 ȳ 1 2 ȳ 1 ) T + 2 (ȳ ȳ 1 2 ȳ 2 )(ȳ 2 1 ȳ 1 2 ȳ 2 ) T B T = (ȳ 2 1 ȳ 2 )(ȳ 1 ȳ 2 ) T (ȳ 2 1 ȳ 2 )(ȳ 1 ȳ 2 ) T B T = 1 2 (ȳ 1 ȳ 2 )(ȳ 1 ȳ 2 ) T Therefore B T = H whe p = 2 Proof Special case II: i = 1 i = 1,, p H = 1 p 1 p 1 p 1 i j (ȳ i ȳ p )(ȳ j ȳ p ) T + i (ȳ i ȳ p )(ȳ i ȳ p ) T Note that the i, j ruig from 1 through p 1 ad i, j ruig from 1 through p would yield the same H Therefore H ca be writte as H = 1 i j (ȳ i ȳ p )(ȳ j ȳ p ) T + i (ȳ i ȳ p )(ȳ i ȳ p ) T 128
6 Iteratioal Joural of Statistics ad Probability Vol 7, No 6; 2018 Now cosider the double sum i H Note that = 1 p ad 1 = 1 p i j (ȳ i ȳ p )(ȳ j ȳ p ) T = p (ȳi ȳ T j ȳ i ȳ T p ȳ p ȳ T j + ȳ p ȳp) T ) (ȳi ȳ T j + p ȳ i ȳt p + pȳ p ȳ T j p2 ȳ p ȳ T p (5) Now cosider the rest of H, 1 (ȳ i ȳ p )(ȳ i ȳ p ) T = 1 ȳ i ȳ T i 1 ȳ i ȳt p 1 ȳ p ȳ T i + 1pȳ p ȳ T p (6) Therefore by (5) ad (6), it is clear that H = 1 ȳ i ȳ T i 1 p ȳ i ȳ T j (7) Now cosider Let Therefore, B T becomes Ȳ = ȳ T 1 ȳ T 2 ȳ T p B T = 1 (ȳ i ȳ)(ȳ i ȳ) T (8) The B T = 1 [Ȳ T Ȳ 1 ] pȳt 11 T Ȳ B T = 1 ȳ i ȳ T i 1 p ȳ i ȳ T j (9) From (8) ad (9) B T = H Proof Geeral case: H = 1 i j (ȳ i ȳ p )(ȳ j ȳ p ) T + i (ȳ i ȳ p )(ȳ i ȳ p ) T First cosider the double sum i H 1 i j ȳ i ȳ T j i j (ȳ i ȳ p )(ȳ j ȳ p ) T = i j ȳ i ȳ T p + 1 i j ȳ p ȳ T j 1 T ȳpȳ p i j (10) 1 i ȳ i j ȳ T j + 1 i ȳ i j ȳ T p + 1 ȳp i j ȳ T j 1 T ȳpȳ p 2 129
7 Iteratioal Joural of Statistics ad Probability Vol 7, No 6; ȳȳt + 1 i ȳ i ȳ T p + 1 ȳp j ȳ T j ȳ p ȳ T p ȳȳ T + i ȳ i ȳ T p + ȳ p j ȳ T j ȳ p ȳ T p (11) Now cosider the rest of H, i (ȳ i ȳ p )(ȳ i ȳ p ) T = i ȳ i ȳ T i i ȳ i ȳ T p ȳ p i ȳ T i + ȳ p ȳ T p (12) Therefore by (11) ad (12) H = i ȳ i ȳ T i ȳȳ T (13) Now cosider B T = B T = i (ȳ i ȳ)(ȳ i ȳ) T i ȳ i ȳ T i i ȳ i ȳ T ȳ i ȳ T i + ȳȳ T B T = i ȳ i ȳ T i ȳȳ T ȳȳ T + ȳȳ T B T = i ȳ i ȳ T i ȳ i ȳ T (14) i (13) ad (14) proves that H = B T 22 Cell Meas Model We ca get the same result for the cell meas model which is defied for X ad B give below X = , B = µ T 1 µ T p ad L = ( I p 1 1 ) ˆB = ȳ T 1 ȳ T p, L ˆB = The X T X = diag ( ) ( ) 1,, p 1 ad (X T X) = diag 1,, p 1 (ȳ 1 ȳ p ) T (ȳ 2 ȳ p ) T (ȳ p 1 ȳ p ) T 130
8 Iteratioal Joural of Statistics ad Probability Vol 7, No 6; 2018 The L ( X T X ) 1 L T becomes L ( X T X ) 1 L T = 1 p 1 + p p p p 1 (15) Notice that the matrix equatio (15) is exactly same as (4) This is a idicatio that Theorem 1 does ot deped o the full rak desig matrix 3 Coclusios This work mathematically proved that the Oe-Way MANOVA test statistic ad the Hotellig Lawley trace test statistic are i fact the same The proof cosisted of two special cases ad the geeral case This result idicates that oe ca use the Oe-Way MANOVA test statistic ad the Hotellig Lawley trace test statistic alteratively if the desig matrix is carefully chose Ackowledgemets The author thaks Dr David J Olive ad Dr Lasathi C R Pelawa Watagoda for some commets o this paper Refereces Fujikoshi, Y (2002) Asymptotic expasios for the distributios of multivariate basic statistics ad oe-way MANOVA tests uder oormality Joural of Statistical Plaig ad Iferece, 108(1), Hotellig, H (1951) A geeralized T test ad measure of multivariate dispersio I J Neyma (Ed), Proceedigs of the Secod Berkeley Symposium o Mathematical Statistics ad Probability (pp 23-41) Berkeley: Uiversity of Califoria Press Kakizawa, Y (2009) Third-order power comparisos for a class of tests for multivariate liear hypothesis uder geeral distributios Joural of Multivariate Aalysis, 100(3), Lawley, D N (1938) A geeralizatio of Fisher s z-test Biometrika, 30, Olive, D J (2017) Robust Multivariate Aalysis Spriger Iteratioal Publishig Olive, D J, Pelawa, W L C R, & Rupasighe, A D H S (2015) Visualizig ad Testig the Multivariate Liear Regressio Model Iteratioal Joural of Statistics ad Probability, 4(1), Rupasighe Arachchige Do, H S (2017) Bootstrappig Aalogs of the Oe Way MANOVA Test (PhD Thesis), Souther Illiois Uiversity, USA, at ( Copyrights Copyright for this article is retaied by the author(s), with first publicatio rights grated to the joural This is a ope-access article distributed uder the terms ad coditios of the Creative Commos Attributio licese ( 131
Agenda: Recap. Lecture. Chapter 12. Homework. Chapt 12 #1, 2, 3 SAS Problems 3 & 4 by hand. Marquette University MATH 4740/MSCS 5740
Ageda: Recap. Lecture. Chapter Homework. Chapt #,, 3 SAS Problems 3 & 4 by had. Copyright 06 by D.B. Rowe Recap. 6: Statistical Iferece: Procedures for μ -μ 6. Statistical Iferece Cocerig μ -μ Recall yes
More informationLinear regression. Daniel Hsu (COMS 4771) (y i x T i β)2 2πσ. 2 2σ 2. 1 n. (x T i β y i ) 2. 1 ˆβ arg min. β R n d
Liear regressio Daiel Hsu (COMS 477) Maximum likelihood estimatio Oe of the simplest liear regressio models is the followig: (X, Y ),..., (X, Y ), (X, Y ) are iid radom pairs takig values i R d R, ad Y
More information3/3/2014. CDS M Phil Econometrics. Types of Relationships. Types of Relationships. Types of Relationships. Vijayamohanan Pillai N.
3/3/04 CDS M Phil Old Least Squares (OLS) Vijayamohaa Pillai N CDS M Phil Vijayamoha CDS M Phil Vijayamoha Types of Relatioships Oly oe idepedet variable, Relatioship betwee ad is Liear relatioships Curviliear
More informationProperties and Hypothesis Testing
Chapter 3 Properties ad Hypothesis Testig 3.1 Types of data The regressio techiques developed i previous chapters ca be applied to three differet kids of data. 1. Cross-sectioal data. 2. Time series data.
More informationChapter 13, Part A Analysis of Variance and Experimental Design
Slides Prepared by JOHN S. LOUCKS St. Edward s Uiversity Slide 1 Chapter 13, Part A Aalysis of Variace ad Eperimetal Desig Itroductio to Aalysis of Variace Aalysis of Variace: Testig for the Equality of
More informationInvestigating the Significance of a Correlation Coefficient using Jackknife Estimates
Iteratioal Joural of Scieces: Basic ad Applied Research (IJSBAR) ISSN 2307-4531 (Prit & Olie) http://gssrr.org/idex.php?joural=jouralofbasicadapplied ---------------------------------------------------------------------------------------------------------------------------
More informationAlgebra of Least Squares
October 19, 2018 Algebra of Least Squares Geometry of Least Squares Recall that out data is like a table [Y X] where Y collects observatios o the depedet variable Y ad X collects observatios o the k-dimesioal
More informationEXAMINATIONS OF THE ROYAL STATISTICAL SOCIETY
EXAMINATIONS OF THE ROYAL STATISTICAL SOCIETY HIGHER CERTIFICATE IN STATISTICS, 017 MODULE 4 : Liear models Time allowed: Oe ad a half hours Cadidates should aswer THREE questios. Each questio carries
More informationMatrix Representation of Data in Experiment
Matrix Represetatio of Data i Experimet Cosider a very simple model for resposes y ij : y ij i ij, i 1,; j 1,,..., (ote that for simplicity we are assumig the two () groups are of equal sample size ) Y
More informationSection 14. Simple linear regression.
Sectio 14 Simple liear regressio. Let us look at the cigarette dataset from [1] (available to dowload from joural s website) ad []. The cigarette dataset cotais measuremets of tar, icotie, weight ad carbo
More informationCEE 522 Autumn Uncertainty Concepts for Geotechnical Engineering
CEE 5 Autum 005 Ucertaity Cocepts for Geotechical Egieerig Basic Termiology Set A set is a collectio of (mutually exclusive) objects or evets. The sample space is the (collectively exhaustive) collectio
More informationSIMPLE LINEAR REGRESSION AND CORRELATION ANALYSIS
SIMPLE LINEAR REGRESSION AND CORRELATION ANALSIS INTRODUCTION There are lot of statistical ivestigatio to kow whether there is a relatioship amog variables Two aalyses: (1) regressio aalysis; () correlatio
More information1 Inferential Methods for Correlation and Regression Analysis
1 Iferetial Methods for Correlatio ad Regressio Aalysis I the chapter o Correlatio ad Regressio Aalysis tools for describig bivariate cotiuous data were itroduced. The sample Pearso Correlatio Coefficiet
More information(all terms are scalars).the minimization is clearer in sum notation:
7 Multiple liear regressio: with predictors) Depedet data set: y i i = 1, oe predictad, predictors x i,k i = 1,, k = 1, ' The forecast equatio is ŷ i = b + Use matrix otatio: k =1 b k x ik Y = y 1 y 1
More information11 Correlation and Regression
11 Correlatio Regressio 11.1 Multivariate Data Ofte we look at data where several variables are recorded for the same idividuals or samplig uits. For example, at a coastal weather statio, we might record
More informationOpen book and notes. 120 minutes. Cover page and six pages of exam. No calculators.
IE 330 Seat # Ope book ad otes 120 miutes Cover page ad six pages of exam No calculators Score Fial Exam (example) Schmeiser Ope book ad otes No calculator 120 miutes 1 True or false (for each, 2 poits
More informationGeometry of LS. LECTURE 3 GEOMETRY OF LS, PROPERTIES OF σ 2, PARTITIONED REGRESSION, GOODNESS OF FIT
OCTOBER 7, 2016 LECTURE 3 GEOMETRY OF LS, PROPERTIES OF σ 2, PARTITIONED REGRESSION, GOODNESS OF FIT Geometry of LS We ca thik of y ad the colums of X as members of the -dimesioal Euclidea space R Oe ca
More informationChapter 1 Simple Linear Regression (part 6: matrix version)
Chapter Simple Liear Regressio (part 6: matrix versio) Overview Simple liear regressio model: respose variable Y, a sigle idepedet variable X Y β 0 + β X + ε Multiple liear regressio model: respose Y,
More informationThis is an introductory course in Analysis of Variance and Design of Experiments.
1 Notes for M 384E, Wedesday, Jauary 21, 2009 (Please ote: I will ot pass out hard-copy class otes i future classes. If there are writte class otes, they will be posted o the web by the ight before class
More informationStatistical Properties of OLS estimators
1 Statistical Properties of OLS estimators Liear Model: Y i = β 0 + β 1 X i + u i OLS estimators: β 0 = Y β 1X β 1 = Best Liear Ubiased Estimator (BLUE) Liear Estimator: β 0 ad β 1 are liear fuctio of
More informationBecause it tests for differences between multiple pairs of means in one test, it is called an omnibus test.
Math 308 Sprig 018 Classes 19 ad 0: Aalysis of Variace (ANOVA) Page 1 of 6 Itroductio ANOVA is a statistical procedure for determiig whether three or more sample meas were draw from populatios with equal
More information2 1. The r.s., of size n2, from population 2 will be. 2 and 2. 2) The two populations are independent. This implies that all of the n1 n2
Chapter 8 Comparig Two Treatmets Iferece about Two Populatio Meas We wat to compare the meas of two populatios to see whether they differ. There are two situatios to cosider, as show i the followig examples:
More informationt distribution [34] : used to test a mean against an hypothesized value (H 0 : µ = µ 0 ) or the difference
EXST30 Backgroud material Page From the textbook The Statistical Sleuth Mea [0]: I your text the word mea deotes a populatio mea (µ) while the work average deotes a sample average ( ). Variace [0]: The
More informationRegression, Inference, and Model Building
Regressio, Iferece, ad Model Buildig Scatter Plots ad Correlatio Correlatio coefficiet, r -1 r 1 If r is positive, the the scatter plot has a positive slope ad variables are said to have a positive relatioship
More informationSimple Linear Regression
Simple Liear Regressio 1. Model ad Parameter Estimatio (a) Suppose our data cosist of a collectio of pairs (x i, y i ), where x i is a observed value of variable X ad y i is the correspodig observatio
More information11 THE GMM ESTIMATION
Cotets THE GMM ESTIMATION 2. Cosistecy ad Asymptotic Normality..................... 3.2 Regularity Coditios ad Idetificatio..................... 4.3 The GMM Iterpretatio of the OLS Estimatio.................
More informationx iu i E(x u) 0. In order to obtain a consistent estimator of β, we find the instrumental variable z which satisfies E(z u) = 0. z iu i E(z u) = 0.
27 However, β MM is icosistet whe E(x u) 0, i.e., β MM = (X X) X y = β + (X X) X u = β + ( X X ) ( X u ) \ β. Note as follows: X u = x iu i E(x u) 0. I order to obtai a cosistet estimator of β, we fid
More informationUniversity of California, Los Angeles Department of Statistics. Simple regression analysis
Uiversity of Califoria, Los Ageles Departmet of Statistics Statistics 100C Istructor: Nicolas Christou Simple regressio aalysis Itroductio: Regressio aalysis is a statistical method aimig at discoverig
More informationS Y Y = ΣY 2 n. Using the above expressions, the correlation coefficient is. r = SXX S Y Y
1 Sociology 405/805 Revised February 4, 004 Summary of Formulae for Bivariate Regressio ad Correlatio Let X be a idepedet variable ad Y a depedet variable, with observatios for each of the values of these
More informationSTATISTICAL PROPERTIES OF LEAST SQUARES ESTIMATORS. Comments:
Recall: STATISTICAL PROPERTIES OF LEAST SQUARES ESTIMATORS Commets:. So far we have estimates of the parameters! 0 ad!, but have o idea how good these estimates are. Assumptio: E(Y x)! 0 +! x (liear coditioal
More informationBayesian Methods: Introduction to Multi-parameter Models
Bayesia Methods: Itroductio to Multi-parameter Models Parameter: θ = ( θ, θ) Give Likelihood p(y θ) ad prior p(θ ), the posterior p proportioal to p(y θ) x p(θ ) Margial posterior ( θ, θ y) is Iterested
More informationMA Advanced Econometrics: Properties of Least Squares Estimators
MA Advaced Ecoometrics: Properties of Least Squares Estimators Karl Whela School of Ecoomics, UCD February 5, 20 Karl Whela UCD Least Squares Estimators February 5, 20 / 5 Part I Least Squares: Some Fiite-Sample
More informationTAMS24: Notations and Formulas
TAMS4: Notatios ad Formulas Basic otatios ad defiitios X: radom variable stokastiska variabel Mea Vätevärde: µ = X = by Xiagfeg Yag kpx k, if X is discrete, xf Xxdx, if X is cotiuous Variace Varias: =
More information[412] A TEST FOR HOMOGENEITY OF THE MARGINAL DISTRIBUTIONS IN A TWO-WAY CLASSIFICATION
[412] A TEST FOR HOMOGENEITY OF THE MARGINAL DISTRIBUTIONS IN A TWO-WAY CLASSIFICATION BY ALAN STUART Divisio of Research Techiques, Lodo School of Ecoomics 1. INTRODUCTION There are several circumstaces
More informationECONOMETRIC THEORY. MODULE XIII Lecture - 34 Asymptotic Theory and Stochastic Regressors
ECONOMETRIC THEORY MODULE XIII Lecture - 34 Asymptotic Theory ad Stochastic Regressors Dr. Shalabh Departmet of Mathematics ad Statistics Idia Istitute of Techology Kapur Asymptotic theory The asymptotic
More informationTable 12.1: Contingency table. Feature b. 1 N 11 N 12 N 1b 2 N 21 N 22 N 2b. ... a N a1 N a2 N ab
Sectio 12 Tests of idepedece ad homogeeity I this lecture we will cosider a situatio whe our observatios are classified by two differet features ad we would like to test if these features are idepedet
More informationEfficient GMM LECTURE 12 GMM II
DECEMBER 1 010 LECTURE 1 II Efficiet The estimator depeds o the choice of the weight matrix A. The efficiet estimator is the oe that has the smallest asymptotic variace amog all estimators defied by differet
More informationStat 319 Theory of Statistics (2) Exercises
Kig Saud Uiversity College of Sciece Statistics ad Operatios Research Departmet Stat 39 Theory of Statistics () Exercises Refereces:. Itroductio to Mathematical Statistics, Sixth Editio, by R. Hogg, J.
More informationCommon Large/Small Sample Tests 1/55
Commo Large/Small Sample Tests 1/55 Test of Hypothesis for the Mea (σ Kow) Covert sample result ( x) to a z value Hypothesis Tests for µ Cosider the test H :μ = μ H 1 :μ > μ σ Kow (Assume the populatio
More informationImproved Class of Ratio -Cum- Product Estimators of Finite Population Mean in two Phase Sampling
Global Joural of Sciece Frotier Research: F Mathematics ad Decisio Scieces Volume 4 Issue 2 Versio.0 Year 204 Type : Double Blid Peer Reviewed Iteratioal Research Joural Publisher: Global Jourals Ic. (USA
More informationDr. Maddah ENMG 617 EM Statistics 11/26/12. Multiple Regression (2) (Chapter 15, Hines)
Dr Maddah NMG 617 M Statistics 11/6/1 Multiple egressio () (Chapter 15, Hies) Test for sigificace of regressio This is a test to determie whether there is a liear relatioship betwee the depedet variable
More informationTABLES AND FORMULAS FOR MOORE Basic Practice of Statistics
TABLES AND FORMULAS FOR MOORE Basic Practice of Statistics Explorig Data: Distributios Look for overall patter (shape, ceter, spread) ad deviatios (outliers). Mea (use a calculator): x = x 1 + x 2 + +
More informationChapters 5 and 13: REGRESSION AND CORRELATION. Univariate data: x, Bivariate data (x,y).
Chapters 5 ad 13: REGREION AND CORRELATION (ectios 5.5 ad 13.5 are omitted) Uivariate data: x, Bivariate data (x,y). Example: x: umber of years studets studied paish y: score o a proficiecy test For each
More informationAdditional Notes and Computational Formulas CHAPTER 3
Additioal Notes ad Computatioal Formulas APPENDIX CHAPTER 3 1 The Greek capital sigma is the mathematical sig for summatio If we have a sample of observatios say y 1 y 2 y 3 y their sum is y 1 + y 2 +
More informationIt should be unbiased, or approximately unbiased. Variance of the variance estimator should be small. That is, the variance estimator is stable.
Chapter 10 Variace Estimatio 10.1 Itroductio Variace estimatio is a importat practical problem i survey samplig. Variace estimates are used i two purposes. Oe is the aalytic purpose such as costructig
More informationSTA Learning Objectives. Population Proportions. Module 10 Comparing Two Proportions. Upon completing this module, you should be able to:
STA 2023 Module 10 Comparig Two Proportios Learig Objectives Upo completig this module, you should be able to: 1. Perform large-sample ifereces (hypothesis test ad cofidece itervals) to compare two populatio
More informationLecture 22: Review for Exam 2. 1 Basic Model Assumptions (without Gaussian Noise)
Lecture 22: Review for Exam 2 Basic Model Assumptios (without Gaussia Noise) We model oe cotiuous respose variable Y, as a liear fuctio of p umerical predictors, plus oise: Y = β 0 + β X +... β p X p +
More informationAsymptotic Results for the Linear Regression Model
Asymptotic Results for the Liear Regressio Model C. Fli November 29, 2000 1. Asymptotic Results uder Classical Assumptios The followig results apply to the liear regressio model y = Xβ + ε, where X is
More informationSummary. Recap ... Last Lecture. Summary. Theorem
Last Lecture Biostatistics 602 - Statistical Iferece Lecture 23 Hyu Mi Kag April 11th, 2013 What is p-value? What is the advatage of p-value compared to hypothesis testig procedure with size α? How ca
More informationUNIVERSITY OF TORONTO Faculty of Arts and Science APRIL/MAY 2009 EXAMINATIONS ECO220Y1Y PART 1 OF 2 SOLUTIONS
PART of UNIVERSITY OF TORONTO Faculty of Arts ad Sciece APRIL/MAY 009 EAMINATIONS ECO0YY PART OF () The sample media is greater tha the sample mea whe there is. (B) () A radom variable is ormally distributed
More informationA statistical method to determine sample size to estimate characteristic value of soil parameters
A statistical method to determie sample size to estimate characteristic value of soil parameters Y. Hojo, B. Setiawa 2 ad M. Suzuki 3 Abstract Sample size is a importat factor to be cosidered i determiig
More informationON POINTWISE BINOMIAL APPROXIMATION
Iteratioal Joural of Pure ad Applied Mathematics Volume 71 No. 1 2011, 57-66 ON POINTWISE BINOMIAL APPROXIMATION BY w-functions K. Teerapabolar 1, P. Wogkasem 2 Departmet of Mathematics Faculty of Sciece
More informationStatistical Inference Based on Extremum Estimators
T. Rotheberg Fall, 2007 Statistical Iferece Based o Extremum Estimators Itroductio Suppose 0, the true value of a p-dimesioal parameter, is kow to lie i some subset S R p : Ofte we choose to estimate 0
More informationPOLS, GLS, FGLS, GMM. Outline of Linear Systems of Equations. Common Coefficients, Panel Data Model. Preliminaries
Outlie of Liear Systems of Equatios POLS, GLS, FGLS, GMM Commo Coefficiets, Pael Data Model Prelimiaries he liear pael data model is a static model because all explaatory variables are dated cotemporaeously
More informationLecture Notes 15 Hypothesis Testing (Chapter 10)
1 Itroductio Lecture Notes 15 Hypothesis Testig Chapter 10) Let X 1,..., X p θ x). Suppose we we wat to kow if θ = θ 0 or ot, where θ 0 is a specific value of θ. For example, if we are flippig a coi, we
More informationTMA4245 Statistics. Corrected 30 May and 4 June Norwegian University of Science and Technology Department of Mathematical Sciences.
Norwegia Uiversity of Sciece ad Techology Departmet of Mathematical Scieces Corrected 3 May ad 4 Jue Solutios TMA445 Statistics Saturday 6 May 9: 3: Problem Sow desity a The probability is.9.5 6x x dx
More informationComparison of Minimum Initial Capital with Investment and Non-investment Discrete Time Surplus Processes
The 22 d Aual Meetig i Mathematics (AMM 207) Departmet of Mathematics, Faculty of Sciece Chiag Mai Uiversity, Chiag Mai, Thailad Compariso of Miimum Iitial Capital with Ivestmet ad -ivestmet Discrete Time
More informationStatistics 20: Final Exam Solutions Summer Session 2007
1. 20 poits Testig for Diabetes. Statistics 20: Fial Exam Solutios Summer Sessio 2007 (a) 3 poits Give estimates for the sesitivity of Test I ad of Test II. Solutio: 156 patiets out of total 223 patiets
More informationTopic 9: Sampling Distributions of Estimators
Topic 9: Samplig Distributios of Estimators Course 003, 2016 Page 0 Samplig distributios of estimators Sice our estimators are statistics (particular fuctios of radom variables), their distributio ca be
More informationSummary and Discussion on Simultaneous Analysis of Lasso and Dantzig Selector
Summary ad Discussio o Simultaeous Aalysis of Lasso ad Datzig Selector STAT732, Sprig 28 Duzhe Wag May 4, 28 Abstract This is a discussio o the work i Bickel, Ritov ad Tsybakov (29). We begi with a short
More informationECE 901 Lecture 12: Complexity Regularization and the Squared Loss
ECE 90 Lecture : Complexity Regularizatio ad the Squared Loss R. Nowak 5/7/009 I the previous lectures we made use of the Cheroff/Hoeffdig bouds for our aalysis of classifier errors. Hoeffdig s iequality
More informationLesson 11: Simple Linear Regression
Lesso 11: Simple Liear Regressio Ka-fu WONG December 2, 2004 I previous lessos, we have covered maily about the estimatio of populatio mea (or expected value) ad its iferece. Sometimes we are iterested
More informationContinuous Data that can take on any real number (time/length) based on sample data. Categorical data can only be named or categorised
Questio 1. (Topics 1-3) A populatio cosists of all the members of a group about which you wat to draw a coclusio (Greek letters (μ, σ, Ν) are used) A sample is the portio of the populatio selected for
More informationStat 139 Homework 7 Solutions, Fall 2015
Stat 139 Homework 7 Solutios, Fall 2015 Problem 1. I class we leared that the classical simple liear regressio model assumes the followig distributio of resposes: Y i = β 0 + β 1 X i + ɛ i, i = 1,...,,
More informationSlide Set 13 Linear Model with Endogenous Regressors and the GMM estimator
Slide Set 13 Liear Model with Edogeous Regressors ad the GMM estimator Pietro Coretto pcoretto@uisa.it Ecoometrics Master i Ecoomics ad Fiace (MEF) Uiversità degli Studi di Napoli Federico II Versio: Friday
More informationResampling Methods. X (1/2), i.e., Pr (X i m) = 1/2. We order the data: X (1) X (2) X (n). Define the sample median: ( n.
Jauary 1, 2019 Resamplig Methods Motivatio We have so may estimators with the property θ θ d N 0, σ 2 We ca also write θ a N θ, σ 2 /, where a meas approximately distributed as Oce we have a cosistet estimator
More informationUniversity of California, Los Angeles Department of Statistics. Practice problems - simple regression 2 - solutions
Uiversity of Califoria, Los Ageles Departmet of Statistics Statistics 00C Istructor: Nicolas Christou EXERCISE Aswer the followig questios: Practice problems - simple regressio - solutios a Suppose y,
More information5. Fractional Hot deck Imputation
5. Fractioal Hot deck Imputatio Itroductio Suppose that we are iterested i estimatig θ EY or eve θ 2 P ry < c where y fy x where x is always observed ad y is subject to missigess. Assume MAR i the sese
More informationRank tests and regression rank scores tests in measurement error models
Rak tests ad regressio rak scores tests i measuremet error models J. Jurečková ad A.K.Md.E. Saleh Charles Uiversity i Prague ad Carleto Uiversity i Ottawa Abstract The rak ad regressio rak score tests
More informationSTP 226 ELEMENTARY STATISTICS
TP 6 TP 6 ELEMENTARY TATITIC CHAPTER 4 DECRIPTIVE MEAURE IN REGREION AND CORRELATION Liear Regressio ad correlatio allows us to examie the relatioship betwee two or more quatitative variables. 4.1 Liear
More informationGoodness-of-Fit Tests and Categorical Data Analysis (Devore Chapter Fourteen)
Goodess-of-Fit Tests ad Categorical Data Aalysis (Devore Chapter Fourtee) MATH-252-01: Probability ad Statistics II Sprig 2019 Cotets 1 Chi-Squared Tests with Kow Probabilities 1 1.1 Chi-Squared Testig................
More informationRandom Variables, Sampling and Estimation
Chapter 1 Radom Variables, Samplig ad Estimatio 1.1 Itroductio This chapter will cover the most importat basic statistical theory you eed i order to uderstad the ecoometric material that will be comig
More informationThoughts on Interaction
Thoughts o Iteractio Roald Christese Departmet of Mathematics ad Statistics Uiversity of New Mexico November 16, 2016 Abstract KEY WORDS: 0 The first sectio examies iteractios i a ubalaced two-way ANOVA.
More informationFirst Year Quantitative Comp Exam Spring, Part I - 203A. f X (x) = 0 otherwise
First Year Quatitative Comp Exam Sprig, 2012 Istructio: There are three parts. Aswer every questio i every part. Questio I-1 Part I - 203A A radom variable X is distributed with the margial desity: >
More informationUNIVERSITY OF NORTH CAROLINA Department of Statistics Chapel Hill, N. C. FOR MULTIVARIATE POPULATIONS. J. N. Srivastava.
UNIVERSITY OF NORTH CAROLINA Departmet of Statistics Chapel Hill N. C. A NOTE ON THE BEST LINEAR UNBIASED ESTIMATES FOR MULTIVARIATE POPULATIONS by J. N. Srivastava November 1962 Cotract No. AF 49(638)-213
More informationRandom assignment with integer costs
Radom assigmet with iteger costs Robert Parviaie Departmet of Mathematics, Uppsala Uiversity P.O. Box 480, SE-7506 Uppsala, Swede robert.parviaie@math.uu.se Jue 4, 200 Abstract The radom assigmet problem
More informationLecture 7: Properties of Random Samples
Lecture 7: Properties of Radom Samples 1 Cotiued From Last Class Theorem 1.1. Let X 1, X,...X be a radom sample from a populatio with mea µ ad variace σ
More informationOverview. p 2. Chapter 9. Pooled Estimate of. q = 1 p. Notation for Two Proportions. Inferences about Two Proportions. Assumptions
Chapter 9 Slide Ifereces from Two Samples 9- Overview 9- Ifereces about Two Proportios 9- Ifereces about Two Meas: Idepedet Samples 9-4 Ifereces about Matched Pairs 9-5 Comparig Variatio i Two Samples
More informationGrant MacEwan University STAT 252 Dr. Karen Buro Formula Sheet
Grat MacEwa Uiversity STAT 5 Dr. Kare Buro Formula Sheet Descriptive Statistics Sample Mea: x = x i i= Sample Variace: s = i= (x i x) = Σ i=x i (Σ i= x i) Sample Stadard Deviatio: s = Sample Variace =
More informationSimple Linear Regression
Chapter 2 Simple Liear Regressio 2.1 Simple liear model The simple liear regressio model shows how oe kow depedet variable is determied by a sigle explaatory variable (regressor). Is is writte as: Y i
More informationSample Size Estimation in the Proportional Hazards Model for K-sample or Regression Settings Scott S. Emerson, M.D., Ph.D.
ample ie Estimatio i the Proportioal Haards Model for K-sample or Regressio ettigs cott. Emerso, M.D., Ph.D. ample ie Formula for a Normally Distributed tatistic uppose a statistic is kow to be ormally
More informationQuick Review of Probability
Quick Review of Probability Berli Che Departmet of Computer Sciece & Iformatio Egieerig Natioal Taiwa Normal Uiversity Refereces: 1. W. Navidi. Statistics for Egieerig ad Scietists. Chapter & Teachig Material.
More informationLinear Regression Models
Liear Regressio Models Dr. Joh Mellor-Crummey Departmet of Computer Sciece Rice Uiversity johmc@cs.rice.edu COMP 528 Lecture 9 15 February 2005 Goals for Today Uderstad how to Use scatter diagrams to ispect
More informationSimple Regression. Acknowledgement. These slides are based on presentations created and copyrighted by Prof. Daniel Menasce (GMU) CS 700
Simple Regressio CS 7 Ackowledgemet These slides are based o presetatios created ad copyrighted by Prof. Daiel Measce (GMU) Basics Purpose of regressio aalysis: predict the value of a depedet or respose
More informationHAJEK-RENYI-TYPE INEQUALITY FOR SOME NONMONOTONIC FUNCTIONS OF ASSOCIATED RANDOM VARIABLES
HAJEK-RENYI-TYPE INEQUALITY FOR SOME NONMONOTONIC FUNCTIONS OF ASSOCIATED RANDOM VARIABLES ISHA DEWAN AND B. L. S. PRAKASA RAO Received 1 April 005; Revised 6 October 005; Accepted 11 December 005 Let
More informationResearch Article A Unified Weight Formula for Calculating the Sample Variance from Weighted Successive Differences
Discrete Dyamics i Nature ad Society Article ID 210761 4 pages http://dxdoiorg/101155/2014/210761 Research Article A Uified Weight Formula for Calculatig the Sample Variace from Weighted Successive Differeces
More informationChapter 6 Sampling Distributions
Chapter 6 Samplig Distributios 1 I most experimets, we have more tha oe measuremet for ay give variable, each measuremet beig associated with oe radomly selected a member of a populatio. Hece we eed to
More informationLecture 8: Non-parametric Comparison of Location. GENOME 560, Spring 2016 Doug Fowler, GS
Lecture 8: No-parametric Compariso of Locatio GENOME 560, Sprig 2016 Doug Fowler, GS (dfowler@uw.edu) 1 Review What do we mea by oparametric? What is a desirable locatio statistic for ordial data? What
More informationStat 200 -Testing Summary Page 1
Stat 00 -Testig Summary Page 1 Mathematicias are like Frechme; whatever you say to them, they traslate it ito their ow laguage ad forthwith it is somethig etirely differet Goethe 1 Large Sample Cofidece
More informationComparing Two Populations. Topic 15 - Two Sample Inference I. Comparing Two Means. Comparing Two Pop Means. Background Reading
Topic 15 - Two Sample Iferece I STAT 511 Professor Bruce Craig Comparig Two Populatios Research ofte ivolves the compariso of two or more samples from differet populatios Graphical summaries provide visual
More informationUCLA STAT 110B Applied Statistics for Engineering and the Sciences
UCLA STAT 110B Applied Statistics for Egieerig ad the Scieces Istructor: Ivo Diov, Asst. Prof. I Statistics ad Neurology Teachig Assistats: Bria Ng, UCLA Statistics Uiversity of Califoria, Los Ageles,
More informationWorksheet 23 ( ) Introduction to Simple Linear Regression (continued)
Worksheet 3 ( 11.5-11.8) Itroductio to Simple Liear Regressio (cotiued) This worksheet is a cotiuatio of Discussio Sheet 3; please complete that discussio sheet first if you have ot already doe so. This
More informationECON 3150/4150, Spring term Lecture 3
Itroductio Fidig the best fit by regressio Residuals ad R-sq Regressio ad causality Summary ad ext step ECON 3150/4150, Sprig term 2014. Lecture 3 Ragar Nymoe Uiversity of Oslo 21 Jauary 2014 1 / 30 Itroductio
More informationA proposed discrete distribution for the statistical modeling of
It. Statistical Ist.: Proc. 58th World Statistical Cogress, 0, Dubli (Sessio CPS047) p.5059 A proposed discrete distributio for the statistical modelig of Likert data Kidd, Marti Cetre for Statistical
More informationThe standard deviation of the mean
Physics 6C Fall 20 The stadard deviatio of the mea These otes provide some clarificatio o the distictio betwee the stadard deviatio ad the stadard deviatio of the mea.. The sample mea ad variace Cosider
More informationThe variance of a sum of independent variables is the sum of their variances, since covariances are zero. Therefore. V (xi )= n n 2 σ2 = σ2.
SAMPLE STATISTICS A radom sample x 1,x,,x from a distributio f(x) is a set of idepedetly ad idetically variables with x i f(x) for all i Their joit pdf is f(x 1,x,,x )=f(x 1 )f(x ) f(x )= f(x i ) The sample
More informationRandom Matrices with Blocks of Intermediate Scale Strongly Correlated Band Matrices
Radom Matrices with Blocks of Itermediate Scale Strogly Correlated Bad Matrices Jiayi Tog Advisor: Dr. Todd Kemp May 30, 07 Departmet of Mathematics Uiversity of Califoria, Sa Diego Cotets Itroductio Notatio
More informationLecture 7: October 18, 2017
Iformatio ad Codig Theory Autum 207 Lecturer: Madhur Tulsiai Lecture 7: October 8, 207 Biary hypothesis testig I this lecture, we apply the tools developed i the past few lectures to uderstad the problem
More informationMOMENT-METHOD ESTIMATION BASED ON CENSORED SAMPLE
Vol. 8 o. Joural of Systems Sciece ad Complexity Apr., 5 MOMET-METHOD ESTIMATIO BASED O CESORED SAMPLE I Zhogxi Departmet of Mathematics, East Chia Uiversity of Sciece ad Techology, Shaghai 37, Chia. Email:
More informationSession 5. (1) Principal component analysis and Karhunen-Loève transformation
200 Autum semester Patter Iformatio Processig Topic 2 Image compressio by orthogoal trasformatio Sessio 5 () Pricipal compoet aalysis ad Karhue-Loève trasformatio Topic 2 of this course explais the image
More information