Week 10 Spring Lecture 19. Estimation of Large Covariance Matrices: Upper bound Observe. is contained in the following parameter space,
|
|
- Sarah Daniels
- 5 years ago
- Views:
Transcription
1 Week 0 Sprig 009 Lecture 9. stiatio of Large Covariace Matrices: Upper boud Observe ; ; : : : ; i.i.d. fro a p-variate Gaussia distributio, N (; pp ). We assue that the covariace atrix pp = ( ij ) i;jp is cotaied i the foowig paraeter space, : jij j M ji jj (+) for a k (; "; M) = () ad ax () =" Theore Uder the assuptio (0), we have og p if ^ C og p + + C : () + + This theore tes us that there is a estiator ^ to obtai the rate. I the ext ecture we wi show this rate ca ot be iproved. This resut iproves the rate og p + i Theore i Bicke ad Levia (008a). Whe = = ad p = e p, their rate is 6, whie the rate i Theore 5 is. The key reaso for such a iproveet is that we reaized atrix estiatio is fudaetay di eret fro vector estiatio! stiatio Procedure: De e ad for a itegers = (~ ij I f i < + ; j < + g) pp S () = p = p ad. We estiate by ^ = k S (k) S (k). (3) We wi set k + for the operator or ad (+) for the robeius or. Techicay it is reativey easier to study this risk upper of the taperig estiator uder the operator or tha the usua badig estiator. Lea We have ^ = (w ij ~ ij ) pp where w ij = k f(k ji jj) + (k ji jj) + g.
2 Note that 8 < whe ji jj k w ij = k f(k ji jj) + (k ji jj) + g = (0; ) whe k < ji jj < k : 0 otherwise. Now we estabish the risk upper boud for the estiator i equatio (3) uder the operator or. We show that the variace part, ad the bias part, thus which ipies by settig ^ ^ C k + og p (4) Ck (5) k + og p C C + k, og p + + k = +. (6) Let C be a geeric costat which ay vary fro pace to pace. We prove the risk upper boud (5) for the bias part rst. It is we kow that the to or of a syetric atrix A = (a ij ) pp is the bouded by its to or, i.e., p kak ax ja ij j. i=;:::;p j= We boud the operator or of the bias part ^ ~ ij = ij, we have by its to or. Sice ^ = ((w ij ) ij ) pp where w ij [0; ] ad is exacty whe ji ^ 4 ax i=;:::;p j:ji jj>k jj k, the 3 j ij j5 M k. Now we estabish (4) which is reativey copicated. The key idea i the proof is to write the whoe atrix as a average of atrices which are su of a arge uber of sa disjoit bock atrices, ad for each sa bock atrix the cassica rado atrix theory ca be appied. The foowig ea shows
3 that the operator or of the rado atrix is cotroed by the axiu of operator ors of p uber of k k rado atrices. Let = (~ ij I f i < + ; j < + g) pp. De e N () = ax. p + Lea 3 Let be de ed as i (3). The 3N () : or each sa rado atrix with = k, we cotro its operator or as foows. Lea 4 There is a costat > 0 such that o P N () > x p5 exp x (7) for a 0 < x < ad p. With Leas 3 ad 4 we are ow ready to show the variace boud (4). By Lea 3 we have h i 9 N (k) = 9 N (k) I N (k) x + I N (k) > x 9 x + I N (k) > x. N (k) Note that kk, which is bouded by a costat, ad. The Cauchy Schwarz iequaity the ipies C x + + C I N (k) > x r r C "x 4 + x# + C P N (k) >. q og p+ Set x = 4. The x is bouded by as!. ro Lea 4 we obtai og p + C + p p5 p 8 e 8 = og p + C : (8) Now we give proofs of auxiiary eas. Proof of Lea : It is easy to see kw ij = # f : fi; jg f; : : : ; + k gg # f : (i; j) f; : : : ; + k gg = (k ji jj) + (k ji jj) + ; 3
4 which takes vaue i [0; k]. Ceary fro the above, kw ij = k for ji jj k. Proof of Lea 3: Without oss of geeraity we assue that p ca be divided by. Set () Sice () j+ S () S () = S (). By (3) = () j+ j < p= : (9) are diagoa bocks of their su over j < p=, we have S () ax () j+ ax () : p 0j < p= This ad (3) ipy the cocusio, sice (k) certai atrix (k) with p k +. ad (k) are a sub-bocks of Proof of Lea 4 : or ay syetric atrix A, we have v T Av u T Au v T Av = (u v) T A (u + v) ku vk kak ku + vk u T Au Let S = be a = et of the uit sphere S i the ucidea distace i R. We have kak u T Au us us = u T Au + kak 3 = u T Au + 3 us 4 kak = which ipies kak 4 us u T Au. Sice we are aowed to pack Card S = = bas of radius =4 ito a + =4 ba i R, voue copariso yieds i.e., Card S = (=4) Card S = (5=4) ; 5. Thus there exist v ; v ; : : : ; v 5 S such that kak 4 j5 v T j Av j ; for a syetric A. This oe step approxiatio arguet is siiar to the proof of Propositio 4. (ii) i hag ad Huag (008). Let ; : : : ; be i.i.d. p-vectors with ( ) ( ) T =. Uder the Gaussia (sub-gaussia) assuptio there exists > 0 such that P v T ( i i )( i i ) T v > x e x= for a x > 0 ad kvk = which ipies tv T ( i i )( i i ) T v < for a t < = ad kvk =, the there exists > 0 such that ( P v T ( i i )( i i ) T ) v > x e x = i= 4
5 for a 0 < x < ad kvk =. (See, e.g., Chapter i Sauis ad Statuevicius (99).) Thus we have o P ax > x P > x p + p + p5 Pfjvj T ( v j; p5 exp x =. )v j j > xg Reark: The proof here works for sub-gaussia assuptio which is sighty ore geera tha Gaussia. 5
6 Lecture 9. stiatio of Large Covariace Matrices: Lower boud (I) Observe ; ; : : : ; i.i.d. fro a p-variate Gaussia distributio, N (; pp ). We assue that the covariace atrix pp = ( ij ) i;jp is cotaied i the foowig paraeter space, o (; "; M) = : j ij j M ji jj (+) for i 6= j ad ax () =". (0) I additio we assue that p e. I this ecture we wi see this assuptio is ecessary to estiate pp cosistety uder the operator or. Theore 5 Uder the assuptio (0), we have if c og p + + c ^ : () I this ecture we wi show if ^ c og p by usig Le Ca s ethod. Next tie we wi appy Assouad s ea to prove the other part of the ower boud if c +. ^ We wi appy Le Ca s ethod to derive a ower boud for iiax risk. Let be a observatio fro a distributio i the coectio fp ; = ; ; : : : ; p gg. Le Ca s ethod, which is based o a two-poit testig arguet, gives a ower boud for the axiu estiatio risk over the paraeter set. More specificay, et L be the oss fuctio. De e r ( 0 ; ) = if t [L (t; 0 ) + L (t; )] ad r i = if p r ( 0 ; ), ad deote P = p P p = P. Lea 6 Let T be a estiator of based o a observatio fro a distributio i the coectio fp ; = ; ; : : : ; p gg, the L (T; ) r i P0 ^ P or q p, et be a diagoa covariace atrix with = og p +, ii = for i 6=, ad et 0 be the idetity atrix. Let = ; ; : : : ; p T N (0; ), ad deote the joit desity of ; : : : ; by f, p with p = ax fp; exp (=)g, which ca be writte as foows Y f = x i Y j x i i;jp;j6= i 6
7 where, = or, is the desity of N 0;. Let = for 0 p ad the oss fuctio L be the squared operator or. It is easy to see d ( 0 ; ) = og p for a p. The the ower boud (??) foows iediatey if there is a costat c > 0 such that P0 ^ P c. () Sice R R q 0 ^ q d = jq0 Jese s iequaity ipies q j d for ay two desities q 0 ad q, ad the q 0 q jq 0 q j d = d q (q0 q ) d = q Hece R q 0 ^ q d q q 0 q d : R q 0 q d =. To estabish equatio (), it thus su ces to show that R p P p = f =f0 d! 0, i.e., p p = f d + p 6=j We ow cacuate R f f j d. or 6= j it is easy to see f f j d = 0. Whe = j; we have Thus f d = p p = p p Y i f f j d! 0. (3) exp x i h ( ) i = = og p =. p f! = d = p = = exp = + dx i f d p og p og p og og p for 0 < <, where the ast step foows fro the iequaity og ( x) x for 0 < x < =. = p p! 0 (4) 7
ECE 901 Lecture 4: Estimation of Lipschitz smooth functions
ECE 9 Lecture 4: Estiatio of Lipschitz sooth fuctios R. Nowak 5/7/29 Cosider the followig settig. Let Y f (X) + W, where X is a rado variable (r.v.) o X [, ], W is a r.v. o Y R, idepedet of X ad satisfyig
More informationAPPLIED MULTIVARIATE ANALYSIS
ALIED MULTIVARIATE ANALYSIS FREQUENTLY ASKED QUESTIONS AMIT MITRA & SHARMISHTHA MITRA DEARTMENT OF MATHEMATICS & STATISTICS INDIAN INSTITUTE OF TECHNOLOGY KANUR X = X X X [] The variace covariace atrix
More informationA PROBABILITY PROBLEM
A PROBABILITY PROBLEM A big superarket chai has the followig policy: For every Euros you sped per buy, you ear oe poit (suppose, e.g., that = 3; i this case, if you sped 8.45 Euros, you get two poits,
More informationAn Extension of Panjer s Recursion
1 A Extesio of Paer s Recursio Kaus Th. Hess, Aett Liewad ad Kaus D. Schidt Lehrstuh für Versicherugsatheatik Techische Uiversität Dresde Abstract Sudt ad Jewe have show that a odegeerate cai uber distributio
More informationLecture 10: Bounded Linear Operators and Orthogonality in Hilbert Spaces
Lecture : Bouded Liear Operators ad Orthogoality i Hilbert Spaces 34 Bouded Liear Operator Let ( X, ), ( Y, ) i i be ored liear vector spaces ad { } X Y The, T is said to be bouded if a real uber c such
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 informationProbability Theory. Exercise Sheet 4. ETH Zurich HS 2017
ETH Zurich HS 2017 D-MATH, D-PHYS Prof. A.-S. Szita Coordiator Yili Wag Probability Theory Exercise Sheet 4 Exercise 4.1 Let X ) N be a sequece of i.i.d. rado variables i a probability space Ω, A, P ).
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 informationBertrand s postulate Chapter 2
Bertrad s postulate Chapter We have see that the sequece of prie ubers, 3, 5, 7,... is ifiite. To see that the size of its gaps is ot bouded, let N := 3 5 p deote the product of all prie ubers that are
More informationLecture 6 Ecient estimators. Rao-Cramer bound.
Lecture 6 Eciet estimators. Rao-Cramer boud. 1 MSE ad Suciecy Let X (X 1,..., X) be a radom sample from distributio f θ. Let θ ˆ δ(x) be a estimator of θ. Let T (X) be a suciet statistic for θ. As we have
More informationExponential Families and Bayesian Inference
Computer Visio Expoetial Families ad Bayesia Iferece Lecture Expoetial Families A expoetial family of distributios is a d-parameter family f(x; havig the followig form: f(x; = h(xe g(t T (x B(, (. where
More informationStanford Statistics 311/Electrical Engineering 377
I. Uiversal predictio ad codig a. Gae: sequecex ofdata, adwattopredict(orcode)aswellasifwekew distributio of data b. Two versios: probabilistic ad adversarial. I either case, let p ad q be desities or
More informationData Analysis and Statistical Methods Statistics 651
Data Aalysis ad Statistical Methods Statistics 651 http://www.stat.tau.edu/~suhasii/teachig.htl Suhasii Subba Rao Exaple The itroge cotet of three differet clover plats is give below. 3DOK1 3DOK5 3DOK7
More informationMa/CS 6a Class 22: Power Series
Ma/CS 6a Class 22: Power Series By Ada Sheffer Power Series Mooial: ax i. Polyoial: a 0 + a 1 x + a 2 x 2 + + a x. Power series: A x = a 0 + a 1 x + a 2 x 2 + Also called foral power series, because we
More informationLecture 11 and 12: Basic estimation theory
Lecture ad 2: Basic estimatio theory Sprig 202 - EE 94 Networked estimatio ad cotrol Prof. Kha March 2 202 I. MAXIMUM-LIKELIHOOD ESTIMATORS The maximum likelihood priciple is deceptively simple. Louis
More informationLecture 12: September 27
36-705: Itermediate Statistics Fall 207 Lecturer: Siva Balakrisha Lecture 2: September 27 Today we will discuss sufficiecy i more detail ad the begi to discuss some geeral strategies for costructig estimators.
More informationf(1), and so, if f is continuous, f(x) = f(1)x.
2.2.35: Let f be a additive fuctio. i Clearly fx = fx ad therefore f x = fx for all Z+ ad x R. Hece, for ay, Z +, f = f, ad so, if f is cotiuous, fx = fx. ii Suppose that f is bouded o soe o-epty ope set.
More informationTomoki Toda. Augmented Human Communication Laboratory Graduate School of Information Science
Seuetial Data Modelig d class Basics of seuetial data odelig ooki oda Augeted Hua Couicatio Laboratory Graduate School of Iforatio Sciece Basic Aroaches How to efficietly odel joit robability of high diesioal
More informationEstimation for Complete Data
Estimatio for Complete Data complete data: there is o loss of iformatio durig study. complete idividual complete data= grouped data A complete idividual data is the oe i which the complete iformatio of
More informationSupplementary Material
Suppleetary Material Wezhuo Ya a0096049@us.edu.s Departet of Mechaical Eieeri, Natioal Uiversity of Siapore, Siapore 117576 Hua Xu pexuh@us.edu.s Departet of Mechaical Eieeri, Natioal Uiversity of Siapore,
More informationREGRESSION WITH QUADRATIC LOSS
REGRESSION WITH QUADRATIC LOSS MAXIM RAGINSKY Regressio with quadratic loss is aother basic problem studied i statistical learig theory. We have a radom couple Z = X, Y ), where, as before, X is a R d
More informationChapter 6 Principles of Data Reduction
Chapter 6 for BST 695: Special Topics i Statistical Theory. Kui Zhag, 0 Chapter 6 Priciples of Data Reductio Sectio 6. Itroductio Goal: To summarize or reduce the data X, X,, X to get iformatio about a
More informationMaximum Likelihood Estimation and Complexity Regularization
ECE90 Sprig 004 Statistical Regularizatio ad Learig Theory Lecture: 4 Maximum Likelihood Estimatio ad Complexity Regularizatio Lecturer: Rob Nowak Scribe: Pam Limpiti Review : Maximum Likelihood Estimatio
More informationJacobi symbols. p 1. Note: The Jacobi symbol does not necessarily distinguish between quadratic residues and nonresidues. That is, we could have ( a
Jacobi sybols efiitio Let be a odd positive iteger If 1, the Jacobi sybol : Z C is the costat fuctio 1 1 If > 1, it has a decopositio ( as ) a product of (ot ecessarily distict) pries p 1 p r The Jacobi
More informationApril 1980 TR/96. Extrapolation techniques for first order hyperbolic partial differential equations. E.H. Twizell
TR/96 Apri 980 Extrapoatio techiques for first order hyperboic partia differetia equatios. E.H. Twize W96086 (0) 0. Abstract A uifor grid of step size h is superiposed o the space variabe x i the first
More informationLargest Entries of Sample Correlation Matrices from Equi-correlated Normal Populations
Largest Etries of Saple Correlatio Matrices fro Equi-correlated Noral Populatios Jiaqig Fa ad Tiefeg Jiag Priceto Uiversity ad Uiversity of Miesota Abstract The paper studies the liitig distributio of
More informationLecture Outline. 2 Separating Hyperplanes. 3 Banach Mazur Distance An Algorithmist s Toolkit October 22, 2009
18.409 A Algorithist s Toolkit October, 009 Lecture 1 Lecturer: Joatha Keler Scribes: Alex Levi (009) 1 Outlie Today we ll go over soe of the details fro last class ad ake precise ay details that were
More informationGENERATING FUNCTIONS
GENERATING FUNCTIONS XI CHEN. Exapes Questio.. Toss a coi ties ad fid the probabiity of gettig exacty k heads. Represet H by x ad T by x 0 ad a sequece, say, HTHHT by (x (x 0 (x (x (x 0. We see that a
More informationChapter 2. Asymptotic Notation
Asyptotic Notatio 3 Chapter Asyptotic Notatio Goal : To siplify the aalysis of ruig tie by gettig rid of details which ay be affected by specific ipleetatio ad hardware. [1] The Big Oh (O-Notatio) : It
More informationECE Spring Prof. David R. Jackson ECE Dept. Notes 20
ECE 6341 Sprig 016 Prof. David R. Jackso ECE Dept. Notes 0 1 Spherical Wave Fuctios Cosider solvig ψ + k ψ = 0 i spherical coordiates z φ θ r y x Spherical Wave Fuctios (cot.) I spherical coordiates we
More informationLecture 13: Maximum Likelihood Estimation
ECE90 Sprig 007 Statistical Learig Theory Istructor: R. Nowak Lecture 3: Maximum Likelihood Estimatio Summary of Lecture I the last lecture we derived a risk (MSE) boud for regressio problems; i.e., select
More informationEcon 325/327 Notes on Sample Mean, Sample Proportion, Central Limit Theorem, Chi-square Distribution, Student s t distribution 1.
Eco 325/327 Notes o Sample Mea, Sample Proportio, Cetral Limit Theorem, Chi-square Distributio, Studet s t distributio 1 Sample Mea By Hiro Kasahara We cosider a radom sample from a populatio. Defiitio
More information10/ Statistical Machine Learning Homework #1 Solutions
Caregie Mello Uiversity Departet of Statistics & Data Sciece 0/36-70 Statistical Macie Learig Hoework # Solutios Proble [40 pts.] DUE: February, 08 Let X,..., X P were X i [0, ] ad P as desity p. Let p
More informationWe have also learned that, thanks to the Central Limit Theorem and the Law of Large Numbers,
Cofidece Itervals III What we kow so far: We have see how to set cofidece itervals for the ea, or expected value, of a oral probability distributio, both whe the variace is kow (usig the stadard oral,
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 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 informationarxiv: v1 [math.st] 12 Dec 2018
DIVERGENCE MEASURES ESTIMATION AND ITS ASYMPTOTIC NORMALITY THEORY : DISCRETE CASE arxiv:181.04795v1 [ath.st] 1 Dec 018 Abstract. 1) BA AMADOU DIADIÉ AND 1,,4) LO GANE SAMB 1. Itroductio 1.1. Motivatios.
More informationLecture 23: Minimal sufficiency
Lecture 23: Miimal sufficiecy Maximal reductio without loss of iformatio There are may sufficiet statistics for a give problem. I fact, X (the whole data set) is sufficiet. If T is a sufficiet statistic
More information7.1 Convergence of sequences of random variables
Chapter 7 Limit Theorems Throughout this sectio we will assume a probability space (, F, P), i which is defied a ifiite sequece of radom variables (X ) ad a radom variable X. The fact that for every ifiite
More informationStatistics and Data Analysis in MATLAB Kendrick Kay, February 28, Lecture 4: Model fitting
Statistics ad Data Aalysis i MATLAB Kedrick Kay, kedrick.kay@wustl.edu February 28, 2014 Lecture 4: Model fittig 1. The basics - Suppose that we have a set of data ad suppose that we have selected the
More informationMixture models (cont d)
6.867 Machie learig, lecture 5 (Jaakkola) Lecture topics: Differet types of ixture odels (cot d) Estiatig ixtures: the EM algorith Mixture odels (cot d) Basic ixture odel Mixture odels try to capture ad
More informationSome remarks on the paper Some elementary inequalities of G. Bennett
Soe rears o the paper Soe eleetary iequalities of G. Beett Dag Ah Tua ad Luu Quag Bay Vieta Natioal Uiversity - Haoi Uiversity of Sciece Abstract We give soe couterexaples ad soe rears of soe of the corollaries
More informationInverse Matrix. A meaning that matrix B is an inverse of matrix A.
Iverse Matrix Two square matrices A ad B of dimesios are called iverses to oe aother if the followig holds, AB BA I (11) The otio is dual but we ofte write 1 B A meaig that matrix B is a iverse of matrix
More informationA string of not-so-obvious statements about correlation in the data. (This refers to the mechanical calculation of correlation in the data.
STAT-UB.003 NOTES for Wedesday 0.MAY.0 We will use the file JulieApartet.tw. We ll give the regressio of Price o SqFt, show residual versus fitted plot, save residuals ad fitted. Give plot of (Resid, Price,
More informationECE 901 Lecture 13: Maximum Likelihood Estimation
ECE 90 Lecture 3: Maximum Likelihood Estimatio R. Nowak 5/7/009 The focus of this lecture is to cosider aother approach to learig based o maximum likelihood estimatio. Ulike earlier approaches cosidered
More informationContents Two Sample t Tests Two Sample t Tests
Cotets 3.5.3 Two Saple t Tests................................... 3.5.3 Two Saple t Tests Setup: Two Saples We ow focus o a sceario where we have two idepedet saples fro possibly differet populatios. Our
More informationSupplementary Material on Testing for changes in Kendall s tau
Suppemetary Materia o Testig for chages i Keda s tau Herod Dehig Uiversity of Bochum Daie Voge Uiversity of Aberdee Marti Weder Uiversity of Greifswad Domiik Wied Uiversity of Cooge Abstract This documet
More informationChapter 4. Fourier Series
Chapter 4. Fourier Series At this poit we are ready to ow cosider the caoical equatios. Cosider, for eample the heat equatio u t = u, < (4.) subject to u(, ) = si, u(, t) = u(, t) =. (4.) Here,
More informationStar Saturation Number of Random Graphs
Star Saturatio Number of Radom Graphs A. Mohammadia B. Tayfeh-Rezaie Schoo of Mathematics, Istitute for Research i Fudameta Scieces IPM, P.O. Box 19395-5746, Tehra, Ira ai m@ipm.ir tayfeh-r@ipm.ir Abstract
More informationThe Hypergeometric Coupon Collection Problem and its Dual
Joural of Idustrial ad Systes Egieerig Vol., o., pp -7 Sprig 7 The Hypergeoetric Coupo Collectio Proble ad its Dual Sheldo M. Ross Epstei Departet of Idustrial ad Systes Egieerig, Uiversity of Souther
More informationTHE GREATEST ORDER OF THE DIVISOR FUNCTION WITH INCREASING DIMENSION
MATHEMATICA MONTISNIGRI Vol XXVIII (013) 17-5 THE GREATEST ORDER OF THE DIVISOR FUNCTION WITH INCREASING DIMENSION GLEB V. FEDOROV * * Mechaics ad Matheatics Faculty Moscow State Uiversity Moscow, Russia
More informationIIT JAM Mathematical Statistics (MS) 2006 SECTION A
IIT JAM Mathematical Statistics (MS) 6 SECTION A. If a > for ad lim a / L >, the which of the followig series is ot coverget? (a) (b) (c) (d) (d) = = a = a = a a + / a lim a a / + = lim a / a / + = lim
More informationRegression with quadratic loss
Regressio with quadratic loss Maxim Ragisky October 13, 2015 Regressio with quadratic loss is aother basic problem studied i statistical learig theory. We have a radom couple Z = X,Y, where, as before,
More informationx !1! + 1!2!
4 Euler-Maclauri Suatio Forula 4. Beroulli Nuber & Beroulli Polyoial 4.. Defiitio of Beroulli Nuber Beroulli ubers B (,,3,) are defied as coefficiets of the followig equatio. x e x - B x! 4.. Expreesio
More informationThe Probabilities of Large Deviations for the Chi-square and Log-likelihood Ratio Statistics Sherzod Mirakhmedov
The Probabiities of Large Deiatios for the Chi-square a Log-ieihoo Ratio Statistics Sherzo Miraheo Istitute of Matheatics. atioa Uiersity of Uzbeista 005 Tashet Duro yui st. 9 e-ai: shiraheo@yahoo.co Abstract.
More informationRatio of Two Random Variables: A Note on the Existence of its Moments
Metodološki zvezki, Vol. 3, o., 6, -7 Ratio of wo Rado Variables: A ote o the Existece of its Moets Ato Cedilik, Kataria Košel, ad Adre Bleec 3 Abstract o eable correct statistical iferece, the kowledge
More informationECE 901 Lecture 14: Maximum Likelihood Estimation and Complexity Regularization
ECE 90 Lecture 4: Maximum Likelihood Estimatio ad Complexity Regularizatio R Nowak 5/7/009 Review : Maximum Likelihood Estimatio We have iid observatios draw from a ukow distributio Y i iid p θ, i,, where
More informationEECS564 Estimation, Filtering, and Detection Hwk 2 Solns. Winter p θ (z) = (2θz + 1 θ), 0 z 1
EECS564 Estimatio, Filterig, ad Detectio Hwk 2 Sols. Witer 25 4. Let Z be a sigle observatio havig desity fuctio where. p (z) = (2z + ), z (a) Assumig that is a oradom parameter, fid ad plot the maximum
More informationOptimal Estimator for a Sample Set with Response Error. Ed Stanek
Optial Estiator for a Saple Set wit Respose Error Ed Staek Itroductio We develop a optial estiator siilar to te FP estiator wit respose error tat was cosidered i c08ed63doc Te first 6 pages of tis docuet
More informationAvailable online at J. Math. Comput. Sci. 4 (2014), No. 3, ISSN:
Available olie at http://scik.org J. Math. Coput. Sci. (1, No. 3, 9-5 ISSN: 197-537 ON SYMMETRICAL FUNCTIONS WITH BOUNDED BOUNDARY ROTATION FUAD. S. M. AL SARARI 1,, S. LATHA 1 Departet of Studies i Matheatics,
More informationAN EFFICIENT ESTIMATION METHOD FOR THE PARETO DISTRIBUTION
Joural of Statistics: Advaces i Theory ad Applicatios Volue 3, Nuber, 00, Pages 6-78 AN EFFICIENT ESTIMATION METHOD FOR THE PARETO DISTRIBUTION Departet of Matheatics Brock Uiversity St. Catharies, Otario
More informationZeros of Polynomials
Math 160 www.timetodare.com 4.5 4.6 Zeros of Polyomials I these sectios we will study polyomials algebraically. Most of our work will be cocered with fidig the solutios of polyomial equatios of ay degree
More informationEstimation of the Mean and the ACVF
Chapter 5 Estimatio of the Mea ad the ACVF A statioary process {X t } is characterized by its mea ad its autocovariace fuctio γ ), ad so by the autocorrelatio fuctio ρ ) I this chapter we preset the estimators
More informationDefine a Markov chain on {1,..., 6} with transition probability matrix P =
Pla Group Work 0. The title says it all Next Tie: MCMC ad Geeral-state Markov Chais Midter Exa: Tuesday 8 March i class Hoework 4 due Thursday Uless otherwise oted, let X be a irreducible, aperiodic Markov
More informationSTAT Homework 1 - Solutions
STAT-36700 Homework 1 - Solutios Fall 018 September 11, 018 This cotais solutios for Homework 1. Please ote that we have icluded several additioal commets ad approaches to the problems to give you better
More informationSome Basic Probability Concepts. 2.1 Experiments, Outcomes and Random Variables
Some Basic Probability Cocepts 2. Experimets, Outcomes ad Radom Variables A radom variable is a variable whose value is ukow util it is observed. The value of a radom variable results from a experimet;
More informationLecture 19. sup y 1,..., yn B d n
STAT 06A: Polyomials of adom Variables Lecture date: Nov Lecture 19 Grothedieck s Iequality Scribe: Be Hough The scribes are based o a guest lecture by ya O Doell. I this lecture we prove Grothedieck s
More information5.1 Review of Singular Value Decomposition (SVD)
MGMT 69000: Topics i High-dimesioal Data Aalysis Falll 06 Lecture 5: Spectral Clusterig: Overview (cotd) ad Aalysis Lecturer: Jiamig Xu Scribe: Adarsh Barik, Taotao He, September 3, 06 Outlie Review of
More informationx 2 x x x x x + x x +2 x
Math 5440: Notes o particle radom walk Aaro Fogelso September 6, 005 Derivatio of the diusio equatio: Imagie that there is a distributio of particles spread alog the x-axis ad that the particles udergo
More informationQueueing Theory II. Summary. M/M/1 Output process Networks of Queue Method of Stages. General Distributions
Queueig Theory II Suary M/M/1 Output process Networks of Queue Method of Stages Erlag Distributio Hyperexpoetial Distributio Geeral Distributios Ebedded Markov Chais 1 M/M/1 Output Process Burke s Theore:
More informationLecture 19. Curve fitting I. 1 Introduction. 2 Fitting a constant to measured data
Lecture 9 Curve fittig I Itroductio Suppose we are preseted with eight poits of easured data (x i, y j ). As show i Fig. o the left, we could represet the uderlyig fuctio of which these data are saples
More informationThis exam contains 19 pages (including this cover page) and 10 questions. A Formulae sheet is provided with the exam.
Probability ad Statistics FS 07 Secod Sessio Exam 09.0.08 Time Limit: 80 Miutes Name: Studet ID: This exam cotais 9 pages (icludig this cover page) ad 0 questios. A Formulae sheet is provided with the
More informationA Central Limit Theorem for Belief Functions
A Cetral Limit Theorem for Belief Fuctios Larry G. Estei Kyougwo Seo November 7, 2. CLT for Belief Fuctios The urose of this Note is to rove a form of CLT (Theorem.4) that is used i Estei ad Seo (2). More
More informationMASSACHUSETTS INSTITUTE OF TECHNOLOGY 6.436J/15.085J Fall 2008 Lecture 19 11/17/2008 LAWS OF LARGE NUMBERS II THE STRONG LAW OF LARGE NUMBERS
MASSACHUSTTS INSTITUT OF TCHNOLOGY 6.436J/5.085J Fall 2008 Lecture 9 /7/2008 LAWS OF LARG NUMBRS II Cotets. The strog law of large umbers 2. The Cheroff boud TH STRONG LAW OF LARG NUMBRS While the weak
More informationLecture 2: Monte Carlo Simulation
STAT/Q SCI 43: Itroductio to Resamplig ethods Sprig 27 Istructor: Ye-Chi Che Lecture 2: ote Carlo Simulatio 2 ote Carlo Itegratio Assume we wat to evaluate the followig itegratio: e x3 dx What ca we do?
More informationStat 543 Exam 3 Spring 2016
Stat 543 Exam 3 Sprig 06 I have either give or received uauthorized assistace o this exam. Name Siged Date Name Prited This exam cosists of parts. Do at east 8 of them. I wi score aswers at 0 poits apiece
More informationComplex Analysis Spring 2001 Homework I Solution
Complex Aalysis Sprig 2001 Homework I Solutio 1. Coway, Chapter 1, sectio 3, problem 3. Describe the set of poits satisfyig the equatio z a z + a = 2c, where c > 0 ad a R. To begi, we see from the triagle
More informationEconomics 241B Relation to Method of Moments and Maximum Likelihood OLSE as a Maximum Likelihood Estimator
Ecoomics 24B Relatio to Method of Momets ad Maximum Likelihood OLSE as a Maximum Likelihood Estimator Uder Assumptio 5 we have speci ed the distributio of the error, so we ca estimate the model parameters
More informationCHAPTER 6 RESISTANCE FACTOR FOR THE DESIGN OF COMPOSITE SLABS
CHAPTER 6 RESISTANCE FACTOR FOR THE DESIGN OF COMPOSITE SLABS 6.1. Geeral Probability-based desig criteria i the for of load ad resistace factor desig (LRFD) are ow applied for ost costructio aterials.
More informationLearning Theory for Conditional Risk Minimization: Supplementary Material
Learig Theory for Coditioal Risk Miiizatio: Suppleetary Material Alexader Zii IST Austria azii@istacat Christoph H Lapter IST Austria chl@istacat Proofs Proof of Theore After the applicatio of (6) ad (8)
More informationConvergence of random variables. (telegram style notes) P.J.C. Spreij
Covergece of radom variables (telegram style otes).j.c. Spreij this versio: September 6, 2005 Itroductio As we kow, radom variables are by defiitio measurable fuctios o some uderlyig measurable space
More informationChapter 12 EM algorithms The Expectation-Maximization (EM) algorithm is a maximum likelihood method for models that have hidden variables eg. Gaussian
Chapter 2 EM algorithms The Expectatio-Maximizatio (EM) algorithm is a maximum likelihood method for models that have hidde variables eg. Gaussia Mixture Models (GMMs), Liear Dyamic Systems (LDSs) ad Hidde
More informationThe Poisson Process *
OpeStax-CNX module: m11255 1 The Poisso Process * Do Johso This work is produced by OpeStax-CNX ad licesed uder the Creative Commos Attributio Licese 1.0 Some sigals have o waveform. Cosider the measuremet
More informationMath 4707 Spring 2018 (Darij Grinberg): midterm 2 page 1. Math 4707 Spring 2018 (Darij Grinberg): midterm 2 with solutions [preliminary version]
Math 4707 Sprig 08 Darij Griberg: idter page Math 4707 Sprig 08 Darij Griberg: idter with solutios [preliiary versio] Cotets 0.. Coutig first-eve tuples......................... 3 0.. Coutig legal paths
More informationLecture 10 October Minimaxity and least favorable prior sequences
STATS 300A: Theory of Statistics Fall 205 Lecture 0 October 22 Lecturer: Lester Mackey Scribe: Brya He, Rahul Makhijai Warig: These otes may cotai factual ad/or typographic errors. 0. Miimaxity ad least
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 informationLecture 8: October 20, Applications of SVD: least squares approximation
Mathematical Toolkit Autum 2016 Lecturer: Madhur Tulsiai Lecture 8: October 20, 2016 1 Applicatios of SVD: least squares approximatio We discuss aother applicatio of sigular value decompositio (SVD) of
More informationExpectation and Variance of a random variable
Chapter 11 Expectatio ad Variace of a radom variable The aim of this lecture is to defie ad itroduce mathematical Expectatio ad variace of a fuctio of discrete & cotiuous radom variables ad the distributio
More informationMatrix Algebra 2.2 THE INVERSE OF A MATRIX Pearson Education, Inc.
2 Matrix Algebra 2.2 THE INVERSE OF A MATRIX MATRIX OPERATIONS A matrix A is said to be ivertible if there is a matrix C such that CA = I ad AC = I where, the idetity matrix. I = I I this case, C is a
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 informationElement sampling: Part 2
Chapter 4 Elemet samplig: Part 2 4.1 Itroductio We ow cosider uequal probability samplig desigs which is very popular i practice. I the uequal probability samplig, we ca improve the efficiecy of the resultig
More informationDirection: This test is worth 150 points. You are required to complete this test within 55 minutes.
Term Test 3 (Part A) November 1, 004 Name Math 6 Studet Number Directio: This test is worth 10 poits. You are required to complete this test withi miutes. I order to receive full credit, aswer each problem
More informationLimit Theorems. Convergence in Probability. Let X be the number of heads observed in n tosses. Then, E[X] = np and Var[X] = np(1-p).
Limit Theorems Covergece i Probability Let X be the umber of heads observed i tosses. The, E[X] = p ad Var[X] = p(-p). L O This P x p NM QP P x p should be close to uity for large if our ituitio is correct.
More information18.S34 (FALL, 2007) GREATEST INTEGER PROBLEMS. n + n + 1 = 4n + 2.
18.S34 (FALL, 007) GREATEST INTEGER PROBLEMS Note: We use the otatio x for the greatest iteger x, eve if the origial source used the older otatio [x]. 1. (48P) If is a positive iteger, prove that + + 1
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 information18.01 Calculus Jason Starr Fall 2005
Lecture 18. October 5, 005 Homework. Problem Set 5 Part I: (c). Practice Problems. Course Reader: 3G 1, 3G, 3G 4, 3G 5. 1. Approximatig Riema itegrals. Ofte, there is o simpler expressio for the atiderivative
More informationBOUNDS ON SOME VAN DER WAERDEN NUMBERS. Tom Brown Department of Mathematics, Simon Fraser University, Burnaby, BC V5A 1S6
BOUNDS ON SOME VAN DER WAERDEN NUMBERS To Brow Departet of Matheatics, Sio Fraser Uiversity, Buraby, BC V5A S6 Bruce M Lada Departet of Matheatics, Uiversity of West Georgia, Carrollto, GA 308 Aaro Robertso
More informationDiscrete Mathematics for CS Spring 2007 Luca Trevisan Lecture 22
CS 70 Discrete Mathematics for CS Sprig 2007 Luca Trevisa Lecture 22 Aother Importat Distributio The Geometric Distributio Questio: A biased coi with Heads probability p is tossed repeatedly util the first
More informationAl Lehnen Madison Area Technical College 10/5/2014
The Correlatio of Two Rado Variables Page Preliiary: The Cauchy-Schwarz-Buyakovsky Iequality For ay two sequeces of real ubers { a } ad = { b } =, the followig iequality is always true. Furtherore, equality
More information