Asymptotic Multivariate Kriging Using Estimated Parameters with Bayesian Prediction Methods for Non-linear Predictands
|
|
- Moses Stafford
- 5 years ago
- Views:
Transcription
1 Asymptotic Multivariate Kriging Using Estimated Parameters with Bayesian Prediction Methods for Non-linear Predictands Elizabeth C. Mannshardt-Shamseldin Advisor: Richard L. Smith Duke University Department of Statistical Science University of North Carolina at Chapel Hill Department of Statistics and Operations Research January 14th, 2009
2 Outline Introduction and Motivation Statistical Methods Background Univariate Linear Methods Developed (Smith and Zhu) Research Questions Multivariate Non-Linear Development Simulation Results Conclusions and Future Work 1
3 Introduction Motivation The need often arises in spatial settings for data transformation. The transformation may be non-linear, and the desired predictand may require interpolation of predictions at multiple sites. In traditional kriging methods, standard formula for MSPE does not take into account estimation of covariance parameters - this generally leads to underestimated prediction errors Bayesian methods offer a solution, but iterative methods can be computationally time intensive 2
4 Introduction Possible Solution Smith and Zhu (2004) establish a second-order expansion for predictive distributions in Gaussian processes with estimated covariances. Here, we establish a similar expansion as in Smith and Zhu for multivariate kriging with non-linear predictands. Main Results Explicit formula for a general, non-linear predictand for: the expected length of a Bayesian prediction interval the coverage probability bias Matching prior (CPB=0) and alternative estimator are explored 3
5 Background: Spatial Statistics We have a stochastic process Z(s), generally assumed to be Gaussian with known mean µ and covariance structure V (θ). Z(s) = µ(s) + e(s) where e(s) is a zero mean error process. Basic mode:l Z N(µ, V (θ)) And the model with mean as linear function of covariates: N(Xβ, V (θ)), with Z X a matrix of covariates β a vector of unknown regression coefficients. 4
6 Background: Covariance Structures Example: Covariance function for the exponential model: cov{z(s i ), Z(s j )} = σ 2 exp ( ( )) dij φ (1) V (θ) vector of standardized covariances determined by θ = (σ 2, φ). Underlying covariance( structure introduced through V (θ), matrix with entries v ij = exp ( d ij φ ). ) φ = range parameter σ = scale parameter 5
7 Background: Kriging Kriging: technique for predicting values at unobserved locations w/in random field through linear combinations of observed variables. Refers to the construction of spatial predictor in terms of known model parameters. Universal kriging: mean process is a linear combination of covariates. Y is vector of known observations; Y 0 value to be predicted (scalar) ( Y Y 0 ) N (( Xβ x T 0 β ) ( V (θ) w, T (θ) w(θ) v 0 (θ) )) (2) X is n p vector of covariates for observations Y x 0 is p 1 vector of covariates for predicted scalar Y 0 β vector of regression coefficients θ is vector of covariance parameters. 6
8 Background: Kriging Universal kriging aims to find linear predictor Ŷ 0 = λ T Y that minimizes MSPE E { (Y 0 Ŷ 0 ) 2} subject to condition X T λ = x 0. Using Lagrange multipliers, the optimal λ is: λ(θ) = V 1 (θ)w(θ)+v 1 (θ)x(x T V 1 (θ)x) 1 (x 0 X T V 1 (θ)w(θ)). with corresponding MSPE: σ0 2 (θ) = v 0(θ) w(θ) T V 1 (θ)w(θ) + (x 0 X T V 1 (θ)w(θ)) T (X T V 1 (θ)x) 1 (x 0 X T V 1 (θ)w(θ)). Thus the predictive distribution function is: Pr {Y 0 z Y = y, θ} = ψ(z; y, θ) = Φ ( z λ(θ) T y σ 0 (θ) ) 7
9 Background: REML Estimation Restricted Maximum Likelihood (REML) estimation is based on the joint density of vector of contrasts. Distribution independent of population mean, and resulting maximum likelihood estimator is approximately unbiased, as opposed to the MLE. REML estimator (Smith, 2001; Stein, 1999) is max Θ ln (θ) where ln(θ) = n q 2 log(2π) log XT X 1 2 log XT V (θ) 1 X 1 2 log V (θ) 1 2 G2 (θ) where G 2 (θ) is the generalized residual sum of squares G 2 (θ) = Y T {V 1 (θ) V 1 (θ)x(x T V 1 (θ)x) 1 X T V 1 (θ)}y Use REML estimator ˆθ to obtain the predictive distribution function: ˆψ(z; y, θ) = ψ(z; y, ˆθ) 8
10 Background: Smith and Zhu (2004) Smith and Zhu provide the original development for univariate normal predictive distribution of methods considered in this paper for non-linear multivariate case. This includes: Establishing a second-order expansion for predictive distributions in Gaussian processes. Using covariance parameter estimates (REML) in the plug-in approach as well as Bayesian methods. Main focus is the estimation of quantiles for predictive distribution and application to prediction intervals. Leads to calculation of second-order coverage probability bias - lends itself to possible existence of matching prior where CPB=0. Also: frequentist correction, z P, leads to coverage probability bias of zero, analogous to existence of matching prior. 9
11 Introduce Notation Recall the restricted log-likelihood function, l n (θ) Let U i = l n(θ) θ i, U ij = 2 l n (θ) θ i θ j, etc, U ij is (i, j) entry of inverse of matrix whose (i, j) entry is U ij and Q(θ) is the log of the prior, π(θ). Superscripts denote components of vectors, subscripts indicate differentiation wrt components of θ; summation notation. Function of interest is predictive distribution function, ψ(z; Z, θ). ψ denotes either plug-in estimator ˆψ, or Bayesian estimator, ψ: ψ = ˆψ + ˆD + O p (n 2 ) (3) where D = 1 2 U ijkψ l U ij U kl 1 2 (ψ ij + 2ψ i Q j )U ij (4) and ˆD indicates the evaluation of D at ˆθ. 10
12 Introduce Notation Further, introduce random Z i, Z ij, Z ijk with mean 0 such that U i = n 1 2Z i, U ij = nκ ij + n 1 2Z ij, U ijk = nκ ijk + n 1 2Z ijk where κ i,j = E{Z i Z j }, κ ij,k = E{Z ij Z k }. Note κ i,j = κ ij and is (i, j) entry of normalized Fisher information matrix. Matrix is assumed invertible w/ inverse entries κ i,j. 11
13 Univariate Normal Case Assume that ψ has expansion: ψ (z; Y ) = ψ(z; Y, θ) + n 1 2R(z, Y ) + n 1 S(z, Y ) + o p (n 1 ) (5) For both the plug-in and Bayesian method, components of R and S can be calculated explicitly, using a Taylor expansion for the plug-in approach and a combination of Taylor and Laplace for the Bayesian approach. For ẑ P (plug-in estimator), R = κ i,j Z i ψ j (6) S = κ i,j κ k,l Z ik Z j ψ l κi,r κ j,s κ k,t κ ijk Z r Z s ψ t κi,j κ k,l Z i Z k ψ jl (7) where S for ẑ P is further denoted S 1. For z P (Bayesian estimator), corresponding expression is: S 2 = S κ ijkκ i,j κ k,l ψ l + ( 1 2 ψ ij + ψ i Q j )κ i,j where Q(θ) is the log of the prior, π(θ). 12
14 Coverage Probability Bias Hence the coverage probability bias, the expected value of ψ(zp ; Y, θ) ψ(z P ; Y, θ), is expressed: CPB = E[ n 1/2 R(z P, Y ) + n 1 R(z P, Y )R (z P, Y ) ψ (z P ; Y, θ) S(z P, Y ) + o p (n 1 )] (8) The coverage probability bias represents difference between P {Y 0 zp Y, θ)} and target probability P, where z P is the plug-in estimate zˆ P or the Bayesian estimate z P of P-quantiles of target distribution. 13
15 Key Findings Development of these expansions allows comparison with standard frequentist correction procedures. It also allows for selection of design criterion based on expected length of a prediction interval and coverage probability bias. Matching Prior Interesting development: coverage probability bias can be reduced to a form (Smith, 2004) that suggests existence of a matching prior. May be possible to chose prior, π, so that expectations of the O(n 1/2 ) and O(n 1 ) terms in second-order CPB are zero. Important result because while it may be difficult or impratical to compute matching prior, it lends itself to assisting in prior selection based on how closely different forms of standard priors (Jeffreys, reference prior, etc.) come to matching prior. 14
16 Key Findings Estimator z P is a form of the asymptotic bias and includes a frequentist correction term developed by Harville and Jeske (1992) and Zimmerman and Cressie (1992): z P = ẑ P n 1 asymptotic bias φ(φ 1 (P )) (9) To calculate CPB, calculation of moments of various expressions involving R, S, and their derivatives is needed. By the asymptotic formulae, these can be expressed in terms of derivatives of ψ and other quantities that are explicit functions of the Gaussian process. 15
17 Preliminary Simulation for Univariate Linear Predictand In this paper we first looked at a preliminary simulation for the univariate predictand. Random plane of 16 location values Simulated corresponding observations: Y (s) = X T (s)β + S(s) X(s) is column vector with entries 1, s 1, s 2 where s 1 and s 2 are the coordinates at site s. β = (123) T and S(s) is a stationary Gaussian process with mean 0 Exponential covariance structure with σ = 1 and φ = 1 is used. Parameter estimates are obtained at each site using the other 15 sites. Theoretical 95% PI are constructed and the Empirical Coverage Probabilities are computed over 100 simulations at each site. 16
18 Preliminary Simulation Results Empirical coverage probabilities obtained through kriging using REML estimates for the covariance parameters are much lower than 95%, with values ranging from 64% to 89% and an Average Empirical Coverage (AEC) of 81.4%. Discrepancy can be attributed to error introduced into model through estimates of covariance parameters Bayesian method used Gibbs sampling in WinBUGS with REML estimates as starting values. Showed empirical coverage results around 95%, with a range of 86% to 99%, and an AEC of 94.8%. The Smith-Zhu Laplace approximation method shows definite improvement with an Average Empirical Coverage of 92.9% and a range of 87% to 98% coverage. 17
19 Comparison of Laplace, Bayesian, and Plug-In Methods Empirical Coverage Probabilities 2 Param Exponential Predictions at 16 Sites Coverage Probability o o True: AEC=94% Bayes: AEC =95% REML: AEC=81% Lapl: AEC=93% Sites 18
20 Conclusion Key results of Smith and Zhu s 2004 paper are expressions for coverage probability bias and expected length of a prediction interval for both plug-in and Bayesian predictors. Established for Gaussian process with mean that is combination of linear regressors and parametrically specified covariance. Possible existence of a matching prior introduced Frequentist correction allows for second-order CPB of zero. This paper expands these methods to the analogous non-linear multivariate predictands, such as those motivated by methods established in Smith, Kolenikov, and Cox (2003). 19
21 Multivariate Non-Linear Development An important difference between the univariate linear and multivariate non-linear case, is that the multivariate predictive distribution (G ) not necessarily available in closed form. Thus, a method is needed to determine derivatives of predictive distribution function. In the multivariate case, predictand can be written as H = m j=1 h(y 0,j ) or H = H(Y 0 ) (10) where h( ) is linear kriging function, such as h(y) = y 2. Example: variance stabilizing square root transform where desired predictand is spatial average (Smith, Kolenikov and Cox, 2003.) H( ) is a more general transformation function 20
22 Multivariate Non-Linear Development Assume G has an expansion: G (z; Y ) = G(z; Y, θ) + n 1 2R(z, Y ) + n 1 S(z, Y ) + o p (n 1 ) Consider multivariate non-linear expansion analogs to Smith and Zhu s expansions and form of CPB: R = κ i,j Z i G j S = κ i,j κ k,l Z ik Z j G l κi,r κ j,s κ k,t κ ijk Z r Z s G t κi,j κ k,l Z i Z k G jl CPB = E[ n 1 2R(z P, Y ) + n 1 R(z P, Y )R (z P, Y ) G (z P ; Y, θ) (11) S(z P, Y ) + o p (n 1 )] Extension to multivariate kriging is generalization of univariate. 21
23 Multivariate Non-Linear Development Objective is to evaluate G = P (H(Y 0 ) z y; θ) and its partial derivatives. For the multivariate, nonlinear predictand, the exact form of G may not be easily manipulated. Develop methodology to derive derivatives of predictive distribution G with respect to z, θ, and both z and θ Employ kernel density estimation to evaluate each term Develop parameteric bootstrap to estimate empirical cdf Can estimate predictive distribution as G B (z Y, θ) = 1 B ΣI{H(Y b o ) z}, where B denotes number of iterations and G B represents the bootstrapped estimate 22
24 Derivative Development For G (z Y, θ) = E f(y0 Y,θ) [I{H(Y 0) z}], partial derivatives up to order 2 are necessary; can be expressed as expectations wrt predictive distribution function. θ i I{H(Y 0 ) z}f(y 0 Y, θ)dy 0 = E f(y0 Y,θ) [ I{H(Y 0 ) z} ] θ ilnf(y 0 Y, θ) where f(y 0 Y, θ) is the restricted likelihood and be analytically evaluated. θ ilnf(y 0 Y, θ) can In practice, I{H(Y 0 ) z} θ ilnf(y 0 Y, θ) is empirically estimated and averaged over many iterations using a numerical approximation for derivatives of the restricted log-likelihood. Simulated values are used in place of theoretical expected values. 23
25 Kernel Density The cumulative distribution of the kernel is used to approximate the predictive distribution G (z Y, θ). G (z Y, θ) = 1 B ΣI{H(Y b o ) z} 1 B ΣB b=1 K 1( z H(Y b h o ) ) (12) The kernel density is further expressed as K and its distribution function written K 1. Density used to estimate predictive density, G (z Y, θ). K 1 = K estimates the predictive distribution G (z Y, θ). 24
26 Kernel Density Here we consider the Epanechnikov kernel outlined in Silverman (1986). The Epanechnikov kernel has an efficiency of 1; based on minimizing mean integrated squared error. 1 f(t) = Bh ΣB b=1 3 ( t 2) 5 t 5 0 otherwise. where t = z H(Y 0) h with z the predicted value, H(Y 0 ) the true value, and h smoothing parameter (bandwidth). Epanechnikov Kernel Value of Kernel t 25
27 Multivariate Non-Linear Development In summary, estimation is achieved through a parametric bootstrap : 1. For b = 1,..., B replications generate Y (b) 0 N[Λ T Y, V 0 ]. 2. Calculate G (z Y, θ) = P [H(Y 0 ) z] 1 B b I{H(Y (b) 0 ) z}. 3. Use kernel density differentiable wrt z and wrt the components of θ to approximate Ĝ and derivatives wrt z 4. Express derivatives wrt θ as expectations wrt restricted loglikelihood f(y 0 Y, θ) 5. Evaluate derivatives wrt θ using numerical approximation 26
28 Expansion of Coverage Probability Bias The coverage probability bias can be expressed as: E [G (z P ) G (z P )] = n 1 2 ( n 1 2κ i,j E + n 1 (n 1 κ i,j κ k,l E [ 1 U i B ΣB b=1 K 1( z H(Y b h ] ) [ ARR G B RR G E [S G ] o ) ) θ ilnf(y b 0 Y, θ) ]) (13) where K 1 is the kernel distribution with kernel density K, A RR G and B RR G are as expressed in Equations (14) and (15) and E[S G ] is the appropriate S for the desired plug-in or bayesian prediction. 1 A RR G = U i B ΣB b=1 K 1( z H(Y o b) ) h θ lnf(y b j 0 Y, θ)u k Σ B 1 b=1 Bh K(z H(Y o b) ) h θ llnf(y 0 b Y, θ) (14) B RR G = 1 Bh ΣB b=1 K ( z H(Y b h o ) ) (15) 27
29 For the Bayesian approach, where S = S 2G : E [S 2G ] = E [S 1G ] [ κ ijkκ i,j κ k,l E B ΣB b=1 K 1( z H(Y o b ) ) h θ llnf(y 0 b Y, θ) + 1 [ 1 2 κi,j E B ΣB b=1 K 1( z H(Y o b ] ) )A S2G h [ + κ i,j 1 E B ΣB b=1 K 1( z H(Y o b ) ) ] h θ ilnf(y 0 b Y, θ) Q j (16) ] where Q(θ) = log(π(θ)) from the Bayesian framework and A S2G = ( 2 lnf(y b 0 Y, θ) + θ i θ j θ ilnf(y 0 b Y, θ) θ j lnf(y 0 b Y θ) ) 28
30 Asymptotic Frequentist Correction Alternative to Matching Prior Not necessary to find exact form of matching prior. Construct artificial predictor z P, equivalent to Bayesian predictor, as an alternative to solving Equation (13) by obtaining matching prior. For percentile P, define z P. Laplace Approximation [ ] z P = ẑ P n 1 Equation (13) G (G 1 (P )) (17) where Equation (13) is the expression for the CPB. This is a function of the asymptotic bias as seen in Equation (9) from Smith and Zhu, and is an analog to the univariate normal case. 29
31 Simulation To compare the Laplace approximation technique to the standard Plug-In approach using REML estimates, a simulation was constructed. Here we look specifically at the sum of the squares of predictions over multiple sites. Run over N = 100 iterations - can be thought of as a double loop. Outer loop generates predictions by kriging w/ REML estimates Inner loop uses kernel density estimation to obtain an empirical predictive distribution across the prediction sites and calculate estimate using Laplace approximation technique 30
32 Simulation n 1 sites of (s 1, s 2 ) coordinates are randomly generated and a random field Y (S) is generated of the form Y (s) = X T (s)β + S(s). X(s) is column vector with entries s 1, s 2, β = ( 1 2 ) and S(s) is a stationary Gaussian process with mean 0 and variance σ 2 = 1. Correlation function is parametrized by an exponential covariance structure cov{y (s 1 ), Y (s 2 )} = σ 2 (exp( d ij φ )) σ = 1.0 and the range parameter φ =
33 Simulation n 1 Y values ( n 1 = 30) treated as observed across original sites. An additional n 2 = 5 sites are generated, and corresponding simulated field values, Y 0, are treated as true values. Objective of simulation is to interpolate a non-linear, multivariate predictand H(Y 0 ) across the n 2 sites. Predictand here is the sum of squares across the n 2 sites, H(Y 0 ) = Σ n 2 i=1 Y
34 Simulation Of interest is the empirical coverage of 95% theoretical prediction intervals generated using the Laplace method vs the plug-in method. n 1 observed sites are used to obtain parameter estimates (using REML) for the range parameter φ and the shape parameter σ. REML estimates plugged-in to the universal kriging methods to interpolate sum of squares prediction over n 2 sites Laplace approximation is calculated using developed methodology 33
35 Simulation Results Non-Linear Plug-In vs Laplace Prediction Intervals: 1 Parameter Empirical 95% PI s for plug-in method result in severe undercoverage. An Average Empirical Coverage (AEC) of 75.8% was found. Laplace approximation technique resulted in an improvement. AEC for the Laplace approximation prediction intervals was 78.7%. Note that the Laplace approximation sometimes exhibits erratic behavior - the correction produced extremely large adjustments, possibly due to the REML estimates hitting the bounds set in the optimization algorithm and the fact that asymptotic arguments are not as reliable for small samples. Thus it is reasonable to assume that the Laplace approximation may result in even more of an improvement over the plug-in method if this can be corrected, and provides an interesting area of future study. 34
36 Empirical probabilities from the Laplace technique are plotted against the plug-in coverages. As expected there is a strong positive correlation. Line y = x shows that majority of Laplace coverages are larger than plug-in coverages. 35
37 Simulation Results Empirical Coverage Probabilities: 2 Parameter Case Empirical 95% PI s for plug-in method result in undercoverage. An Average Empirical Coverage (AEC) of 91.9% was found. Laplace approximation technique resulted in a slight improvement. AEC for Laplace approximation prediction intervals was 92.2%. Empirical probabilities from Laplace technique are plotted against plug-in coverages. Line y = x shows empirical coverages of Laplace approximation larger than plug-in coverages in about half of simulated intervals. Plot shows evidence of greater improvement in Laplace approximation over plug-in method when empirical coverage is low 36
38
39 Conclusions Developed a practical method for analytical evaluation which included a boot-strap method to obtain predictions for general, non-linear predictands and incorporates kernel density estimation for unknown or computationally difficult predictive distribution. Laplace approximation technique showed improvement in linear univariate case, with empirical coverage probabilities for PI s analogous to Bayesian PI s, both showing very close agreement to theoretical prediction coverage of 95%. Simulation for multivariate non-linear predictand showed promising results for Laplace approximation technique. Results also suggest the existence of matching prior for nonlinear predictands, which has a form analogous to the form derived for the univariate normal case in Smith and Zhu (2004). 37
40 Future Work Investigation of different prior specifications for Bayesian and Laplace methods, specifically the Jeffreys prior and the reference prior Specific computation of matching prior to achieve second-order coverage probability bias of zero Application to data analysis, such as the square-root transformation of the PM 2.5 data considered in Smith, Kolenikov, and Cox (2003) 38
41 Thank You! 39
BAYESIAN KRIGING AND BAYESIAN NETWORK DESIGN
BAYESIAN KRIGING AND BAYESIAN NETWORK DESIGN Richard L. Smith Department of Statistics and Operations Research University of North Carolina Chapel Hill, N.C., U.S.A. J. Stuart Hunter Lecture TIES 2004
More informationESTIMATING THE MEAN LEVEL OF FINE PARTICULATE MATTER: AN APPLICATION OF SPATIAL STATISTICS
ESTIMATING THE MEAN LEVEL OF FINE PARTICULATE MATTER: AN APPLICATION OF SPATIAL STATISTICS Richard L. Smith Department of Statistics and Operations Research University of North Carolina Chapel Hill, N.C.,
More informationASYMPTOTIC THEORY FOR KRIGING WITH ESTIMATED PARAMETERS AND ITS APPLICATION TO NETWORK DESIGN
ASYMPTOTIC THEORY FOR KRIGING WITH ESTIMATED PARAMETERS AND ITS APPLICATION TO NETWORK DESIGN Richard L. Smith Department of Statistics and Operations Research University of North Carolina Chapel Hill,
More informationChapter 4 - Fundamentals of spatial processes Lecture notes
TK4150 - Intro 1 Chapter 4 - Fundamentals of spatial processes Lecture notes Odd Kolbjørnsen and Geir Storvik January 30, 2017 STK4150 - Intro 2 Spatial processes Typically correlation between nearby sites
More informationCovariance function estimation in Gaussian process regression
Covariance function estimation in Gaussian process regression François Bachoc Department of Statistics and Operations Research, University of Vienna WU Research Seminar - May 2015 François Bachoc Gaussian
More informationChapter 4 - Fundamentals of spatial processes Lecture notes
Chapter 4 - Fundamentals of spatial processes Lecture notes Geir Storvik January 21, 2013 STK4150 - Intro 2 Spatial processes Typically correlation between nearby sites Mostly positive correlation Negative
More informationSpatial statistics, addition to Part I. Parameter estimation and kriging for Gaussian random fields
Spatial statistics, addition to Part I. Parameter estimation and kriging for Gaussian random fields 1 Introduction Jo Eidsvik Department of Mathematical Sciences, NTNU, Norway. (joeid@math.ntnu.no) February
More informationKarhunen-Loeve Expansion and Optimal Low-Rank Model for Spatial Processes
TTU, October 26, 2012 p. 1/3 Karhunen-Loeve Expansion and Optimal Low-Rank Model for Spatial Processes Hao Zhang Department of Statistics Department of Forestry and Natural Resources Purdue University
More informationStatistics for analyzing and modeling precipitation isotope ratios in IsoMAP
Statistics for analyzing and modeling precipitation isotope ratios in IsoMAP The IsoMAP uses the multiple linear regression and geostatistical methods to analyze isotope data Suppose the response variable
More informationDefault priors and model parametrization
1 / 16 Default priors and model parametrization Nancy Reid O-Bayes09, June 6, 2009 Don Fraser, Elisabeta Marras, Grace Yun-Yi 2 / 16 Well-calibrated priors model f (y; θ), F(y; θ); log-likelihood l(θ)
More informationStatistics & Data Sciences: First Year Prelim Exam May 2018
Statistics & Data Sciences: First Year Prelim Exam May 2018 Instructions: 1. Do not turn this page until instructed to do so. 2. Start each new question on a new sheet of paper. 3. This is a closed book
More informationSpring 2017 Econ 574 Roger Koenker. Lecture 14 GEE-GMM
University of Illinois Department of Economics Spring 2017 Econ 574 Roger Koenker Lecture 14 GEE-GMM Throughout the course we have emphasized methods of estimation and inference based on the principle
More informationLikelihood-Based Methods
Likelihood-Based Methods Handbook of Spatial Statistics, Chapter 4 Susheela Singh September 22, 2016 OVERVIEW INTRODUCTION MAXIMUM LIKELIHOOD ESTIMATION (ML) RESTRICTED MAXIMUM LIKELIHOOD ESTIMATION (REML)
More informationFall 2017 STAT 532 Homework Peter Hoff. 1. Let P be a probability measure on a collection of sets A.
1. Let P be a probability measure on a collection of sets A. (a) For each n N, let H n be a set in A such that H n H n+1. Show that P (H n ) monotonically converges to P ( k=1 H k) as n. (b) For each n
More informationModel Selection for Geostatistical Models
Model Selection for Geostatistical Models Richard A. Davis Colorado State University http://www.stat.colostate.edu/~rdavis/lectures Joint work with: Jennifer A. Hoeting, Colorado State University Andrew
More informationREGRESSION WITH SPATIALLY MISALIGNED DATA. Lisa Madsen Oregon State University David Ruppert Cornell University
REGRESSION ITH SPATIALL MISALIGNED DATA Lisa Madsen Oregon State University David Ruppert Cornell University SPATIALL MISALIGNED DATA 10 X X X X X X X X 5 X X X X X 0 X 0 5 10 OUTLINE 1. Introduction 2.
More informationHierarchical Modeling for Univariate Spatial Data
Hierarchical Modeling for Univariate Spatial Data Geography 890, Hierarchical Bayesian Models for Environmental Spatial Data Analysis February 15, 2011 1 Spatial Domain 2 Geography 890 Spatial Domain This
More informationof the 7 stations. In case the number of daily ozone maxima in a month is less than 15, the corresponding monthly mean was not computed, being treated
Spatial Trends and Spatial Extremes in South Korean Ozone Seokhoon Yun University of Suwon, Department of Applied Statistics Suwon, Kyonggi-do 445-74 South Korea syun@mail.suwon.ac.kr Richard L. Smith
More informationBootstrap and Parametric Inference: Successes and Challenges
Bootstrap and Parametric Inference: Successes and Challenges G. Alastair Young Department of Mathematics Imperial College London Newton Institute, January 2008 Overview Overview Review key aspects of frequentist
More informationBayesian and Frequentist Methods for Approximate Inference in Generalized Linear Mixed Models
Bayesian and Frequentist Methods for Approximate Inference in Generalized Linear Mixed Models Evangelos A. Evangelou A dissertation submitted to the faculty of the University of North Carolina at Chapel
More informationOn Modifications to Linking Variance Estimators in the Fay-Herriot Model that Induce Robustness
Statistics and Applications {ISSN 2452-7395 (online)} Volume 16 No. 1, 2018 (New Series), pp 289-303 On Modifications to Linking Variance Estimators in the Fay-Herriot Model that Induce Robustness Snigdhansu
More informationWeighted Least Squares I
Weighted Least Squares I for i = 1, 2,..., n we have, see [1, Bradley], data: Y i x i i.n.i.d f(y i θ i ), where θ i = E(Y i x i ) co-variates: x i = (x i1, x i2,..., x ip ) T let X n p be the matrix of
More informationGauge Plots. Gauge Plots JAPANESE BEETLE DATA MAXIMUM LIKELIHOOD FOR SPATIALLY CORRELATED DISCRETE DATA JAPANESE BEETLE DATA
JAPANESE BEETLE DATA 6 MAXIMUM LIKELIHOOD FOR SPATIALLY CORRELATED DISCRETE DATA Gauge Plots TuscaroraLisa Central Madsen Fairways, 996 January 9, 7 Grubs Adult Activity Grub Counts 6 8 Organic Matter
More informationHierarchical Modelling for Univariate Spatial Data
Hierarchical Modelling for Univariate Spatial Data Sudipto Banerjee 1 and Andrew O. Finley 2 1 Biostatistics, School of Public Health, University of Minnesota, Minneapolis, Minnesota, U.S.A. 2 Department
More informationGaussian Processes. Le Song. Machine Learning II: Advanced Topics CSE 8803ML, Spring 2012
Gaussian Processes Le Song Machine Learning II: Advanced Topics CSE 8803ML, Spring 01 Pictorial view of embedding distribution Transform the entire distribution to expected features Feature space Feature
More informationEcon 582 Nonparametric Regression
Econ 582 Nonparametric Regression Eric Zivot May 28, 2013 Nonparametric Regression Sofarwehaveonlyconsideredlinearregressionmodels = x 0 β + [ x ]=0 [ x = x] =x 0 β = [ x = x] [ x = x] x = β The assume
More informationBayesian estimation of the discrepancy with misspecified parametric models
Bayesian estimation of the discrepancy with misspecified parametric models Pierpaolo De Blasi University of Torino & Collegio Carlo Alberto Bayesian Nonparametrics workshop ICERM, 17-21 September 2012
More informationSpring 2012 Math 541B Exam 1
Spring 2012 Math 541B Exam 1 1. A sample of size n is drawn without replacement from an urn containing N balls, m of which are red and N m are black; the balls are otherwise indistinguishable. Let X denote
More informationMCMC algorithms for fitting Bayesian models
MCMC algorithms for fitting Bayesian models p. 1/1 MCMC algorithms for fitting Bayesian models Sudipto Banerjee sudiptob@biostat.umn.edu University of Minnesota MCMC algorithms for fitting Bayesian models
More informationParametric Techniques Lecture 3
Parametric Techniques Lecture 3 Jason Corso SUNY at Buffalo 22 January 2009 J. Corso (SUNY at Buffalo) Parametric Techniques Lecture 3 22 January 2009 1 / 39 Introduction In Lecture 2, we learned how to
More informationModeling and Interpolation of Non-Gaussian Spatial Data: A Comparative Study
Modeling and Interpolation of Non-Gaussian Spatial Data: A Comparative Study Gunter Spöck, Hannes Kazianka, Jürgen Pilz Department of Statistics, University of Klagenfurt, Austria hannes.kazianka@uni-klu.ac.at
More informationLecture 20 May 18, Empirical Bayes Interpretation [Efron & Morris 1973]
Stats 300C: Theory of Statistics Spring 2018 Lecture 20 May 18, 2018 Prof. Emmanuel Candes Scribe: Will Fithian and E. Candes 1 Outline 1. Stein s Phenomenon 2. Empirical Bayes Interpretation of James-Stein
More informationf(x θ)dx with respect to θ. Assuming certain smoothness conditions concern differentiating under the integral the integral sign, we first obtain
0.1. INTRODUCTION 1 0.1 Introduction R. A. Fisher, a pioneer in the development of mathematical statistics, introduced a measure of the amount of information contained in an observaton from f(x θ). Fisher
More informationComparing Non-informative Priors for Estimation and Prediction in Spatial Models
Environmentrics 00, 1 12 DOI: 10.1002/env.XXXX Comparing Non-informative Priors for Estimation and Prediction in Spatial Models Regina Wu a and Cari G. Kaufman a Summary: Fitting a Bayesian model to spatial
More informationModels for spatial data (cont d) Types of spatial data. Types of spatial data (cont d) Hierarchical models for spatial data
Hierarchical models for spatial data Based on the book by Banerjee, Carlin and Gelfand Hierarchical Modeling and Analysis for Spatial Data, 2004. We focus on Chapters 1, 2 and 5. Geo-referenced data arise
More informationStat 5101 Lecture Notes
Stat 5101 Lecture Notes Charles J. Geyer Copyright 1998, 1999, 2000, 2001 by Charles J. Geyer May 7, 2001 ii Stat 5101 (Geyer) Course Notes Contents 1 Random Variables and Change of Variables 1 1.1 Random
More informationOptimization. The value x is called a maximizer of f and is written argmax X f. g(λx + (1 λ)y) < λg(x) + (1 λ)g(y) 0 < λ < 1; x, y X.
Optimization Background: Problem: given a function f(x) defined on X, find x such that f(x ) f(x) for all x X. The value x is called a maximizer of f and is written argmax X f. In general, argmax X f may
More informationGeostatistical Modeling for Large Data Sets: Low-rank methods
Geostatistical Modeling for Large Data Sets: Low-rank methods Whitney Huang, Kelly-Ann Dixon Hamil, and Zizhuang Wu Department of Statistics Purdue University February 22, 2016 Outline Motivation Low-rank
More informationIntegrated Likelihood Estimation in Semiparametric Regression Models. Thomas A. Severini Department of Statistics Northwestern University
Integrated Likelihood Estimation in Semiparametric Regression Models Thomas A. Severini Department of Statistics Northwestern University Joint work with Heping He, University of York Introduction Let Y
More informationOn prediction and density estimation Peter McCullagh University of Chicago December 2004
On prediction and density estimation Peter McCullagh University of Chicago December 2004 Summary Having observed the initial segment of a random sequence, subsequent values may be predicted by calculating
More informationSubmitted to the Brazilian Journal of Probability and Statistics
Submitted to the Brazilian Journal of Probability and Statistics Multivariate normal approximation of the maximum likelihood estimator via the delta method Andreas Anastasiou a and Robert E. Gaunt b a
More informationF & B Approaches to a simple model
A6523 Signal Modeling, Statistical Inference and Data Mining in Astrophysics Spring 215 http://www.astro.cornell.edu/~cordes/a6523 Lecture 11 Applications: Model comparison Challenges in large-scale surveys
More informationABC random forest for parameter estimation. Jean-Michel Marin
ABC random forest for parameter estimation Jean-Michel Marin Université de Montpellier Institut Montpelliérain Alexander Grothendieck (IMAG) Institut de Biologie Computationnelle (IBC) Labex Numev! joint
More informationMIT Spring 2015
Regression Analysis MIT 18.472 Dr. Kempthorne Spring 2015 1 Outline Regression Analysis 1 Regression Analysis 2 Multiple Linear Regression: Setup Data Set n cases i = 1, 2,..., n 1 Response (dependent)
More informationStatistics 203: Introduction to Regression and Analysis of Variance Course review
Statistics 203: Introduction to Regression and Analysis of Variance Course review Jonathan Taylor - p. 1/?? Today Review / overview of what we learned. - p. 2/?? General themes in regression models Specifying
More informationIntroduction to Estimation Methods for Time Series models Lecture 2
Introduction to Estimation Methods for Time Series models Lecture 2 Fulvio Corsi SNS Pisa Fulvio Corsi Introduction to Estimation () Methods for Time Series models Lecture 2 SNS Pisa 1 / 21 Estimators:
More informationML estimation: Random-intercepts logistic model. and z
ML estimation: Random-intercepts logistic model log p ij 1 p = x ijβ + υ i with υ i N(0, συ) 2 ij Standardizing the random effect, θ i = υ i /σ υ, yields log p ij 1 p = x ij β + σ υθ i with θ i N(0, 1)
More informationThe Bayesian approach to inverse problems
The Bayesian approach to inverse problems Youssef Marzouk Department of Aeronautics and Astronautics Center for Computational Engineering Massachusetts Institute of Technology ymarz@mit.edu, http://uqgroup.mit.edu
More information1. Fisher Information
1. Fisher Information Let f(x θ) be a density function with the property that log f(x θ) is differentiable in θ throughout the open p-dimensional parameter set Θ R p ; then the score statistic (or score
More informationA Very Brief Summary of Statistical Inference, and Examples
A Very Brief Summary of Statistical Inference, and Examples Trinity Term 2009 Prof. Gesine Reinert Our standard situation is that we have data x = x 1, x 2,..., x n, which we view as realisations of random
More informationMethods of Estimation
Methods of Estimation MIT 18.655 Dr. Kempthorne Spring 2016 1 Outline Methods of Estimation I 1 Methods of Estimation I 2 X X, X P P = {P θ, θ Θ}. Problem: Finding a function θˆ(x ) which is close to θ.
More informationEcon 2148, fall 2017 Gaussian process priors, reproducing kernel Hilbert spaces, and Splines
Econ 2148, fall 2017 Gaussian process priors, reproducing kernel Hilbert spaces, and Splines Maximilian Kasy Department of Economics, Harvard University 1 / 37 Agenda 6 equivalent representations of the
More informationRestricted Maximum Likelihood in Linear Regression and Linear Mixed-Effects Model
Restricted Maximum Likelihood in Linear Regression and Linear Mixed-Effects Model Xiuming Zhang zhangxiuming@u.nus.edu A*STAR-NUS Clinical Imaging Research Center October, 015 Summary This report derives
More informationStatistical Methods for Handling Incomplete Data Chapter 2: Likelihood-based approach
Statistical Methods for Handling Incomplete Data Chapter 2: Likelihood-based approach Jae-Kwang Kim Department of Statistics, Iowa State University Outline 1 Introduction 2 Observed likelihood 3 Mean Score
More informationSTAT 730 Chapter 4: Estimation
STAT 730 Chapter 4: Estimation Timothy Hanson Department of Statistics, University of South Carolina Stat 730: Multivariate Analysis 1 / 23 The likelihood We have iid data, at least initially. Each datum
More informationKriging models with Gaussian processes - covariance function estimation and impact of spatial sampling
Kriging models with Gaussian processes - covariance function estimation and impact of spatial sampling François Bachoc former PhD advisor: Josselin Garnier former CEA advisor: Jean-Marc Martinez Department
More informationLikelihood and p-value functions in the composite likelihood context
Likelihood and p-value functions in the composite likelihood context D.A.S. Fraser and N. Reid Department of Statistical Sciences University of Toronto November 19, 2016 Abstract The need for combining
More informationMasters Comprehensive Examination Department of Statistics, University of Florida
Masters Comprehensive Examination Department of Statistics, University of Florida May 6, 003, 8:00 am - :00 noon Instructions: You have four hours to answer questions in this examination You must show
More informationDefault Priors and Effcient Posterior Computation in Bayesian
Default Priors and Effcient Posterior Computation in Bayesian Factor Analysis January 16, 2010 Presented by Eric Wang, Duke University Background and Motivation A Brief Review of Parameter Expansion Literature
More informationParametric Techniques
Parametric Techniques Jason J. Corso SUNY at Buffalo J. Corso (SUNY at Buffalo) Parametric Techniques 1 / 39 Introduction When covering Bayesian Decision Theory, we assumed the full probabilistic structure
More informationProblem Selected Scores
Statistics Ph.D. Qualifying Exam: Part II November 20, 2010 Student Name: 1. Answer 8 out of 12 problems. Mark the problems you selected in the following table. Problem 1 2 3 4 5 6 7 8 9 10 11 12 Selected
More informationAn Extended BIC for Model Selection
An Extended BIC for Model Selection at the JSM meeting 2007 - Salt Lake City Surajit Ray Boston University (Dept of Mathematics and Statistics) Joint work with James Berger, Duke University; Susie Bayarri,
More information1 Mixed effect models and longitudinal data analysis
1 Mixed effect models and longitudinal data analysis Mixed effects models provide a flexible approach to any situation where data have a grouping structure which introduces some kind of correlation between
More informationσ(a) = a N (x; 0, 1 2 ) dx. σ(a) = Φ(a) =
Until now we have always worked with likelihoods and prior distributions that were conjugate to each other, allowing the computation of the posterior distribution to be done in closed form. Unfortunately,
More informationTwo hours. To be supplied by the Examinations Office: Mathematical Formula Tables THE UNIVERSITY OF MANCHESTER. 21 June :45 11:45
Two hours MATH20802 To be supplied by the Examinations Office: Mathematical Formula Tables THE UNIVERSITY OF MANCHESTER STATISTICAL METHODS 21 June 2010 9:45 11:45 Answer any FOUR of the questions. University-approved
More informationThe loss function and estimating equations
Chapter 6 he loss function and estimating equations 6 Loss functions Up until now our main focus has been on parameter estimating via the maximum likelihood However, the negative maximum likelihood is
More informationNow consider the case where E(Y) = µ = Xβ and V (Y) = σ 2 G, where G is diagonal, but unknown.
Weighting We have seen that if E(Y) = Xβ and V (Y) = σ 2 G, where G is known, the model can be rewritten as a linear model. This is known as generalized least squares or, if G is diagonal, with trace(g)
More informationEstimation Theory. as Θ = (Θ 1,Θ 2,...,Θ m ) T. An estimator
Estimation Theory Estimation theory deals with finding numerical values of interesting parameters from given set of data. We start with formulating a family of models that could describe how the data were
More information1 One-way analysis of variance
LIST OF FORMULAS (Version from 21. November 2014) STK2120 1 One-way analysis of variance Assume X ij = µ+α i +ɛ ij ; j = 1, 2,..., J i ; i = 1, 2,..., I ; where ɛ ij -s are independent and N(0, σ 2 ) distributed.
More informationEstimation theory. Parametric estimation. Properties of estimators. Minimum variance estimator. Cramer-Rao bound. Maximum likelihood estimators
Estimation theory Parametric estimation Properties of estimators Minimum variance estimator Cramer-Rao bound Maximum likelihood estimators Confidence intervals Bayesian estimation 1 Random Variables Let
More informationMonte Carlo Studies. The response in a Monte Carlo study is a random variable.
Monte Carlo Studies The response in a Monte Carlo study is a random variable. The response in a Monte Carlo study has a variance that comes from the variance of the stochastic elements in the data-generating
More informationGraduate Econometrics I: Maximum Likelihood I
Graduate Econometrics I: Maximum Likelihood I Yves Dominicy Université libre de Bruxelles Solvay Brussels School of Economics and Management ECARES Yves Dominicy Graduate Econometrics I: Maximum Likelihood
More informationGeneralized Linear Models. Kurt Hornik
Generalized Linear Models Kurt Hornik Motivation Assuming normality, the linear model y = Xβ + e has y = β + ε, ε N(0, σ 2 ) such that y N(μ, σ 2 ), E(y ) = μ = β. Various generalizations, including general
More informationOverview of Spatial Statistics with Applications to fmri
with Applications to fmri School of Mathematics & Statistics Newcastle University April 8 th, 2016 Outline Why spatial statistics? Basic results Nonstationary models Inference for large data sets An example
More informationASSESSING A VECTOR PARAMETER
SUMMARY ASSESSING A VECTOR PARAMETER By D.A.S. Fraser and N. Reid Department of Statistics, University of Toronto St. George Street, Toronto, Canada M5S 3G3 dfraser@utstat.toronto.edu Some key words. Ancillary;
More informationPractice Exam 1. (A) (B) (C) (D) (E) You are given the following data on loss sizes:
Practice Exam 1 1. Losses for an insurance coverage have the following cumulative distribution function: F(0) = 0 F(1,000) = 0.2 F(5,000) = 0.4 F(10,000) = 0.9 F(100,000) = 1 with linear interpolation
More informationMIXED MODELS THE GENERAL MIXED MODEL
MIXED MODELS This chapter introduces best linear unbiased prediction (BLUP), a general method for predicting random effects, while Chapter 27 is concerned with the estimation of variances by restricted
More informationEfficient Estimation of Population Quantiles in General Semiparametric Regression Models
Efficient Estimation of Population Quantiles in General Semiparametric Regression Models Arnab Maity 1 Department of Statistics, Texas A&M University, College Station TX 77843-3143, U.S.A. amaity@stat.tamu.edu
More informationSome Curiosities Arising in Objective Bayesian Analysis
. Some Curiosities Arising in Objective Bayesian Analysis Jim Berger Duke University Statistical and Applied Mathematical Institute Yale University May 15, 2009 1 Three vignettes related to John s work
More informationStatistics for Spatial Functional Data
Statistics for Spatial Functional Data Marcela Alfaro Córdoba North Carolina State University February 11, 2016 INTRODUCTION Based on Statistics for spatial functional data: some recent contributions from
More informationIntroduction to General and Generalized Linear Models
Introduction to General and Generalized Linear Models Mixed effects models - Part II Henrik Madsen Poul Thyregod Informatics and Mathematical Modelling Technical University of Denmark DK-2800 Kgs. Lyngby
More informationComputational Statistics. Jian Pei School of Computing Science Simon Fraser University
Computational Statistics Jian Pei School of Computing Science Simon Fraser University jpei@cs.sfu.ca BASIC OPTIMIZATION METHODS J. Pei: Computational Statistics 2 Why Optimization? In statistical inference,
More informationA union of Bayesian, frequentist and fiducial inferences by confidence distribution and artificial data sampling
A union of Bayesian, frequentist and fiducial inferences by confidence distribution and artificial data sampling Min-ge Xie Department of Statistics, Rutgers University Workshop on Higher-Order Asymptotics
More informationStat 5102 Final Exam May 14, 2015
Stat 5102 Final Exam May 14, 2015 Name Student ID The exam is closed book and closed notes. You may use three 8 1 11 2 sheets of paper with formulas, etc. You may also use the handouts on brand name distributions
More informationECE521 week 3: 23/26 January 2017
ECE521 week 3: 23/26 January 2017 Outline Probabilistic interpretation of linear regression - Maximum likelihood estimation (MLE) - Maximum a posteriori (MAP) estimation Bias-variance trade-off Linear
More informationSelection Criteria Based on Monte Carlo Simulation and Cross Validation in Mixed Models
Selection Criteria Based on Monte Carlo Simulation and Cross Validation in Mixed Models Junfeng Shang Bowling Green State University, USA Abstract In the mixed modeling framework, Monte Carlo simulation
More information2 Statistical Estimation: Basic Concepts
Technion Israel Institute of Technology, Department of Electrical Engineering Estimation and Identification in Dynamical Systems (048825) Lecture Notes, Fall 2009, Prof. N. Shimkin 2 Statistical Estimation:
More informationComparing Non-informative Priors for Estimation and. Prediction in Spatial Models
Comparing Non-informative Priors for Estimation and Prediction in Spatial Models Vigre Semester Report by: Regina Wu Advisor: Cari Kaufman January 31, 2010 1 Introduction Gaussian random fields with specified
More informationForecasting Data Streams: Next Generation Flow Field Forecasting
Forecasting Data Streams: Next Generation Flow Field Forecasting Kyle Caudle South Dakota School of Mines & Technology (SDSMT) kyle.caudle@sdsmt.edu Joint work with Michael Frey (Bucknell University) and
More informationLinear Methods for Prediction
Chapter 5 Linear Methods for Prediction 5.1 Introduction We now revisit the classification problem and focus on linear methods. Since our prediction Ĝ(x) will always take values in the discrete set G we
More informationStat260: Bayesian Modeling and Inference Lecture Date: February 10th, Jeffreys priors. exp 1 ) p 2
Stat260: Bayesian Modeling and Inference Lecture Date: February 10th, 2010 Jeffreys priors Lecturer: Michael I. Jordan Scribe: Timothy Hunter 1 Priors for the multivariate Gaussian Consider a multivariate
More informationNonstationary spatial process modeling Part II Paul D. Sampson --- Catherine Calder Univ of Washington --- Ohio State University
Nonstationary spatial process modeling Part II Paul D. Sampson --- Catherine Calder Univ of Washington --- Ohio State University this presentation derived from that presented at the Pan-American Advanced
More informationNon-Parametric Bootstrap Mean. Squared Error Estimation For M- Quantile Estimators Of Small Area. Averages, Quantiles And Poverty
Working Paper M11/02 Methodology Non-Parametric Bootstrap Mean Squared Error Estimation For M- Quantile Estimators Of Small Area Averages, Quantiles And Poverty Indicators Stefano Marchetti, Nikos Tzavidis,
More informationModel Specification Testing in Nonparametric and Semiparametric Time Series Econometrics. Jiti Gao
Model Specification Testing in Nonparametric and Semiparametric Time Series Econometrics Jiti Gao Department of Statistics School of Mathematics and Statistics The University of Western Australia Crawley
More informationParametric Bootstrap Methods for Bias Correction in Linear Mixed Models
CIRJE-F-801 Parametric Bootstrap Methods for Bias Correction in Linear Mixed Models Tatsuya Kubokawa University of Tokyo Bui Nagashima Graduate School of Economics, University of Tokyo April 2011 CIRJE
More informationLecture 3 September 1
STAT 383C: Statistical Modeling I Fall 2016 Lecture 3 September 1 Lecturer: Purnamrita Sarkar Scribe: Giorgio Paulon, Carlos Zanini Disclaimer: These scribe notes have been slightly proofread and may have
More informationStep-Stress Models and Associated Inference
Department of Mathematics & Statistics Indian Institute of Technology Kanpur August 19, 2014 Outline Accelerated Life Test 1 Accelerated Life Test 2 3 4 5 6 7 Outline Accelerated Life Test 1 Accelerated
More information,..., θ(2),..., θ(n)
Likelihoods for Multivariate Binary Data Log-Linear Model We have 2 n 1 distinct probabilities, but we wish to consider formulations that allow more parsimonious descriptions as a function of covariates.
More informationApplied Asymptotics Case studies in higher order inference
Applied Asymptotics Case studies in higher order inference Nancy Reid May 18, 2006 A.C. Davison, A. R. Brazzale, A. M. Staicu Introduction likelihood-based inference in parametric models higher order approximations
More informationThe comparative studies on reliability for Rayleigh models
Journal of the Korean Data & Information Science Society 018, 9, 533 545 http://dx.doi.org/10.7465/jkdi.018.9..533 한국데이터정보과학회지 The comparative studies on reliability for Rayleigh models Ji Eun Oh 1 Joong
More information