A Matrix Variate Skew-t Distribution

Size: px
Start display at page:

Download "A Matrix Variate Skew-t Distribution"

Transcription

1 A Matrx Varate Skew-t Dstrbuton Mchael P.B. Gallaugher and Paul D. McNcholas arv:73.364v3 [stat.me] 3 Apr 7 Dept. of Mathematcs & Statstcs, McMaster Unversty, Hamlton, Ontaro, Canada. Abstract Although there s ample work n the lterature dealng wth skewness n the multvarate settng, there s a relatve paucty of work n the matrx varate paradgm. Such work s, for example, useful for modellng three-way data. A matrx varate skew-t dstrbuton s derved based on a mean-varance matrx normal mxture. An expectaton-condtonal maxmzaton algorthm s developed for parameter estmaton. Smulated data are used for llustraton. Keywords: Matrx varate dstrbuton; skew-t dstrbuton Introducton Matrx varate dstrbutons have proven to be useful for modellng three-way data, such as multvarate longtudnal data. However, n most cases, the underlyng dstrbuton has been ellptcal such as the matrx varate normal and the matrx varate t dstrbutons. However, there has been relatvely lttle work done on matrx varate data that can account for skewness present n the data. The work that has been carred out n the area of matrx varate skew dstrbutons s mostly lmted to the matrx varate skew-normal dstrbuton. Heren, we derve a matrx varate skew-t dstrbuton. The remander of ths paper s lad out as follows. In Secton, some background s presented. In Secton 3, the densty of the matrx varate skew-t dstrbuton s derved and a parameter estmaton procedure s gven. Secton 4 looks at some smulatons, and we conclude wth a summary and some future work (Secton 5). Background. Matrx Varate Dstrbutons One natural method to model three-way data s to use a matrx-varate dstrbuton. There are many examples n the lterature of such dstrbutons, the most well-known beng the

2 matrx-normal dstrbuton. For notonal clarty, we use to denote a realzaton of a random matrx. An n p random matrx follows a matrx varate normal dstrbuton wth locaton parameter M and scale matrces Σ and Ψ of dmensons n n and p p, respectvely. We wrte N n p (M, Σ, Ψ) to denote such a random matrx and the densty of can be wrtten f( M, Σ, Ψ) = (π) np Σ p Ψ n exp tr ( Σ ( M)Ψ ( M) )}. () One well known property of the matrx varate normal dstrbuton (Harrar and Gupta, 8) s N n p (M, Σ, Ψ) vec( ) N np (vec(m), Ψ Σ) () where N np ( ) s the multvarate normal densty wth dmenson np, vec(m) s the vectorzaton of M, and s the Kronecker product. Although the matrx varate normal s arguably the most mathematcally tractable, there are examples of non-normal cases. One famous example s the Wshart dstrbuton (Wshart, 98) arsng as the dstrbuton of the sample covarance matrx of a multvarate normal sample. More recently, however, there has been some work done n the area of matrx skew dstrbutons such as the matrx-varate skew normal dstrbuton, e.g., Chen and Gupta (5), Domínguez-Molna et al. (7), and Harrar and Gupta (8). More nformaton on matrx varate dstrbutons can be found n Gupta and Nagar (999). Very recently, there has also been work done n the area of fnte mxtures. Specfcally, Anderlucc et al. (5) looked at clusterng and classfcaton of multvarate longtudnal data usng a mxture of matrx varate normal dstrbutons. Also, Doğru et al. (6), looked at mxtures of matrx varate t dstrbutons.. Normal Varance-Mean Mxtures Varous multvarate dstrbutons such as the multvarate t, and skew-t, the shfted asymmetrc Laplace dstrbuton, and the generalzed hyperbolc dstrbutons arse as specal cases of a normal varance-mean mxture (cf. McNcholas, 6, Ch. 6). In ths formulaton, the densty of a p-dmensonal random vector takes the form f(x) = whch s equvalent to the representaton φ p (x µ + wα, wσ)h(w θ)dw, = µ + W α + W V, (3) where V N p (, Σ) and W > s a latent random varable wth densty h(w θ). The multvarate skew-t dstrbuton wth ν degrees of freedom arses as a specal case wth W IG ( ν, ν ), where IG( ) denotes the nverse Gamma dstrbuton wth densty functon f(x α, β) = βα Γ(α) x α exp β x }.

3 .3 The Generalzed Inverse Gaussan Dstrbuton A random varable Y has a generalzed nverse Gaussan (GIG) dstrbuton wth parameters a, b and λ f ts densty functon can be wrtten as where f(y a, b, λ) = K λ (x) = ( a ) λ y λ b K λ ( ab) exp ay + } b y, y λ exp x ( y + )} dy y s the modfed Bessel functon of the thrd knd wth ndex λ. Several functons of GIG random varables have tractable expected values, e.g., b K λ+ ( ab) E(Y ) = a K λ ( ab), (4) ( ) a K λ+ ( ab) E = Y b K λ ( λ ab) b, (5) ( ) b E(log Y ) = log + a K λ ( ab) λ K λ( ab), (6) where a, b R +, λ R, and K λ ( ) s the modfed Bessel functon of the thrd knd wth ndex λ. These results wll prove to be useful for parameter estmaton for the matrx-varate skew-t dstrbuton. 3 Methodology 3. A Matrx Varate Skew-t Dstrbuton We wll say that an n p random matrx has a matrx varate skew-t dstrbuton, MVST n p (M, A, Σ, Ψ, ν), f can be wrtten = M + W A + W V, (7) where M and A are n p matrces, V N n p (, Σ, Ψ), and W IG ( ν, ν ). Analogous to ts multvarate counterpart, M s a locaton matrx, A s a skewness matrx, Σ and Ψ are scale matrces, and ν s the degrees of freedom. It then follows that w N n p (M + wa, wσ, Ψ) 3

4 and thus the jont densty of and W s f(, w ϑ) = f( w)f(w) = ν ν (π) np Σ p Ψ n Γ( ν )w exp ν+np [ ( tr Σ ( M wa)ψ ( M wa) ) + ν ]}, (8) w where ϑ = (M, A, Σ, Ψ, ν). We note that the exponental term n (8) can be wrtten as exp tr(σ ( M)Ψ A ) } exp [ ]} δ(; M, Σ, Ψ) + ν + wρ(a, Σ, Ψ), w where δ(; M, Σ, Ψ) = tr(σ ( M)Ψ ( M) ) and ρ(a, Σ, Ψ) = tr(σ AΨ A ). Therefore, the margnal densty of s f() = = f(, w)dw ν ν Σ p Ψ n Γ( ν ) exp tr(σ ( M)Ψ A ) } (π) np w ν+np exp [ δ(; M, Σ, Ψ) + ν Makng the change of varables gven by ρ(a, Σ, Ψ) y = w δ(; M, Σ, Ψ) + ν we can wrte f MVST ( ϑ) = ( ) ν ν exp tr(σ ( M)Ψ A )} (π) np Σ p Ψ n Γ( ν ) K ν+np w ]} + wρ(a, Σ, Ψ) dw. ( δ(; M, Σ, Ψ) + ν ) ν+np 4 ρ(a, Σ, Ψ) ( ) [ρ(a, Σ, Ψ)] [δ(; M, Σ, Ψ) + ν]. The densty of, as derved here, s consdered a matrx varate extenson of the multvarate skew-t densty used by Murray et al. (4a,b). As dscussed by Dutlleul (999) and Anderlucc et al. (5) n the matrx varate normal case, the estmates of Σ and Ψ are unque only up to a multplcatve constant. Indeed, f we let Σ = vσ and Ψ = (/v)ψ, v, the lkelhood s unchanged. Ths dentfablty ssue can be resolved, for example, 4

5 by settng tr(σ) = n or tr(ψ) = p. Note that Ψ Σ = Ψ Σ, so the estmate of the Kronecker product s unque. For the purposes of parameter estmaton, note that the condtonal densty of W s f(w ) = f( w)f(w) f() = [ρ(a, Σ, Ψ)/(δ(; M, Σ, Ψ) + ν)] λ w λ K λ ( ρ(a, Σ, Ψ)[δ(; M, Σ, Ψ) + ν]) exp Therefore, where λ = (ν + np)/. Fnally, we note that W GIG (ρ(a, Σ, Ψ), δ(; M, Σ, Ψ) + ν, λ), } ρ(a, Σ, Ψ)w + [δ(; M, Σ, Ψ) + ν]/w. MVST n p (M, A, Σ, Ψ, ν) vec( ) MST np (vec(m), vec(a), Ψ Σ, ν), (9) where MST np ( ) denotes the multvarate skew-t dstrbuton wth locaton parameter vec(m), skewness parameter vec(a), scale matrx Ψ Σ, and ν degrees of freedom. Ths can be easly seen from the representaton gven n (3) and the property of the matrx normal dstrbuton gven n (). Note that the normal varance-mean mxture representaton (7) as well as the relatonshp wth the multvarate skew-t dstrbuton (9) present two convenent methods to generate random matrces from the matrx varate skew t dstrbuton. The former s used n Secton Parameter Estmaton Suppose we observe a sample of N matrces,,... N from an n p matrx varate skewt dstrbuton. As wth the multvarate skew-t dstrbuton, we proceed as f the observed data s ncomplete, and ntroduce the latent varables W,..., W n. The complete-data loglkelhood s then l c (ϑ) =C + Nν ( ν ) log Np Nn ( ( ν )) log Σ log Ψ N log Γ ν + tr ( Σ ( M)Ψ A ) + tr ( Σ AΨ ( M) ) w [ tr(σ ( M)Ψ ( M) ) + ν ] log(w ) w tr(σ AΨ A ), where C s constant wth respect to the parameters. We proceed by usng an expectatoncondtonal maxmzaton (ECM) algorthm (Meng and Rubn, 993) descrbed overleaf. 5

6 ) Intalzaton: Intalze the parameters M, A, Σ, Ψ, ν. Set t = ) E Step: Update a, b, c, where a (t+) where and = E(W, ˆϑ (t) ) b (t+) c (t+) δ( ; ˆM (t), ˆΣ (t), ˆΨ (t) ) + ˆν (t) K λ (t) +(κ (t) ) K λ (t)(κ (t) ) = ρ(â(t), ˆΣ (t), ˆΨ (t) ) ( ) (t) = E, ˆϑ W = ρ(â(t), ˆΣ (t), ˆΨ (t) ) K +(κ (t) ) λ(t) δ( ; ˆM (t), ˆΣ (t), ˆΨ + (t) ) + ˆν (t) K λ (t)(κ (t) ) = E(log(W ), ˆϑ (t) ) ( δ( ; = log ˆM (t), ˆΣ (t), ˆΨ ) (t) ) + ˆν (t) ρ(â(t), ˆΣ (t), ˆΨ + (t) ) K λ (t)(κ (t) ) () ˆν (t) + np δ( ; ˆM (t), ˆΣ (t), ˆΨ (t) ) + ν (t) () λ K λ(κ (t) ) κ (t) = [ρ(â(t), ˆΣ (t), ˆΨ (t) )][δ( ; ˆM (t), ˆΣ (t), ˆΨ (t) ) + ˆν (t) ], λ=λ (t) λ (t) = ν(t) + np 3) Frst CM Step: Update the parameters M, A, ν. ) N ˆM (t+) (a (t+) b (t+) = N a(t+) b (t+) N, (3) () Â (t+) = ) N (b (t+) b (t+) N a(t+) b (t+) N, (4) where a (t+) = (/N) N a(t+) and b (t+) = (/N) N b(t+). The update for the degrees of freedom cannot be obtaned n closed form. Instead we solve (5) for ν to obtan ˆν (t+). ( ν ) ( ν ) log + ϕ N (b (t+) + c (t+) ) =, (5) where ϕ( ) s the dgamma functon. 6

7 4) Second CM Step: Update Σ [ ˆΣ (t+) = N ( Np b (t+) ( ˆM (t+) ) ˆΨ(t) ( ˆM (t+) ) Â(t+) ˆΨ(t) ( ˆM (t+) ) ( ˆM (t+) ) ˆΨ(t) Â (t+) + a (t+) Â (t+) ˆΨ(t) (t+) )] Â (6) 5) Thrd CM Step: Update Ψ ˆΨ (t+) = Nn [ N ( b (t+) ( Â(t+) ˆΣ(t+) ˆM ) (t+) )] + a (t+) Â (t+) ˆΣ(t+) Â (t+) ( ˆM (t+) ) ˆΣ(t+) ( ˆM (t+) ) ( ˆM (t+) ) ˆΣ(t+) Â (t+) (7) 6) Check Convergence: If not converged, set t = t + and return to step. Note that there are several optons for determnng convergence of ths ECM algorthm. In the smulatons n Secton 4, a crteron based on the Atken acceleraton (Atken, 96) s used. The Atken acceleraton at teraton t s a (t) = l(t+) l (t), (8) l (t) l (t ) where l (t) s the (observed) log-lkelhood at teraton t. The quantty n (8) can be used to derve an asymptotc estmate (.e., an estmate of the value after very many teratons) of the log-lkelhood at teraton t +,.e., l (t+) = l (t) + a (t) (l(t+) l (t) ) (cf. Böhnng et al., 994; Lndsay, 995). As n McNcholas et al. (), we stop our EM algorthms when l (t+) l (t) < ɛ, provded ths dfference s postve. As dscussed n Dutlleul (999) and Anderlucc et al. (5) for parameter estmaton n the matrx varate normal case, the estmates of Σ and Ψ are unque only up to a multplcatve constant. Indeed, f we let Σ = vσ and Ψ = (/v)ψ, v, the lkelhood s unchanged. However, we notce that, Ψ Σ = Ψ Σ, so the estmate of the Kronecker product s unque. 7

8 4 Smulatons We conduct two smulatons to llustrate the estmaton of the parameters. In both smulatons, we take 5 dfferent datasets of sze, from a 3 4 matrx skew-t dstrbuton. Also, n both smulatons, Σ = , Ψ = and ν = 4. In smulaton, we took the locaton and skewness matrx to be M and A, respectvely, and M and A n smulaton, where M =, A =, M = , A = In Fgures and, we show lne plots of the margnals for each column (labelled V, V, V3, V4) of a typcal dataset from smulatons and, respectvely. The dashed red lnes denote the means. In Fgure, the skewness n columns,, and 4, for smulaton, s very promnent when vsually compared to column 3, whch has zero skewness. The skewness s also apparent n the lneplots for smulaton, however, because the values of the skewness are generally less than those for smulaton, t s not as promnent. The component-wse means of the parameters as well as the component wse standard devatons are gven n Table. We see that the estmates of the mean matrx and skewness matrx are very close to the true value for both smulatons. Moreover, we see that the estmates of Σ and Ψ also correspond approxmately to the ther true values, and thus so would the Kronecker product, whch s not shown. 5 Dscusson The densty of a matrx varate skew-t dstrbuton was derved. Ths dstrbuton can be consdered as a three-way extenson of the multvarate skew-t dstrbuton. Parameter estmaton was carred out usng an ECM algorthm. Because the formulaton of multvarate skew-t dstrbuton ths work s based on s a specal case of the generalzed hyperbolc dstrbuton, t s reasonable to postulate an extenson to a broader class of matrx varate dstrbutons. Ongong work consders a fnte mxture of matrx varate skew-t dstrbutons for clusterng and classfcaton of three-way data. 8,.

9 a b V V c d.5 V3. V Fgure : Typcal Margnals for Smulaton for (a) V, (b) V, (c) V3 and (d) V4. The red dashed lnes denote the means. Table : Component wse averages and standard devatons for the estmated parameters for smulatons and. Smulaton M(sd) A(sd) Σ(sd) Ψ(sd) ν(sd) (.63) 4. (.9) Acknowledgements The authors gratefully acknowledge the fnancal support provded by the Vaner Canada Graduate Scholarshps (Gallaugher) and the Canada Research Chars program (McNcholas). 9

10 5 a b 5 5 V V c d 4 5 V3 V Fgure : Typcal Margnals for Smulaton for (a) V, (b) V, (c) V3 and (d) V4. The red dashed lnes denote the means. References Atken, A. C. (96). A seres formula for the roots of algebrac and transcendental equatons. Proceedngs of the Royal Socety of Ednburgh 45, 4. Anderlucc, L., C. Vrol, et al. (5). Covarance pattern mxture models for the analyss of multvarate heterogeneous longtudnal data. The Annals of Appled Statstcs 9 (), Böhnng, D., E. Detz, R. Schaub, P. Schlattmann, and B. Lndsay (994). The dstrbuton of the lkelhood rato for mxtures of denstes from the one-parameter exponental famly. Annals of the Insttute of Statstcal Mathematcs 46, Chen, J. T. and A. K. Gupta (5). Matrx varate skew normal dstrbutons. Statstcs 39 (3), Doğru, F. Z., Y. M. Bulut, and O. Arslan (6). Fnte mxtures of matrx varate t dstrbutons. Gaz Unversty Journal of Scence 9 (),

11 Domínguez-Molna, J. A., G. González-Farías, R. Ramos-Quroga, and A. K. Gupta (7). A matrx varate closed skew-normal dstrbuton wth applcatons to stochastc fronter analyss. Communcatons n Statstcs Theory and Methods 36 (9), Dutlleul, P. (999). The MLE algorthm for the matrx normal dstrbuton. Journal of Statstcal Computaton and Smulaton 64 (), 5 3. Gupta, A. K. and D. K. Nagar (999). Matrx Varate Dstrbutons. Boca Raton: Chapman & Hall/CRC Press. Harrar, S. W. and A. K. Gupta (8). On matrx varate skew-normal dstrbutons. Statstcs 4 (), Lndsay, B. G. (995). Mxture models: Theory, geometry and applcatons. In NSF-CBMS Regonal Conference Seres n Probablty and Statstcs, Volume 5. Calforna: Insttute of Mathematcal Statstcs: Hayward. McNcholas, P. D. (6). Mxture Model-Based Classfcaton. Boca Raton: Chapman & Hall/CRC Press. McNcholas, P. D., T. B. Murphy, A. F. McDad, and D. Frost (). Seral and parallel mplementatons of model-based clusterng va parsmonous Gaussan mxture models. Computatonal Statstcs and Data Analyss 54 (3), Meng,.-L. and D. B. Rubn (993). Maxmum lkelhood estmaton va the ECM algorthm: a general framework. Bometrka 8, Murray, P. M., R. B. Browne, and P. D. McNcholas (4a). Mxtures of skew-t factor analyzers. Computatonal Statstcs and Data Analyss 77, Murray, P. M., P. D. McNcholas, and R. B. Browne (4b). A mxture of common skew-t factor analyzers. Stat 3 (), Wshart, J. (98). The generalsed product moment dstrbuton n samples from a normal multvarate populaton. Bometrka, 3 5.

Three Skewed Matrix Variate Distributions

Three Skewed Matrix Variate Distributions Three Skewed Matrix Variate Distributions ariv:174.531v5 [stat.me] 13 Aug 18 Michael P.B. Gallaugher and Paul D. McNicholas Dept. of Mathematics & Statistics, McMaster University, Hamilton, Ontario, Canada.

More information

On an Extension of Stochastic Approximation EM Algorithm for Incomplete Data Problems. Vahid Tadayon 1

On an Extension of Stochastic Approximation EM Algorithm for Incomplete Data Problems. Vahid Tadayon 1 On an Extenson of Stochastc Approxmaton EM Algorthm for Incomplete Data Problems Vahd Tadayon Abstract: The Stochastc Approxmaton EM (SAEM algorthm, a varant stochastc approxmaton of EM, s a versatle tool

More information

Parametric fractional imputation for missing data analysis. Jae Kwang Kim Survey Working Group Seminar March 29, 2010

Parametric fractional imputation for missing data analysis. Jae Kwang Kim Survey Working Group Seminar March 29, 2010 Parametrc fractonal mputaton for mssng data analyss Jae Kwang Km Survey Workng Group Semnar March 29, 2010 1 Outlne Introducton Proposed method Fractonal mputaton Approxmaton Varance estmaton Multple mputaton

More information

Computation of Higher Order Moments from Two Multinomial Overdispersion Likelihood Models

Computation of Higher Order Moments from Two Multinomial Overdispersion Likelihood Models Computaton of Hgher Order Moments from Two Multnomal Overdsperson Lkelhood Models BY J. T. NEWCOMER, N. K. NEERCHAL Department of Mathematcs and Statstcs, Unversty of Maryland, Baltmore County, Baltmore,

More information

MATH 829: Introduction to Data Mining and Analysis The EM algorithm (part 2)

MATH 829: Introduction to Data Mining and Analysis The EM algorithm (part 2) 1/16 MATH 829: Introducton to Data Mnng and Analyss The EM algorthm (part 2) Domnque Gullot Departments of Mathematcal Scences Unversty of Delaware Aprl 20, 2016 Recall 2/16 We are gven ndependent observatons

More information

Conjugacy and the Exponential Family

Conjugacy and the Exponential Family CS281B/Stat241B: Advanced Topcs n Learnng & Decson Makng Conjugacy and the Exponental Famly Lecturer: Mchael I. Jordan Scrbes: Bran Mlch 1 Conjugacy In the prevous lecture, we saw conjugate prors for the

More information

Computing MLE Bias Empirically

Computing MLE Bias Empirically Computng MLE Bas Emprcally Kar Wa Lm Australan atonal Unversty January 3, 27 Abstract Ths note studes the bas arses from the MLE estmate of the rate parameter and the mean parameter of an exponental dstrbuton.

More information

Hidden Markov Models & The Multivariate Gaussian (10/26/04)

Hidden Markov Models & The Multivariate Gaussian (10/26/04) CS281A/Stat241A: Statstcal Learnng Theory Hdden Markov Models & The Multvarate Gaussan (10/26/04) Lecturer: Mchael I. Jordan Scrbes: Jonathan W. Hu 1 Hdden Markov Models As a bref revew, hdden Markov models

More information

Using T.O.M to Estimate Parameter of distributions that have not Single Exponential Family

Using T.O.M to Estimate Parameter of distributions that have not Single Exponential Family IOSR Journal of Mathematcs IOSR-JM) ISSN: 2278-5728. Volume 3, Issue 3 Sep-Oct. 202), PP 44-48 www.osrjournals.org Usng T.O.M to Estmate Parameter of dstrbutons that have not Sngle Exponental Famly Jubran

More information

Estimation: Part 2. Chapter GREG estimation

Estimation: Part 2. Chapter GREG estimation Chapter 9 Estmaton: Part 2 9. GREG estmaton In Chapter 8, we have seen that the regresson estmator s an effcent estmator when there s a lnear relatonshp between y and x. In ths chapter, we generalzed the

More information

Robust mixture modeling using multivariate skew t distributions

Robust mixture modeling using multivariate skew t distributions Robust mxture modelng usng multvarate skew t dstrbutons Tsung-I Ln Department of Appled Mathematcs and Insttute of Statstcs Natonal Chung Hsng Unversty, Tawan August, 1 T.I. Ln (NCHU Natonal Chung Hsng

More information

ANSWERS. Problem 1. and the moment generating function (mgf) by. defined for any real t. Use this to show that E( U) var( U)

ANSWERS. Problem 1. and the moment generating function (mgf) by. defined for any real t. Use this to show that E( U) var( U) Econ 413 Exam 13 H ANSWERS Settet er nndelt 9 deloppgaver, A,B,C, som alle anbefales å telle lkt for å gøre det ltt lettere å stå. Svar er gtt . Unfortunately, there s a prntng error n the hnt of

More information

Gaussian Mixture Models

Gaussian Mixture Models Lab Gaussan Mxture Models Lab Objectve: Understand the formulaton of Gaussan Mxture Models (GMMs) and how to estmate GMM parameters. You ve already seen GMMs as the observaton dstrbuton n certan contnuous

More information

The EM Algorithm (Dempster, Laird, Rubin 1977) The missing data or incomplete data setting: ODL(φ;Y ) = [Y;φ] = [Y X,φ][X φ] = X

The EM Algorithm (Dempster, Laird, Rubin 1977) The missing data or incomplete data setting: ODL(φ;Y ) = [Y;φ] = [Y X,φ][X φ] = X The EM Algorthm (Dempster, Lard, Rubn 1977 The mssng data or ncomplete data settng: An Observed Data Lkelhood (ODL that s a mxture or ntegral of Complete Data Lkelhoods (CDL. (1a ODL(;Y = [Y;] = [Y,][

More information

Solutions Homework 4 March 5, 2018

Solutions Homework 4 March 5, 2018 1 Solutons Homework 4 March 5, 018 Soluton to Exercse 5.1.8: Let a IR be a translaton and c > 0 be a re-scalng. ˆb1 (cx + a) cx n + a (cx 1 + a) c x n x 1 cˆb 1 (x), whch shows ˆb 1 s locaton nvarant and

More information

An Application of Fuzzy Hypotheses Testing in Radar Detection

An Application of Fuzzy Hypotheses Testing in Radar Detection Proceedngs of the th WSES Internatonal Conference on FUZZY SYSEMS n pplcaton of Fuy Hypotheses estng n Radar Detecton.K.ELSHERIF, F.M.BBDY, G.M.BDELHMID Department of Mathematcs Mltary echncal Collage

More information

Finite Mixture Models and Expectation Maximization. Most slides are from: Dr. Mario Figueiredo, Dr. Anil Jain and Dr. Rong Jin

Finite Mixture Models and Expectation Maximization. Most slides are from: Dr. Mario Figueiredo, Dr. Anil Jain and Dr. Rong Jin Fnte Mxture Models and Expectaton Maxmzaton Most sldes are from: Dr. Maro Fgueredo, Dr. Anl Jan and Dr. Rong Jn Recall: The Supervsed Learnng Problem Gven a set of n samples X {(x, y )},,,n Chapter 3 of

More information

First Year Examination Department of Statistics, University of Florida

First Year Examination Department of Statistics, University of Florida Frst Year Examnaton Department of Statstcs, Unversty of Florda May 7, 010, 8:00 am - 1:00 noon Instructons: 1. You have four hours to answer questons n ths examnaton.. You must show your work to receve

More information

STATS 306B: Unsupervised Learning Spring Lecture 10 April 30

STATS 306B: Unsupervised Learning Spring Lecture 10 April 30 STATS 306B: Unsupervsed Learnng Sprng 2014 Lecture 10 Aprl 30 Lecturer: Lester Mackey Scrbe: Joey Arthur, Rakesh Achanta 10.1 Factor Analyss 10.1.1 Recap Recall the factor analyss (FA) model for lnear

More information

Maximum Likelihood Estimation of Binary Dependent Variables Models: Probit and Logit. 1. General Formulation of Binary Dependent Variables Models

Maximum Likelihood Estimation of Binary Dependent Variables Models: Probit and Logit. 1. General Formulation of Binary Dependent Variables Models ECO 452 -- OE 4: Probt and Logt Models ECO 452 -- OE 4 Maxmum Lkelhood Estmaton of Bnary Dependent Varables Models: Probt and Logt hs note demonstrates how to formulate bnary dependent varables models

More information

3.1 Expectation of Functions of Several Random Variables. )' be a k-dimensional discrete or continuous random vector, with joint PMF p (, E X E X1 E X

3.1 Expectation of Functions of Several Random Variables. )' be a k-dimensional discrete or continuous random vector, with joint PMF p (, E X E X1 E X Statstcs 1: Probablty Theory II 37 3 EPECTATION OF SEVERAL RANDOM VARIABLES As n Probablty Theory I, the nterest n most stuatons les not on the actual dstrbuton of a random vector, but rather on a number

More information

Generalized Linear Methods

Generalized Linear Methods Generalzed Lnear Methods 1 Introducton In the Ensemble Methods the general dea s that usng a combnaton of several weak learner one could make a better learner. More formally, assume that we have a set

More information

Parameters Estimation of the Modified Weibull Distribution Based on Type I Censored Samples

Parameters Estimation of the Modified Weibull Distribution Based on Type I Censored Samples Appled Mathematcal Scences, Vol. 5, 011, no. 59, 899-917 Parameters Estmaton of the Modfed Webull Dstrbuton Based on Type I Censored Samples Soufane Gasm École Supereure des Scences et Technques de Tuns

More information

Supplementary material: Margin based PU Learning. Matrix Concentration Inequalities

Supplementary material: Margin based PU Learning. Matrix Concentration Inequalities Supplementary materal: Margn based PU Learnng We gve the complete proofs of Theorem and n Secton We frst ntroduce the well-known concentraton nequalty, so the covarance estmator can be bounded Then we

More information

Parametric fractional imputation for missing data analysis

Parametric fractional imputation for missing data analysis Secton on Survey Research Methods JSM 2008 Parametrc fractonal mputaton for mssng data analyss Jae Kwang Km Wayne Fuller Abstract Under a parametrc model for mssng data, the EM algorthm s a popular tool

More information

Interval Estimation of Stress-Strength Reliability for a General Exponential Form Distribution with Different Unknown Parameters

Interval Estimation of Stress-Strength Reliability for a General Exponential Form Distribution with Different Unknown Parameters Internatonal Journal of Statstcs and Probablty; Vol. 6, No. 6; November 17 ISSN 197-73 E-ISSN 197-74 Publshed by Canadan Center of Scence and Educaton Interval Estmaton of Stress-Strength Relablty for

More information

Lecture 3: Probability Distributions

Lecture 3: Probability Distributions Lecture 3: Probablty Dstrbutons Random Varables Let us begn by defnng a sample space as a set of outcomes from an experment. We denote ths by S. A random varable s a functon whch maps outcomes nto the

More information

Dr. Shalabh Department of Mathematics and Statistics Indian Institute of Technology Kanpur

Dr. Shalabh Department of Mathematics and Statistics Indian Institute of Technology Kanpur Analyss of Varance and Desgn of Exerments-I MODULE III LECTURE - 2 EXPERIMENTAL DESIGN MODELS Dr. Shalabh Deartment of Mathematcs and Statstcs Indan Insttute of Technology Kanur 2 We consder the models

More information

Econ107 Applied Econometrics Topic 3: Classical Model (Studenmund, Chapter 4)

Econ107 Applied Econometrics Topic 3: Classical Model (Studenmund, Chapter 4) I. Classcal Assumptons Econ7 Appled Econometrcs Topc 3: Classcal Model (Studenmund, Chapter 4) We have defned OLS and studed some algebrac propertes of OLS. In ths topc we wll study statstcal propertes

More information

Composite Hypotheses testing

Composite Hypotheses testing Composte ypotheses testng In many hypothess testng problems there are many possble dstrbutons that can occur under each of the hypotheses. The output of the source s a set of parameters (ponts n a parameter

More information

ENG 8801/ Special Topics in Computer Engineering: Pattern Recognition. Memorial University of Newfoundland Pattern Recognition

ENG 8801/ Special Topics in Computer Engineering: Pattern Recognition. Memorial University of Newfoundland Pattern Recognition EG 880/988 - Specal opcs n Computer Engneerng: Pattern Recognton Memoral Unversty of ewfoundland Pattern Recognton Lecture 7 May 3, 006 http://wwwengrmunca/~charlesr Offce Hours: uesdays hursdays 8:30-9:30

More information

Gaussian process classification: a message-passing viewpoint

Gaussian process classification: a message-passing viewpoint Gaussan process classfcaton: a message-passng vewpont Flpe Rodrgues fmpr@de.uc.pt November 014 Abstract The goal of ths short paper s to provde a message-passng vewpont of the Expectaton Propagaton EP

More information

Gaussian Conditional Random Field Network for Semantic Segmentation - Supplementary Material

Gaussian Conditional Random Field Network for Semantic Segmentation - Supplementary Material Gaussan Condtonal Random Feld Networ for Semantc Segmentaton - Supplementary Materal Ravtea Vemulapall, Oncel Tuzel *, Mng-Yu Lu *, and Rama Chellappa Center for Automaton Research, UMIACS, Unversty of

More information

Andreas C. Drichoutis Agriculural University of Athens. Abstract

Andreas C. Drichoutis Agriculural University of Athens. Abstract Heteroskedastcty, the sngle crossng property and ordered response models Andreas C. Drchouts Agrculural Unversty of Athens Panagots Lazards Agrculural Unversty of Athens Rodolfo M. Nayga, Jr. Texas AMUnversty

More information

Module 3 LOSSY IMAGE COMPRESSION SYSTEMS. Version 2 ECE IIT, Kharagpur

Module 3 LOSSY IMAGE COMPRESSION SYSTEMS. Version 2 ECE IIT, Kharagpur Module 3 LOSSY IMAGE COMPRESSION SYSTEMS Verson ECE IIT, Kharagpur Lesson 6 Theory of Quantzaton Verson ECE IIT, Kharagpur Instructonal Objectves At the end of ths lesson, the students should be able to:

More information

ANOMALIES OF THE MAGNITUDE OF THE BIAS OF THE MAXIMUM LIKELIHOOD ESTIMATOR OF THE REGRESSION SLOPE

ANOMALIES OF THE MAGNITUDE OF THE BIAS OF THE MAXIMUM LIKELIHOOD ESTIMATOR OF THE REGRESSION SLOPE P a g e ANOMALIES OF THE MAGNITUDE OF THE BIAS OF THE MAXIMUM LIKELIHOOD ESTIMATOR OF THE REGRESSION SLOPE Darmud O Drscoll ¹, Donald E. Ramrez ² ¹ Head of Department of Mathematcs and Computer Studes

More information

On mutual information estimation for mixed-pair random variables

On mutual information estimation for mixed-pair random variables On mutual nformaton estmaton for mxed-par random varables November 3, 218 Aleksandr Beknazaryan, Xn Dang and Haln Sang 1 Department of Mathematcs, The Unversty of Msssspp, Unversty, MS 38677, USA. E-mal:

More information

Comparison of the Population Variance Estimators. of 2-Parameter Exponential Distribution Based on. Multiple Criteria Decision Making Method

Comparison of the Population Variance Estimators. of 2-Parameter Exponential Distribution Based on. Multiple Criteria Decision Making Method Appled Mathematcal Scences, Vol. 7, 0, no. 47, 07-0 HIARI Ltd, www.m-hkar.com Comparson of the Populaton Varance Estmators of -Parameter Exponental Dstrbuton Based on Multple Crtera Decson Makng Method

More information

Joint Statistical Meetings - Biopharmaceutical Section

Joint Statistical Meetings - Biopharmaceutical Section Iteratve Ch-Square Test for Equvalence of Multple Treatment Groups Te-Hua Ng*, U.S. Food and Drug Admnstraton 1401 Rockvlle Pke, #200S, HFM-217, Rockvlle, MD 20852-1448 Key Words: Equvalence Testng; Actve

More information

Simulated Power of the Discrete Cramér-von Mises Goodness-of-Fit Tests

Simulated Power of the Discrete Cramér-von Mises Goodness-of-Fit Tests Smulated of the Cramér-von Mses Goodness-of-Ft Tests Steele, M., Chaselng, J. and 3 Hurst, C. School of Mathematcal and Physcal Scences, James Cook Unversty, Australan School of Envronmental Studes, Grffth

More information

Econ Statistical Properties of the OLS estimator. Sanjaya DeSilva

Econ Statistical Properties of the OLS estimator. Sanjaya DeSilva Econ 39 - Statstcal Propertes of the OLS estmator Sanjaya DeSlva September, 008 1 Overvew Recall that the true regresson model s Y = β 0 + β 1 X + u (1) Applyng the OLS method to a sample of data, we estmate

More information

Dr. Shalabh Department of Mathematics and Statistics Indian Institute of Technology Kanpur

Dr. Shalabh Department of Mathematics and Statistics Indian Institute of Technology Kanpur Analyss of Varance and Desgn of Experment-I MODULE VII LECTURE - 3 ANALYSIS OF COVARIANCE Dr Shalabh Department of Mathematcs and Statstcs Indan Insttute of Technology Kanpur Any scentfc experment s performed

More information

Multivariate Ratio Estimator of the Population Total under Stratified Random Sampling

Multivariate Ratio Estimator of the Population Total under Stratified Random Sampling Open Journal of Statstcs, 0,, 300-304 ttp://dx.do.org/0.436/ojs.0.3036 Publsed Onlne July 0 (ttp://www.scrp.org/journal/ojs) Multvarate Rato Estmator of te Populaton Total under Stratfed Random Samplng

More information

Effects of Ignoring Correlations When Computing Sample Chi-Square. John W. Fowler February 26, 2012

Effects of Ignoring Correlations When Computing Sample Chi-Square. John W. Fowler February 26, 2012 Effects of Ignorng Correlatons When Computng Sample Ch-Square John W. Fowler February 6, 0 It can happen that ch-square must be computed for a sample whose elements are correlated to an unknown extent.

More information

Chat eld, C. and A.J.Collins, Introduction to multivariate analysis. Chapman & Hall, 1980

Chat eld, C. and A.J.Collins, Introduction to multivariate analysis. Chapman & Hall, 1980 MT07: Multvarate Statstcal Methods Mke Tso: emal mke.tso@manchester.ac.uk Webpage for notes: http://www.maths.manchester.ac.uk/~mkt/new_teachng.htm. Introducton to multvarate data. Books Chat eld, C. and

More information

A quantum-statistical-mechanical extension of Gaussian mixture model

A quantum-statistical-mechanical extension of Gaussian mixture model A quantum-statstcal-mechancal extenson of Gaussan mxture model Kazuyuk Tanaka, and Koj Tsuda 2 Graduate School of Informaton Scences, Tohoku Unversty, 6-3-09 Aramak-aza-aoba, Aoba-ku, Senda 980-8579, Japan

More information

Lecture 12: Classification

Lecture 12: Classification Lecture : Classfcaton g Dscrmnant functons g The optmal Bayes classfer g Quadratc classfers g Eucldean and Mahalanobs metrcs g K Nearest Neghbor Classfers Intellgent Sensor Systems Rcardo Guterrez-Osuna

More information

Population Design in Nonlinear Mixed Effects Multiple Response Models: extension of PFIM and evaluation by simulation with NONMEM and MONOLIX

Population Design in Nonlinear Mixed Effects Multiple Response Models: extension of PFIM and evaluation by simulation with NONMEM and MONOLIX Populaton Desgn n Nonlnear Mxed Effects Multple Response Models: extenson of PFIM and evaluaton by smulaton wth NONMEM and MONOLIX May 4th 007 Carolne Bazzol, Sylve Retout, France Mentré Inserm U738 Unversty

More information

Simulation and Probability Distribution

Simulation and Probability Distribution CHAPTER Probablty, Statstcs, and Relablty for Engneers and Scentsts Second Edton PROBABILIT DISTRIBUTION FOR CONTINUOUS RANDOM VARIABLES A. J. Clark School of Engneerng Department of Cvl and Envronmental

More information

Chapter 14: Logit and Probit Models for Categorical Response Variables

Chapter 14: Logit and Probit Models for Categorical Response Variables Chapter 4: Logt and Probt Models for Categorcal Response Varables Sect 4. Models for Dchotomous Data We wll dscuss only ths secton of Chap 4, whch s manly about Logstc Regresson, a specal case of the famly

More information

BOOTSTRAP METHOD FOR TESTING OF EQUALITY OF SEVERAL MEANS. M. Krishna Reddy, B. Naveen Kumar and Y. Ramu

BOOTSTRAP METHOD FOR TESTING OF EQUALITY OF SEVERAL MEANS. M. Krishna Reddy, B. Naveen Kumar and Y. Ramu BOOTSTRAP METHOD FOR TESTING OF EQUALITY OF SEVERAL MEANS M. Krshna Reddy, B. Naveen Kumar and Y. Ramu Department of Statstcs, Osmana Unversty, Hyderabad -500 007, Inda. nanbyrozu@gmal.com, ramu0@gmal.com

More information

EM and Structure Learning

EM and Structure Learning EM and Structure Learnng Le Song Machne Learnng II: Advanced Topcs CSE 8803ML, Sprng 2012 Partally observed graphcal models Mxture Models N(μ 1, Σ 1 ) Z X N N(μ 2, Σ 2 ) 2 Gaussan mxture model Consder

More information

Linear Approximation with Regularization and Moving Least Squares

Linear Approximation with Regularization and Moving Least Squares Lnear Approxmaton wth Regularzaton and Movng Least Squares Igor Grešovn May 007 Revson 4.6 (Revson : March 004). 5 4 3 0.5 3 3.5 4 Contents: Lnear Fttng...4. Weghted Least Squares n Functon Approxmaton...

More information

Differentiating Gaussian Processes

Differentiating Gaussian Processes Dfferentatng Gaussan Processes Andrew McHutchon Aprl 17, 013 1 Frst Order Dervatve of the Posteror Mean The posteror mean of a GP s gven by, f = x, X KX, X 1 y x, X α 1 Only the x, X term depends on the

More information

Structure and Drive Paul A. Jensen Copyright July 20, 2003

Structure and Drive Paul A. Jensen Copyright July 20, 2003 Structure and Drve Paul A. Jensen Copyrght July 20, 2003 A system s made up of several operatons wth flow passng between them. The structure of the system descrbes the flow paths from nputs to outputs.

More information

See Book Chapter 11 2 nd Edition (Chapter 10 1 st Edition)

See Book Chapter 11 2 nd Edition (Chapter 10 1 st Edition) Count Data Models See Book Chapter 11 2 nd Edton (Chapter 10 1 st Edton) Count data consst of non-negatve nteger values Examples: number of drver route changes per week, the number of trp departure changes

More information

Effective plots to assess bias and precision in method comparison studies

Effective plots to assess bias and precision in method comparison studies Effectve plots to assess bas and precson n method comparson studes Bern, November, 016 Patrck Taffé, PhD Insttute of Socal and Preventve Medcne () Unversty of Lausanne, Swtzerland Patrck.Taffe@chuv.ch

More information

Math 680: Exercise 4 The EM Algorithm

Math 680: Exercise 4 The EM Algorithm Math 680: Exercse 4 The EM Algorthm The galaxes data Task 1. See the scrpt fle http://www.math.mcgll.ca/dstephens/680/r/ex4-015.r. We have so K = 5 s preferred usng EM. K BIC 3 159.86 4 160.333 5 1590.867

More information

Statistical inference for generalized Pareto distribution based on progressive Type-II censored data with random removals

Statistical inference for generalized Pareto distribution based on progressive Type-II censored data with random removals Internatonal Journal of Scentfc World, 2 1) 2014) 1-9 c Scence Publshng Corporaton www.scencepubco.com/ndex.php/ijsw do: 10.14419/jsw.v21.1780 Research Paper Statstcal nference for generalzed Pareto dstrbuton

More information

An (almost) unbiased estimator for the S-Gini index

An (almost) unbiased estimator for the S-Gini index An (almost unbased estmator for the S-Gn ndex Thomas Demuynck February 25, 2009 Abstract Ths note provdes an unbased estmator for the absolute S-Gn and an almost unbased estmator for the relatve S-Gn for

More information

ERROR RATES STABILITY OF THE HOMOSCEDASTIC DISCRIMINANT FUNCTION

ERROR RATES STABILITY OF THE HOMOSCEDASTIC DISCRIMINANT FUNCTION ISSN - 77-0593 UNAAB 00 Journal of Natural Scences, Engneerng and Technology ERROR RATES STABILITY OF THE HOMOSCEDASTIC DISCRIMINANT FUNCTION A. ADEBANJI, S. NOKOE AND O. IYANIWURA 3 *Department of Mathematcs,

More information

Chapter 5. Solution of System of Linear Equations. Module No. 6. Solution of Inconsistent and Ill Conditioned Systems

Chapter 5. Solution of System of Linear Equations. Module No. 6. Solution of Inconsistent and Ill Conditioned Systems Numercal Analyss by Dr. Anta Pal Assstant Professor Department of Mathematcs Natonal Insttute of Technology Durgapur Durgapur-713209 emal: anta.bue@gmal.com 1 . Chapter 5 Soluton of System of Lnear Equatons

More information

Maximum Likelihood Estimation

Maximum Likelihood Estimation Maxmum Lkelhood Estmaton INFO-2301: Quanttatve Reasonng 2 Mchael Paul and Jordan Boyd-Graber MARCH 7, 2017 INFO-2301: Quanttatve Reasonng 2 Paul and Boyd-Graber Maxmum Lkelhood Estmaton 1 of 9 Why MLE?

More information

U-Pb Geochronology Practical: Background

U-Pb Geochronology Practical: Background U-Pb Geochronology Practcal: Background Basc Concepts: accuracy: measure of the dfference between an expermental measurement and the true value precson: measure of the reproducblty of the expermental result

More information

Stat 642, Lecture notes for 01/27/ d i = 1 t. n i t nj. n j

Stat 642, Lecture notes for 01/27/ d i = 1 t. n i t nj. n j Stat 642, Lecture notes for 01/27/05 18 Rate Standardzaton Contnued: Note that f T n t where T s the cumulatve follow-up tme and n s the number of subjects at rsk at the mdpont or nterval, and d s the

More information

Lecture Notes on Linear Regression

Lecture Notes on Linear Regression Lecture Notes on Lnear Regresson Feng L fl@sdueducn Shandong Unversty, Chna Lnear Regresson Problem In regresson problem, we am at predct a contnuous target value gven an nput feature vector We assume

More information

MAXIMUM LIKELIHOOD FOR GENERALIZED LINEAR MODEL AND GENERALIZED ESTIMATING EQUATIONS

MAXIMUM LIKELIHOOD FOR GENERALIZED LINEAR MODEL AND GENERALIZED ESTIMATING EQUATIONS www.arpapress.com/volumes/vol18issue1/ijrras_18_1_08.pdf MAXIMUM LIKELIHOOD FOR GENERALIZED LINEAR MODEL AND GENERALIZED ESTIMATING EQUATIONS A. Lanan MAM Laboratory. Department of Mathematcs. Unversty

More information

Improvement in Estimating the Population Mean Using Exponential Estimator in Simple Random Sampling

Improvement in Estimating the Population Mean Using Exponential Estimator in Simple Random Sampling Bulletn of Statstcs & Economcs Autumn 009; Volume 3; Number A09; Bull. Stat. Econ. ISSN 0973-70; Copyrght 009 by BSE CESER Improvement n Estmatng the Populaton Mean Usng Eponental Estmator n Smple Random

More information

Reports of the Institute of Biostatistics

Reports of the Institute of Biostatistics Reports of the Insttute of Bostatstcs No 0 / 2007 Lebnz Unversty of Hannover Natural Scences Faculty Ttel: IUT for multple endponts Authors: Maro Hasler Introducton Some of the focus n new drug development

More information

4 Analysis of Variance (ANOVA) 5 ANOVA. 5.1 Introduction. 5.2 Fixed Effects ANOVA

4 Analysis of Variance (ANOVA) 5 ANOVA. 5.1 Introduction. 5.2 Fixed Effects ANOVA 4 Analyss of Varance (ANOVA) 5 ANOVA 51 Introducton ANOVA ANOVA s a way to estmate and test the means of multple populatons We wll start wth one-way ANOVA If the populatons ncluded n the study are selected

More information

Hydrological statistics. Hydrological statistics and extremes

Hydrological statistics. Hydrological statistics and extremes 5--0 Stochastc Hydrology Hydrologcal statstcs and extremes Marc F.P. Berkens Professor of Hydrology Faculty of Geoscences Hydrologcal statstcs Mostly concernes wth the statstcal analyss of hydrologcal

More information

The RS Generalized Lambda Distribution Based Calibration Model

The RS Generalized Lambda Distribution Based Calibration Model Internatonal Journal of Statstcs and Probablty; Vol. 2, No. 1; 2013 ISSN 1927-7032 E-ISSN 1927-7040 Publshed by Canadan Center of Scence and Educaton The RS Generalzed Lambda Dstrbuton Based Calbraton

More information

j) = 1 (note sigma notation) ii. Continuous random variable (e.g. Normal distribution) 1. density function: f ( x) 0 and f ( x) dx = 1

j) = 1 (note sigma notation) ii. Continuous random variable (e.g. Normal distribution) 1. density function: f ( x) 0 and f ( x) dx = 1 Random varables Measure of central tendences and varablty (means and varances) Jont densty functons and ndependence Measures of assocaton (covarance and correlaton) Interestng result Condtonal dstrbutons

More information

2E Pattern Recognition Solutions to Introduction to Pattern Recognition, Chapter 2: Bayesian pattern classification

2E Pattern Recognition Solutions to Introduction to Pattern Recognition, Chapter 2: Bayesian pattern classification E395 - Pattern Recognton Solutons to Introducton to Pattern Recognton, Chapter : Bayesan pattern classfcaton Preface Ths document s a soluton manual for selected exercses from Introducton to Pattern Recognton

More information

Logistic Regression. CAP 5610: Machine Learning Instructor: Guo-Jun QI

Logistic Regression. CAP 5610: Machine Learning Instructor: Guo-Jun QI Logstc Regresson CAP 561: achne Learnng Instructor: Guo-Jun QI Bayes Classfer: A Generatve model odel the posteror dstrbuton P(Y X) Estmate class-condtonal dstrbuton P(X Y) for each Y Estmate pror dstrbuton

More information

Goodness of fit and Wilks theorem

Goodness of fit and Wilks theorem DRAFT 0.0 Glen Cowan 3 June, 2013 Goodness of ft and Wlks theorem Suppose we model data y wth a lkelhood L(µ) that depends on a set of N parameters µ = (µ 1,...,µ N ). Defne the statstc t µ ln L(µ) L(ˆµ),

More information

Bayesian predictive Configural Frequency Analysis

Bayesian predictive Configural Frequency Analysis Psychologcal Test and Assessment Modelng, Volume 54, 2012 (3), 285-292 Bayesan predctve Confgural Frequency Analyss Eduardo Gutérrez-Peña 1 Abstract Confgural Frequency Analyss s a method for cell-wse

More information

Statistical pattern recognition

Statistical pattern recognition Statstcal pattern recognton Bayes theorem Problem: decdng f a patent has a partcular condton based on a partcular test However, the test s mperfect Someone wth the condton may go undetected (false negatve

More information

How its computed. y outcome data λ parameters hyperparameters. where P denotes the Laplace approximation. k i k k. Andrew B Lawson 2013

How its computed. y outcome data λ parameters hyperparameters. where P denotes the Laplace approximation. k i k k. Andrew B Lawson 2013 Andrew Lawson MUSC INLA INLA s a relatvely new tool that can be used to approxmate posteror dstrbutons n Bayesan models INLA stands for ntegrated Nested Laplace Approxmaton The approxmaton has been known

More information

The Order Relation and Trace Inequalities for. Hermitian Operators

The Order Relation and Trace Inequalities for. Hermitian Operators Internatonal Mathematcal Forum, Vol 3, 08, no, 507-57 HIKARI Ltd, wwwm-hkarcom https://doorg/0988/mf088055 The Order Relaton and Trace Inequaltes for Hermtan Operators Y Huang School of Informaton Scence

More information

Primer on High-Order Moment Estimators

Primer on High-Order Moment Estimators Prmer on Hgh-Order Moment Estmators Ton M. Whted July 2007 The Errors-n-Varables Model We wll start wth the classcal EIV for one msmeasured regressor. The general case s n Erckson and Whted Econometrc

More information

x = , so that calculated

x = , so that calculated Stat 4, secton Sngle Factor ANOVA notes by Tm Plachowsk n chapter 8 we conducted hypothess tests n whch we compared a sngle sample s mean or proporton to some hypotheszed value Chapter 9 expanded ths to

More information

Durban Watson for Testing the Lack-of-Fit of Polynomial Regression Models without Replications

Durban Watson for Testing the Lack-of-Fit of Polynomial Regression Models without Replications Durban Watson for Testng the Lack-of-Ft of Polynomal Regresson Models wthout Replcatons Ruba A. Alyaf, Maha A. Omar, Abdullah A. Al-Shha ralyaf@ksu.edu.sa, maomar@ksu.edu.sa, aalshha@ksu.edu.sa Department

More information

Non-Mixture Cure Model for Interval Censored Data: Simulation Study ABSTRACT

Non-Mixture Cure Model for Interval Censored Data: Simulation Study ABSTRACT Malaysan Journal of Mathematcal Scences 8(S): 37-44 (2014) Specal Issue: Internatonal Conference on Mathematcal Scences and Statstcs 2013 (ICMSS2013) MALAYSIAN JOURNAL OF MATHEMATICAL SCIENCES Journal

More information

MIMA Group. Chapter 2 Bayesian Decision Theory. School of Computer Science and Technology, Shandong University. Xin-Shun SDU

MIMA Group. Chapter 2 Bayesian Decision Theory. School of Computer Science and Technology, Shandong University. Xin-Shun SDU Group M D L M Chapter Bayesan Decson heory Xn-Shun Xu @ SDU School of Computer Scence and echnology, Shandong Unversty Bayesan Decson heory Bayesan decson theory s a statstcal approach to data mnng/pattern

More information

The Multiple Classical Linear Regression Model (CLRM): Specification and Assumptions. 1. Introduction

The Multiple Classical Linear Regression Model (CLRM): Specification and Assumptions. 1. Introduction ECONOMICS 5* -- NOTE (Summary) ECON 5* -- NOTE The Multple Classcal Lnear Regresson Model (CLRM): Specfcaton and Assumptons. Introducton CLRM stands for the Classcal Lnear Regresson Model. The CLRM s also

More information

Multivariate Nonparametric Tests of Independence

Multivariate Nonparametric Tests of Independence Multvarate Nonparametrc Tests of Independence Sara Tasknen, Hannu Oa + and Ronald H. Randles # Dept. of Mathematcs and Statstcs, Unversty of Jyväskylä + Tampere School of Publc Health, Unversty of Tampere

More information

Statistical Hypothesis Testing for Returns to Scale Using Data Envelopment Analysis

Statistical Hypothesis Testing for Returns to Scale Using Data Envelopment Analysis Statstcal Hypothess Testng for Returns to Scale Usng Data nvelopment nalyss M. ukushge a and I. Myara b a Graduate School of conomcs, Osaka Unversty, Osaka 560-0043, apan (mfuku@econ.osaka-u.ac.p) b Graduate

More information

Markov Chain Monte Carlo (MCMC), Gibbs Sampling, Metropolis Algorithms, and Simulated Annealing Bioinformatics Course Supplement

Markov Chain Monte Carlo (MCMC), Gibbs Sampling, Metropolis Algorithms, and Simulated Annealing Bioinformatics Course Supplement Markov Chan Monte Carlo MCMC, Gbbs Samplng, Metropols Algorthms, and Smulated Annealng 2001 Bonformatcs Course Supplement SNU Bontellgence Lab http://bsnuackr/ Outlne! Markov Chan Monte Carlo MCMC! Metropols-Hastngs

More information

4.3 Poisson Regression

4.3 Poisson Regression of teratvely reweghted least squares regressons (the IRLS algorthm). We do wthout gvng further detals, but nstead focus on the practcal applcaton. > glm(survval~log(weght)+age, famly="bnomal", data=baby)

More information

The lower and upper bounds on Perron root of nonnegative irreducible matrices

The lower and upper bounds on Perron root of nonnegative irreducible matrices Journal of Computatonal Appled Mathematcs 217 (2008) 259 267 wwwelsevercom/locate/cam The lower upper bounds on Perron root of nonnegatve rreducble matrces Guang-Xn Huang a,, Feng Yn b,keguo a a College

More information

Basic Statistical Analysis and Yield Calculations

Basic Statistical Analysis and Yield Calculations October 17, 007 Basc Statstcal Analyss and Yeld Calculatons Dr. José Ernesto Rayas Sánchez 1 Outlne Sources of desgn-performance uncertanty Desgn and development processes Desgn for manufacturablty A general

More information

Inexact Newton Methods for Inverse Eigenvalue Problems

Inexact Newton Methods for Inverse Eigenvalue Problems Inexact Newton Methods for Inverse Egenvalue Problems Zheng-jan Ba Abstract In ths paper, we survey some of the latest development n usng nexact Newton-lke methods for solvng nverse egenvalue problems.

More information

P R. Lecture 4. Theory and Applications of Pattern Recognition. Dept. of Electrical and Computer Engineering /

P R. Lecture 4. Theory and Applications of Pattern Recognition. Dept. of Electrical and Computer Engineering / Theory and Applcatons of Pattern Recognton 003, Rob Polkar, Rowan Unversty, Glassboro, NJ Lecture 4 Bayes Classfcaton Rule Dept. of Electrcal and Computer Engneerng 0909.40.0 / 0909.504.04 Theory & Applcatons

More information

On Outlier Robust Small Area Mean Estimate Based on Prediction of Empirical Distribution Function

On Outlier Robust Small Area Mean Estimate Based on Prediction of Empirical Distribution Function On Outler Robust Small Area Mean Estmate Based on Predcton of Emprcal Dstrbuton Functon Payam Mokhtaran Natonal Insttute of Appled Statstcs Research Australa Unversty of Wollongong Small Area Estmaton

More information

Which estimator of the dispersion parameter for the Gamma family generalized linear models is to be chosen?

Which estimator of the dispersion parameter for the Gamma family generalized linear models is to be chosen? STATISTICS Dalarna Unversty D-level Master s Thess 007 Whch estmator of the dsperson parameter for the Gamma famly generalzed lnear models s to be chosen? Submtted by: Juan Du Regstraton Number: 8096-T084

More information

arxiv: v1 [stat.me] 29 Jul 2017

arxiv: v1 [stat.me] 29 Jul 2017 Publshed n Statstca Neerlandca, 2016, vol. 70, no 4, p. 396-413. A Skew-Normal Copula-Drven GLMM Kalyan Das 1, Mohamad Elmasr 2 and Arusharka Sen 3 1 Unversty of Calcutta, 2 McGll Unversty and 3 Concorda

More information

LOW BIAS INTEGRATED PATH ESTIMATORS. James M. Calvin

LOW BIAS INTEGRATED PATH ESTIMATORS. James M. Calvin Proceedngs of the 007 Wnter Smulaton Conference S G Henderson, B Bller, M-H Hseh, J Shortle, J D Tew, and R R Barton, eds LOW BIAS INTEGRATED PATH ESTIMATORS James M Calvn Department of Computer Scence

More information

DERIVATION OF THE PROBABILITY PLOT CORRELATION COEFFICIENT TEST STATISTICS FOR THE GENERALIZED LOGISTIC DISTRIBUTION

DERIVATION OF THE PROBABILITY PLOT CORRELATION COEFFICIENT TEST STATISTICS FOR THE GENERALIZED LOGISTIC DISTRIBUTION Internatonal Worshop ADVANCES IN STATISTICAL HYDROLOGY May 3-5, Taormna, Italy DERIVATION OF THE PROBABILITY PLOT CORRELATION COEFFICIENT TEST STATISTICS FOR THE GENERALIZED LOGISTIC DISTRIBUTION by Sooyoung

More information

ECONOMETRICS II (ECO 2401S) University of Toronto. Department of Economics. Winter 2017 Instructor: Victor Aguirregabiria

ECONOMETRICS II (ECO 2401S) University of Toronto. Department of Economics. Winter 2017 Instructor: Victor Aguirregabiria ECOOMETRICS II ECO 40S Unversty of Toronto Department of Economcs Wnter 07 Instructor: Vctor Agurregabra SOLUTIO TO FIAL EXAM Tuesday, Aprl 8, 07 From :00pm-5:00pm 3 hours ISTRUCTIOS: - Ths s a closed-book

More information