Gaussian-log-Gaussian wavelet trees, frequentist and Bayesian inference, and statistical signal processing applications
|
|
- Berenice Banks
- 5 years ago
- Views:
Transcription
1 Aalborg Unverstet Gaussan-log-Gaussan wavelet trees, frequentst and Bayesan nference, and statstcal sgnal processng applcatons Møller, Jesper; Jacobsen, Robert Dahl Publcaton date: 014 Document Verson Early verson, also known as pre-prnt Lnk to publcaton from Aalborg Unversty Ctaton for publshed verson (APA): Møller, J., & Jacobsen, R. D. (014). Gaussan-log-Gaussan wavelet trees, frequentst and Bayesan nference, and statstcal sgnal processng applcatons. Department of Mathematcal Scences, Aalborg Unversty. Research Report Seres, No. R General rghts Copyrght and moral rghts for the publcatons made accessble n the publc portal are retaned by the authors and/or other copyrght owners and t s a condton of accessng publcatons that users recognse and abde by the legal requrements assocated wth these rghts.? Users may download and prnt one copy of any publcaton from the publc portal for the purpose of prvate study or research.? You may not further dstrbute the materal or use t for any proft-makng actvty or commercal gan? You may freely dstrbute the URL dentfyng the publcaton n the publc portal? Take down polcy If you beleve that ths document breaches copyrght please contact us at vbn@aub.aau.dk provdng detals, and we wll remove access to the work mmedately and nvestgate your clam.
2 AALBORG UNIVERSITY Gaussan-log-Gaussan wavelet trees, frequentst and Bayesan nference, and statstcal sgnal processng applcatons by Jesper Møller and Robert Dahl Jacobsen R Aprl 014 Department of Mathematcal Scences Aalborg Unversty Fredrk Bajers Vej 7 G DK - 90 Aalborg Øst Denmark Phone: Telefax: URL: e ISSN On-lne verson ISSN
3 Gaussan-log-Gaussan wavelet trees, frequentst and Bayesan nference, and statstcal sgnal processng applcatons Aprl 4, 014 Jesper Møller and Robert Dahl Jacobsen Department of Mathematcal Scences, Aalborg Unversty Abstract We ntroduce a promsng alternatve to the usual hdden Markov tree model for Gaussan wavelet coeffcents, where ther varances are specfed by the hdden states and take values n a fnte set. In our new model, the hdden states have a smlar dependence structure but they are jontly Gaussan, and the wavelet coeffcents have log-varances equal to the hdden states. We argue why ths provdes a flexble model where frequentst and Bayesan nference procedures become tractable for estmaton of parameters and hdden states. Our methodology s llustrated for denosng and edge detecton problems n two-dmensonal mages. Key words: condtonal auto-regresson; EM algorthm; hdden Markov tree; ntegrated nested Laplace approxmatons. 1 Introducton To model statstcal dependences and non-gaussanty of wavelet coeffcents n sgnal processng, Crouse, Nowak & Baranuk (1998) ntroduced a model where the wavelet coeffcents condtonal on a hdden Markov tree are ndependent Gaussan varables, wth the hdden states takng values n a fnte set (n applcatons, each hdden varable s often bnary) and used for determnng the varances of the wavelet coeffcent. We refer to ths as the Gaussan-fnte-mxture (GFM) wavelet tree model or just the GFM model. The GFM model and a clever mplementaton of the EM-algorthm have been wdely used n connecton to e.g. mage segmentaton, sgnal classfcaton, denosng, and mage document categorzaton, see e.g. Crouse et al. (1998), Po & Do (006), and Cho & Baranuk (001). Accordng to Crouse et al. (1998), the three standard problems (page 89) are tranng (.e. parameter estmaton), lkelhood determnaton 1
4 (.e. determnng the lkelhood gven an observed set of wavelet coeffcents), and state estmaton (.e. estmaton of the hdden states); they focus on the two frst problems, but menton that state estmaton s useful for problems such as segmentaton (page 893). In the present paper, we propose an alternatve model called the Gaussan-log- Gaussan (GLG) wavelet tree model or just the GLG model where the hdden states are jontly Gaussan and descrbed by a smlar dependence structure as n the GFM model, and where the wavelet coeffcents condtonal on the hdden states are stll ndependent Gaussan varables but the log-varance for each wavelet coeffcent s gven by the correspondng hdden state. In comparson wth the GFM model, n many cases the GLG model provdes a flexble model and a better ft for wavelet coeffcents, t s easy to handle for parameter estmaton n a frequetst settng as well as n a Bayesan settng, where state estmaton s also possble n the latter case, and t works well for denosng and edge detecton problems. The paper s organzed as follows. Secton provdes further detals of the GFM and GLG models. Secton 3 studes the moment structure of parametrc GLG models and explots the tractablty of the lower-dmensonal dstrbutons of the GLG model to develop composte lkelhoods so that the EM-algorthm becomes feasble for parameter estmaton. Secton 4 concerns fast Bayesan procedures for margnal posteror estmaton of parameters and hdden states n the GLG model, where we use ntegrated nested Laplace approxmatons (Rue, Martno & Chopn 009). Secton 5 demonstrates how our methods n Sectons 3 and 4 apply for denosng and edge detecton n two-dmensonal mages. Secton 6 contans concludng remarks. Techncal detals are deferred to Appendx A-D. Matlab and R (R Core Team 013) codes for our statstcal nference procedures are avalable at Wavelet tree models For both the GFM and the GLG model, we consder wavelet coeffcents w = (w 1,..., w n ), where the unts 1,..., n represent an abstract sngle ndex system. The unts are dentfed wth the nodes of a tree wth root 1 (the coarsest level of the wavelet transform) and edges correspondng to the parent-chld relatons of the wavelet coeffcents at the coarsest to the fnest level, see Fgure 1. Condtonal on hdden states s = (s 1,..., s n ), the wavelet coeffcents are ndependent Gaussan dstrbuted, where each w depends only on s (n Secton 5. we modfy the GFM and GLG models and consder wavelet coeffcents wth nose). For smplcty and snce t s frequently the case n applcatons, we assume that each condtonal mean E[w s ] = 0 s centered. However, for the two models, the condtonal varance Var[w s ] depends on and s n dfferent ways; the detals are gven n Sectons.1 and.. The condtonal ndependence structure for the hdden states s the same for the two models and gven by the tree structure,.e. s s vewed as a drected graphcal model (see e.g. Laurtzen (1996)): For = 1,..., n, denote c() {1,..., n} the chldren of, where each chld j c() s at one level lower than (see Fgure 1); f s at the fnest wavelet
5 1 1st level ρ(j) nd level j c() 3rd level Fgure 1: Illustraton of a bnary tree structure correspondng to a one-dmensonal sgnal wth l = 3 levels of wavelet coeffcents. Node j has one parent ρ(j) and node has two chldren c(). level, has no chldren (c() = ); else c(). Typcally n applcatons, f s not at the fnest wavelet level, has d chldren, where d s the dmenson of the sgnal/mage. Now, the jont densty for hdden states and wavelet coeffcents factorzes as p(s, w) = p 0 (s 1 ) n [ q (w s ) =1 j c() ] p (s j s ) where p 0 ( ), p ( ), and q ( ) are ether probablty mass functons or probablty densty functons, wth the true nature beng obvous from the context, and where we set j c() p (s j s ) = 1 f c() =. We refer to (1) as a wavelet tree model. We shall consder parametrc models, usng θ as generc notaton for the unknown parameters, and to stress the dependence of θ we wrte e.g. p(s, w θ) for the densty p(s, w). When we later dscuss parameter estmaton (Sectons 3 and 4), we consder k ndependent pars (s (1), w (1) ),..., (s (k), w (k) ) wth densty p(s, w θ), where we suppose only the wavelet coeffcents w (1),..., w (k) are observed..1 The GFM model For the GFM model, t s assumed n Crouse et al. (1998) that the state space of each s s a fnte set {1,..., m} (often m = ), (1) q ( s ) s a Gaussan densty where both the mean µ,s depend on the ndex and the argument s. and the varance σ,s Crouse et al. (1998) remark that nstead of a sngle Gaussan dstrbuton, the m-state Gaussan mxture dstrbuton for each wavelet coeffcent s needed because of the compressng property... resultng n a large number of small coeffcents and a small number of large coeffcents (page 887); and the condtonal dependence structure s used to characterze the key dependences between the wavelet coeffcents (page 887),.e. t matches both the clusterng and persstence propertes of the wavelet transform 3
6 (page 891) so that f one coeffcent s n a hgh-varance (low-varance) state, then ts neghbor s very lkely to also be n a a hgh-varance (low-varance) state (page 891). The parameters of the GFM model are the varance σ,s of q ( s ) N(0, σ,s ), s = 1,..., m, = 1,..., n, the ntal probabltes p 0 ( ) and the unknown transton probabltes p ( ) of the hdden state varables wth c() and = 0,..., n (settng c(0) = {1}). Usually the varances and transton probabltes are assumed only to depend on the level of the nodes. Then, denotng l the number of levels n the tree, the number of parameters s r GFM = ml + m 1 + m(m 1)(l 1). (). The GLG model In the GLG model, each wavelet coeffcent w condtonal on s s zero-mean Gaussan wth varance exp(s ),.e. q ( s ) = q( s ) does not depend on, and q(w s ) N(0, exp(s )); (3) the hdden states are jontly Gaussan,.e. p 0 (s 1 ) = p(s 1 µ 0, σ0 ) and p (s j s ) = p(s j s, α, β, κ ) for j c(), where p(s 1 µ 0, σ 0) N(µ 0, σ 0), (4) p(s j s, α, β, κ ) N(α + β s, κ ), (5) where µ 0, α, and β are real parameters and σ 0 and κ are postve parameters. The densty (3) s completely determned by the varance exp(s ), and t appears to be a more flexble model for wavelet coeffcents than the m-state Gaussan mxture model used n Crouse et al. (1998): In the GFM model, wavelet coeffcents from all trees and assocated to the same parent (or to the root) are sharng the same set of m possble varances, whle n the GLG model, each wavelet coeffcent w (t) for each tree t s havng ts own log-gaussan hdden state s (t). In Secton 3.1. and further on we assume as n the GFM model tyng wthn levels, that s the parameters on each level are equal (detaled later n (15)). Then the number of parameters n the GLG model for a tree wth l levels s r GLG = 3l 1. In comparson the GFM model wth m = s specfed by r GFM = 4l 1 parameters, whle the dfference wll be even larger as m grows, cf. (). 4
7 3 Parameter estmaton usng composte lkelhoods and the EM-algorthm Secton 3.1 descrbes the frst and hgher order moment structure of the hdden states and the wavelets coeffcents under the GLG model. In partcular we clarfy the meanng of tyng wthn levels, whch s assumed when we n Secton 3. dscuss parameter estmaton usng composte lkelhoods and the EM-algorthm. 3.1 Mean and varance-covarance structure Full parametrzaton Ths secton consders a full parametrzaton of the GLG model (4),.e. when µ 0 R, σ 0 > 0, (α, β, κ ) R R (0, ) (6) for 0 and c(). For each node j 1 n the tree structure, let ρ(j) denote the parent to j (see Fgure 1), and set ρ(1) = 0. By (4) and (5), each hdden state s j s Gaussan dstrbuted wth a mean and varance whch are determned by the means and the varances of ts ancestors: p j (s j ) = p(s j µ ρ(j), σ ρ(j) ) N(µ ρ(j), σ ρ(j) ) (7) for j = 1,..., n, where the mean and the varance are determned recursvely from the coarsest level to the second fnest level by µ = α + β µ ρ(), σ = κ + β σ ρ() (8) for 1 and c(). Conversely, the GLG model s parametrzed by (µ 0, σ 0 ) (, ) (0, ) and (µ, σ, β ) (, ) (0, ) (, ) for all 1 wth c(), snce α = µ β µ ρ() and κ = σ β σρ() (9) whenever 1 and c(). Set κ 0 = σ 0 and denote σ,j = Cov(s, s j ), the covarance of s and s j. Note that σ, = σ ρ() ; a general expresson for σ,j s gven by (34) n Appendx A. In partcular, σ h,j = κ ρ(h) β h f j c(h), σ,j = κ ρ(h) β h (10) f, j c(h) and j. [ ] Moments of the form E w awb j for a = 0, 1,... and b = 0, 1,... can be derved by condtonng on the hdden states and explotng well-known moment results for the log- Gaussan dstrbuton, see e.g. (30)-(3) n Appendx A. In partcular, lettng c(0) = {1}, 5
8 then for any h 0 and j c(h), η () h := E [ w j ] = exp ( µh + σ h /), (11) η (4) h := E [ wj 4 ] ( = 3 exp µh + σh), (1) := E [ w wj ] ( ) = exp µ h + κ ρ(h) β h + σ h f c(h) and j, (13) η (,) h ξ (,) h,j := E [ w j w h] = exp ( µh + µ ρ(h) + κ ρ(h) β h + σ h / + σ ρ(h) /). (14) 3.1. Tyng wthn levels For each node n the tree structure, denote l() the level of,.e. l() s the number of nodes n the path from the root to, and let l be the number of levels (see Fgure 1). For convenence, defne l(0) = 0. Henceforth we assume tyng wthn levels of the parameters n (4) and (5), that s α = α(l()), β = β(l()), κ = κ(l()), 1 l() < l. (15) Thus the unknown parameters are µ 0 R, σ 0 > 0, (α(1),..., α(l)) R l, (β(1),..., β(l)) R l, (κ(1),..., κ(l)) (0, ) l. Note that for 1 l() < l, by (8), (15), and nducton, (µ, σ ) depends on the node only through ts correspondng level l(),.e. µ = µ(l()), σ = σ (l()). (16) Furthermore, for 0 l(h) < l and j c(h), we obtan from (11)-(15) that (η () h, η(4) h, η (,) h, ξ (,) h,j ) depends on h only through l(h),.e. η () h = η () (l(h)), η (4) h = η (4) (l(h)), η (,) h = η (,) (l(h)), ξ (,) h,j = ξ (,) (l(h)). (17) 3. Parameter estmaton For parameter estmaton n the GFM model, Crouse et al. (1998) propose to use the EM-algorthm. Here the man dffculty s the calculaton of p (s, s j w) for j c(), the two-dmensonal margnal probabltes of any s and ts chld s j condtonal on the wavelet coeffcents, where the calculaton has to be done for each E-step of the EMalgorthm and each wavelet tree w = w (t), t = 1,..., k. Crouse et al. (1998) solve ths problem usng an upward-downward algorthm whch s equvalent to the forwardbackward algorthm for hdden Markov chans. Durand, Gonçalvès & Guédon (004) mprove on the numercal lmtatons on ths algorthm. Modfyng the upward-downward algorthm n Crouse et al. (1998) to the GLG model s not leadng to a computatonally feasble algorthm manly because, for each s, we have replaced ts fnte state space {1,..., m} under the GFM model by the real lne 6
9 under the GLG model, and numercal ntegraton would be repeatably needed at the varous (many) steps of the algorthm. As notced n Appendx C, the Gauss-Hermte quadrature rule provdes good approxmatons wth few quadrature nodes when consderng trees wth no more than two levels. However, snce the ntegrants nvolved n the transton between levels of the upward-downward algorthm are not suffcently smooth, we propose nstead an EM algorthm for estmatng θ based on composte lkelhoods for the jont dstrbuton of wavelets correspondng to each parent and ts chldren. These jont dstrbutons are relatvely easy to handle. Further detals are gven n the sequel Margnal lkelhoods When defnng composte lkelhoods n connecton to the EM-algorthm n Secton 3.., we use the followng margnal lkelhoods gven n terms of the full parametrzaton (4) and (5). Combnng (3) and (4), we obtan the densty of (s 1, w 1 ), exp p(s 1, w 1 µ 0, σ0) = ( 1 and hence the margnal densty of the root wavelet, q(w 1 µ 0, σ 0) = [ w 1 exp(s 1 ) + s 1 + (s 1 µ 0 ) σ 0 ]) πσ 0 (18) p(s 1, w 1 µ 0, σ 0) ds 1. (19) The margnal log-lkelhood based on the root wavelet vector w 1 = (w (1) 1,..., w(k) 1 ) for the k trees s gven by l 0 (µ 0, σ 0 w 1 ) = k t=1 log q(w (t) 1 µ 0, σ 0). (0) Consder any {1,..., n} wth c(). Denote w,c() the vector consstng of w and all w j wth j c(), and s,c() the vector consstng of s and all s j wth j c(). Usng (3)-(5) and (7), we obtan the densty of (s,c(), w,c() ), p(s,c(), w,c() µ ρ(), σρ(), α, β, κ ) = ( {[ ] exp 1 w exp(s ) + s + (s µ ρ() ) + σρ() j c() [ (π) 1+ c() σ ρ() κ c() ]}) wj exp(s j ) + s j + (s j α β s ) κ where c() denotes the number of chldren to. Hence the densty of w,c() s gven by the ntegral q(w,c() µ ρ(), σρ(), α, β, κ ) = j c() (1) p(s,c(), w,c() µ ρ(), σ ρ(), α, β, κ ) ds j ds. () 7
10 Fnally, denotng w,c() the vector of the th wavelets w (1),..., w (k) w (1) j,..., w (k) j, j c(), the log-lkelhood based on w,c() s l (µ ρ(), σ ρ(), α, β, κ w,c() ) = 3.. EM-algorthm k t=1 j c() and ther chldren log q(w (t), w (t) j µ ρ(), σρ(), α, β, κ ). (3) Ths secton shows how the EM-algorthm apples on composte lkelhoods (Gao & Song 011) defned from the margnal lkelhoods n Secton 3..1 under the assumpton of tyng wthn levels, cf. (15). We proceed from the coarsest to the fnest level, where parameter estmates are calculated by the EM-algorthm as detaled n Appendx C 1. Apply the EM-algorthm for the (margnal) log-lkelhood (0) to obtan an estmate ( µ 0, σ 0 ).. For r = 1,..., l 1, denotng w (r) the vector of all w,c() wth l() = r, the log-composte lkelhood gven by the sum of the log-lkelhoods (3) based on all w,c() wth l() = r s l (r) (µ(r 1), σ (r 1), α(r), β(r), κ(r) w (r) ) = l (µ(r 1), σ (r 1), α(r), β(r), κ (r) w,c() ). :l()=r Now, suppose we have obtaned an estmate ( µ(r 1), σ (r 1)). Then we apply the EM-algorthm on l (r) ( µ(r 1), σ (r 1), α(r), β(r), κ(r) w (r) ) to obtan an estmate ( α(r), β(r), κ (r)). Thereby, usng (8) and (15), an estmate ( µ(r), σ (r)) s also obtaned. These composte lkelhoods for our GLG model can be handled manly because of the condtonal ndependence structure and snce the margnal dstrbuton of s s Gaussan. In contrast, for the GFM model, unless n s small or all except a few nodes have at most one chld, t s not feasble to handle margnal dstrbutons and correspondng composte lkelhoods. For the ntal values used n steps 1 and, moment-based estmates obtaned as descrbed n Appendx B are used. If such an estmate s not meanngful (see Remark 1 n Appendx B), we replace the parameter estmate by a fxed value whch makes better sense. Each teraton of step 1 leads to an ncrease of the margnal log-lkelhood (0), so the value returned by the EM algorthm s a local maxmum; and each teraton of step leads to an ncrease of the log-composte lkelhood, so the value returned by the EM algorthm s a local maxmum when (µ(r 1), σ (r 1)) = ( µ(r 1), σ (r 1)) s fxed. In each step, as usual when applyng the EM-algorthm, there s no guarantee that the global maxmum wll be found. 8
11 4 Bayesan nference For the GFM model, Bayesan methods are not feasble: Indeed Crouse et al. (1998) derve recursons for calculatng the condtonal denstes p(s (t) w (t), θ) and p(s (t) j, s(t) w (t), θ), j c(), but t s not possble to calculate or satsfactory approxmate the margnal posteror denstes for (any subparameter of) θ or (any subvector) of s (t). For nstance, f w = (w (1),..., w (k) ) s the vector of wavelets from all the trees, p(s (t) w) = (t) p(s w (t), θ)p(θ w) dθ where under the GFM model we do not know what p(θ w) s and t seems hopeless to evaluate ths hgh dmensonal ntegral. Usng a Bayesan approach for the GLG model, wth a pror mposed on all the r GLG unknown parameters, also leads to a complcated posteror dstrbuton. In prncple t could be handled by Markov chan Monte Carlo (MCMC) methods, but MCMC samplng remans panfully slow from the end user s pont of vew (page 3 n Rue et al. (009)). However, approxmate Bayesan methods based on Laplace approxmatons (Terney & Kadane 1986, Rue & Martno 007, Rue et al. 009) are feasble for GLG submodels when the number of unknown parameters s not hgh, as n our GLG submodel ntroduced n Secton 4.1. Furthermore, Secton 4. consders ntegrated nested Laplace approxmatons (INLA) to obtan margnal posteror dstrbutons for θ and the hdden states (Rue et al. 009). 4.1 Condtonal auto-regressons Romberg, Cho & Baranuk (001) consder GFM submodels where θ s of dmenson nne, and they demonstrate that the submodels are acceptable for denosng mages wth a hgh degree of self-smlarty, e.g. as found n mages of natural scenes. Encouraged by these results and because of the larger flexblty n modellng the varances of sngle wavelet coeffcents n the GLG model, we consder the followng GLG submodel. Frst, notce that by (4), s s a Gaussan Markov random feld or n fact a condtonal auto-regresson (CAR; Besag (1974, 1975); Rue & Held (005, Chapter 1)). The Gaussan dstrbuton of s s specfed by the mean µ ρ() of each s and the precson matrx (the nverse of the varance-covarance matrx of s) whch has (, j)th entry 1 + c() β κ f = j, c(), cf. Appendx A. κ ρ() 1 κ,j = β ρ() κ ρ(j) β ρ(j) κ ρ() f = j, c() =, f = ρ(j), f j = ρ(), 0 otherwse, (4) 9
12 Second, consder the homogeneous GLG model specfed by that α = α, β = β, κ = κ, whenever l() < l. Then the free parameters are θ = (µ 0, σ0, α, β, κ ) (, ) (0, ) (, ) (, ) (0, ). By (8) and (16), we obtan a specal mean and varance structure for the hdden states: For level r = 1,..., l, α βr 1 µ(r) = β 1 + βr µ 0 f β 1, rα + µ 0 f β = 1, and σ κ βr 1 (r) = β 1 + βr σ0 f β 1, rκ + σ0 f β = INLA Integrated nested Laplace approxmatons (INLA) s a general framework for performng approxmate Bayesan nference n latent Gaussan models where the number of parameters s small (see Rue et al. (009) and Martns, Smpson, Lndgren & Rue (013)). Rue et al. (009) notce that The man beneft of INLA s computatonal: where Markov chan Monte Carlo algorthms need hours or days to run, INLA provdes more precse estmates n seconds or mnutes. Ths ncludes estmates of the posteror margnals for θ and for the hdden states. Parsmonous GLG submodels ft the INLA assumptons. We have mplemented the homogeneous GLG model n INLA, where pror specfcaton s largely handled automatcally n INLA. Specfc calls used n the experments reported n the sequel can be seen n our released code. 5 Examples of applcatons Ths secton compares results usng the GLG and GFM models for wavelet coeffcents n real mages. The GFM model has proven to be useful for modellng dfferent knds of multscale transforms (Crouse et al. 1998, Romberg et al. 001, Po & Do 006), but our results are only for the standard wavelet transform, where n both the GFM and the GLG model the drectons of the wavelet transform are modelled ndependently. Secton 5.1 dscusses how well GLG and GFM models descrbe standard wavelet coeffcents, Secton 5. consders denosng of mages, and Secton 5.3 concerns edge detecton. 5.1 Modellng standard wavelet coeffcents n mages For llustratve purposes, n ths and the followng sectons, we use three test mages from the USC-SIPI mage database avalable at Lena, 10
13 mandrll, and peppers, see Fgure. These mages are 51-by-51 pxels represented as 8 bt grayscale wth pxel values n the unt nterval, and we have ftted the GFM and GLG models to wavelet transforms usng the correspondng EM algorthms. Fgure 3 shows four hstograms of the wavelet coeffcent from a sngle subband along wth the ftted margnal dstrbutons. The fgure llustates that no model s fttng better than the other n all cases: For level 1 of the vertcal subband of Lena (upper left panel) and for level of the vertcal subband of mandrll (upper rght panel), the GLG model provdes the best ft; for level 3 of the vertcal subband of mandrll (lower left panel), the GLG model s too hghly peaked at zero and the GFM model provdes a better ft; and for level 3 of the dagonal subband of mandrll (lower rght panel), the two models ft equally well. 5. Denosng Consder an mage corrupted wth addtve whte nose,.e. we add an ndependent term to each pxel value from the same zero-mean normal dstrbuton. Recall that when workng wth orthonormal wavelets, the dstrbuton and the ndependence propertes of the nose are preserved by the wavelet transform, and the procedure for denosng wth wavelets works as follows: nosy data nosy wavelets nose-free wavelets nose-free data. Thus, a wavelet tree w = (w 1,..., w n ) s also observed wth addtve whte nose: v = w + ε, = 1,..., n, (5) where ε N(0, σε), the ε are mutually ndependent and ndependent of (s, w), and we assume that the nose varance σɛ s known. The dependence structure n the tree wth nosy observatons s llustrated n Fgure 4. From ths and (5) we obtan n p(w v, s, θ) = p(w v, s, θ). =1 Below we dscuss estmaton of w. In the frequentst setup, we estmate w by E[w v, θ], wth θ replaced by ts estmate obtaned by the approprate EM-algorthm (see Secton 3.. and Crouse et al. (1998)). For an m-state GFM model, E[w v, θ] = v m j=1 σ,j p(s = j v ) σ,j + σ ε (see Crouse et al. (1998)). Under the GLG model, we have E[w v, θ] = v c(v µ ρ(), σρ() ) ( [ exp(s ) (exp(s ) + σε) exp 1 v 3/ exp(s ) + σε + (s ]) µ ρ() ) σρ() ds (6) 11
14 Fgure : The three test mages: Lena, mandrll, and peppers. where we use the Gauss-Hermte quadrature rule for approxmatng the ntegral. Equaton (6) s derved n Appendx D. In the Bayesan setup for the homogeneous GLG model, we work wth the posteror dstrbuton p(w v ) from whch we can calculate varous pont estmates. We have p(w v ) = p(w v, s )p(s v )ds, (7) E(w v ) = E(w v, s )p(s v )ds, where p(s v ) s calculated n INLA. Snce p(w s ) N(0, exp(s )) and p(v w ) 1
15 Fgure 3: Hstograms of wavelet coeffcents from one scale of the 3 level wavelet transform wth a Daubeches 4 wavelet. The probablty densty functons of the ftted GLG model (sold lne) and the ftted GFM model (gray lne) are shown. Upper left panel: Level 1 of the vertcal subband of Lena. Upper rght panel: Level of the vertcal subband of mandrll. Lower left panel: Level 3 of the vertcal subband of mandrll. Lower rght panel: Level 3 of the dagonal subband of mandrll. N(w, σ ɛ ), we obtan and ( v exp(s ) p(w v, s ) p(w s )p(v w ) N σɛ + exp(s ), σɛ ) exp(s ) σɛ + exp(s ) E(w v ) = v exp(s ) σ ɛ + exp(s ) p(s v )ds. We apply the two denosng schemes wth a three level wavelet transform usng the Daubeches 4 flter to nosy versons of the three test mages n Fgure. To estmate the performance of a denosng scheme, we calculate the peak sgnal-to-nose rato (PSNR) 13
16 s 1 w 1 s s 3 ε 1 w v 1 ε w 3 ε 3 v v 3 Fgure 4: Graphcal model of a bnary tree wth two levels and nosy observatons. The rectangular nodes are observed varables and the round nodes are unobserved varables. n decbels between a test mage I and a nosy or cleaned mage J. For mages of sze N N, the PSNR n decbels s defned as PSNR = 0 log 10 N(max{I(x)} mn{i(x)}) I J where the maxmum and the mnmum are over all pxels x and s the Frobenus norm. Table 1 shows for the test mages and dfferent nose levels σ ε, the PSNR between each test mage and ts nosy or denosed verson: For the frequentst results, the mages denosed usng the GLG model have PSNRs that are consstently hgher than those denosed usng the GFM model. The Bayesan results yelds the lowest PSNR values, but they are also based on a more parsmonous model. An example of the vsual appearance of denosng usng frequentst means s seen n Fgure 5; agan the GLG model performs best, where detals around e.g. the stem of the center pepper are more crsp. The medan (the 50% quantle) of the posteror dstrbuton s only one possble pont estmate of the posteror dstrbuton. However, usng other quantles or the posteror mean are not provdng better results, see Fgure Edge detecton Edge detecton n an mage s performed by labellng each pxel as beng ether an edge or a non-edge. Turnng to the wavelet transform for ths task has the advantage that wavelet coeffcents are large near edges and small n the homogeneous parts of an mage; the dffculty les n quantfyng large and small. Another advantage s that a multresoluton analyss allows us to search for edges that are present at only selected scales of the mage, thereby gnorng edges that are ether too coarse or too fne. In ths secton, for each tree t = 1,..., k, we focus on how to label the wavelet coeffcent w (t) by an ndcator varable f (t), where f (t) = 1 means w (t) s large, and f (t) = 0 means w (t) s small. Labellng of wavelet coeffcents usng the GFM model s ntroduced n 14
17 Table 1: For the three test mages and three nose levels, peak sgnal-to-nose ratos n db between the mage and ts nosy verson ot ts denosed verson obtaned usng ether the GFM model and the EM-algorthm, the GLG model and the EM-algorthm, or the homogeneous GLG model and INLA. In the latter case, the PSNR s calculated usng the medan of the posteror mage. For each mage, a three level Daubeches 4 wavelet transform s used. test mage PSNR nose level σ ε nosy GFM GLG hom. GLG Lena Mandrll Peppers Sun, Gu, Chen & Zhang (004); we recap ths labellng algorthm and afterwards modfy t to work wth the GLG model. Fnally, we dscuss how to transfer these labels to the pxels and show examples. The labellng n Sun et al. (004) conssts of three steps. Frst, usng the EM algorthm of Crouse et al. (1998), an estmate θ of the parameter vector θ of a -state GFM model s obtaned from the data {w (t) } k t=1. Second, usng an emprcal Bayesan approach, the maxmum a posteror (MAP) estmate of the hdden states s (t) = argmax p(s w (t), θ) = argmax p(s, w (t) θ), (8) s s t = 1,..., k, s computed usng the Vterb algorthm (Durand et al. 004). Thrd, the MAP estmate s used to defne f (t) = (ŝ(t) ). The dea of labellng wavelet coeffcents wth the GLG model s overall the same as presented above for the GFM model, wth the dfferences arsng from the contnuous nature of the hdden states and dfferent algorthms beng appled for parameter estmaton and state estmaton. Frst, the EM algorthm n Secton 3.. s used to provde an estmate θ of the parameter vector of the GLG model. Second, n analogy wth (8) we compute the MAP estmate ŝ(t). However, the Vterb algorthm cannot be used here: The Vterb algorthm computes the MAP estmate by successvely maxmzng the terms n (1) assocated to each level of the wavelet tree. For the GFM model, t s easy to perform these maxmzaton steps due to the fact that the hdden state space s fnte. For the GLG model, the MAP estmate can be computed at the fnest level, 15
18 Fgure 5: Denosng results for the peppers mage from Table 1 when the standard devaton of the nose s 0.0. Top left panel: The orgnal mage. Top rght panel: The nosy mage (PSNR s 13.57). Bottom left panel: The nosy mage cleaned usng the GFM model and the EM-algorthm (PSNR s 3.70). Bottom rght mage: The nosy mage cleaned usng the GLG model and the EM-algorthm (PSNR s 4.41). but ths estmate s a complcated functon that cannot easly be used n the remanng 16
19 Fgure 6: Denosng the peppers mage usng the posteror dstrbuton (7) and INLA. The orgnal and nosy mages are seen n Fgure 5. The top left, top rght, and bottom left mages are based on the 5%, 75%, and 50% quantles of the posteror dstrbuton, respectvely (the PSNRs are 16.38, 16.41, and 19.18, respectvely). The bottom rght mage s based on the mean of the posteror dstrbuton (PSNR s 19.15). The posteror mean and medan are almost dentcal. maxmzaton steps. Instead, we note that n p(s, w θ) = p(s θ) p(w s ) (9) =1 17
20 where p(s θ) s a multdmensonal Gaussan densty functon wth mean vector µ and precson matrx gven by (4) wth θ = θ. The log of (9) and ts gradent vector and Hessan matrx wth respect to s are log p(s, w θ) 1 n {(s µ) ( ) (s } µ) + w exp( s ) + s, =1 log p(s, w θ) = (s µ) + 1 [ w exp( s ) 1 ] 1 n, H ( log p(s, w) θ) = 1 dag( w exp( s ), 1 n ), where means that an addtve term whch s not dependng on s has been omtted n the rght hand sde expresson. The Hessan matrx s strctly negatve defnte for all (s, w) wth w 0 and hence ŝ(t) can be found by solvng log p(s, w (t) θ) = 0 usng standard numercal tools. Thrd, observe that f the estmate (ŝ(t) ) s large n the estmated dstrbuton N( µ ρ(), σ ρ()) for s, then we expect w (t) to be large. Therefore, denotng z p the p-fractle n N( µ ρ(), σ ρ()) (wth e.g. p = 0.9), we defne = 1 f (ŝ(t) ) z p and zero otherwse. It remans to specfy the transfer of f (t) (defned by one of the two methods above) to the pxel doman (ths ssue s not dscussed n Sun et al. (004)). For specfcty, consder a gray scale mage I = {p j } kn j=1 and {w(t) } k t=1 = W {p j} kn j=1, where W s the used wavelet transform operator. To each pxel j we assocate a bnary varable e j ndcatng f j s part of an edge or not: Snce the wavelet transform does not necessarly map bnary values to bnary values, we defne {ẽ j } kn j=1 = W 1 {f (t) } k t=1 and set { 1 f ẽj 0, e j = 0 otherwse. f (t) The e j s are senstve to the choce of W, and usng the Haar wavelet results n thn edges. As mentoned, the multresoluton analyss of the wavelet transform allows us to consder edges that are present at only specfc scales. To exclude edges at a level l n the wavelet transform, we smply modfy {f (t) } k (t) t=1 by settng f = 0 f l() = l. Fgure 7 compares the results of the two edge detecton algorthms, where we only use the fnest scale n the wavelet transform. The method based on the GLG model classfes fewer pxels as edges; n partcular the GFM model classfcatons nclude many false postves. Whle the mages wthn Fgure 7 are comparable, we notce they are not drectly comparable to the mages presented n Sun et al. (004) who use a non-decmated wavelet transform and an extenson of the GFM model where the dfferent drectons are not modelled ndependently. 18
21 Fgure 7: Examples of edge detecton of the Lena and peppers mages usng the method from Sun et al. (004) (left column) and our varant that uses the GLG model (rght column). A three level Haar wavelet transform s used and only the fnest level of the wavelet transform s consdered. The 90% fractle s used for thresholdng wth the GLG model. 6 Concludng remarks We have ntroduced the GLG model for wavelet trees, developed methods for performng nference, and demonstrated possble applcatons n sgnal and mage processng, where the GLG model outperforms the GFM model of Crouse et al. (1998). However, there 19
22 s stll work to be done. We do not have a procedure for lkelhood determnaton of a full wavelet tree gven the model parameters n the general GLG model (t s possble to compute the lkelhood n INLA, but ths s only for submodels). In the GFM model ths lkelhood s calculated as a by-product of the EM algorthm n Crouse et al. (1998), but as noted we cannot easly modfy ths EM algorthm to the GLG model. As an alternatve method for nference we have consdered a varatonal EM algorthm (see e.g. Khan (01)). The parameter estmates obtaned wth ths varatonal method may be more consstent across the levels of the wavelet transform. We have omtted a further dscusson of ths varatonal method, snce t cannot be used for makng nference wth nosy observatons. Acknowledgment Supported by the Dansh Councl for Independent Research Natural Scences, grant , Mathematcal and Statstcal Analyss of Spatal Data, and by the Centre for Stochastc Geometry and Advanced Bomagng, funded by a grant from the Vllum Foundaton. We are grateful to Håvard Rue for help wth INLA. We thank Peter Cragmle, Morten Nelsen, and Mohammad Emtyaz Khan for helpful dscussons. Appendx A: Moments Usng (1) and (3) and by condtonng on s and explotng the condtonal ndependence structure, we obtan E [ w ] ) = exp (µ ρ() + σρ() /, (30) E [ w 4 ] ( ) 3 ( E [ ]) w = exp σρ(), (31) [ ] E w w j E [ ] [ ] = exp(σ,j ) f j. (3) w E wj For = 1,..., n, let v = s β ρ() s ρ() where β 0 = 0. Then s = j P 1, v j h P j,ρ() β h (33) where P 1, s the path of nodes from 1 to (n the tree, and ncludng 1 and ), P j,ρ() s the path of nodes from j to ρ() f j P 1, \ {}, and we set h P j,ρ() β h = 1 f j =. Note that v 1,..., v n are ndependent Gaussan dstrbuted and v N(α ρ(), κ ρ() ) where κ 0 = σ 0. Hence we mmedately obtan from (33) that [ ][ σ,j = β h1 β h ]. (34) h 0 P 1, P 1,j κ ρ(h 0 ) h 1 P h0,ρ() h P h0,ρ(j) 0
23 Fnally, because of the smple one-to-one lnear relatonshp between (v 1,..., v n ) and (s 1,..., s n ), (4) s straghtforwardly derved. Appendx B: Estmatng equatons based on moment relatons Assume c() 1, = 1,..., n; ths condton s n general satsfed n wavelet applcatons. Usng mean value relatons for the full parametrzaton (4) we descrbe a smple and fast procedure whch provdes consstent estmates for the parameters under (15) as the number of wavelet trees tends to nfnty. Let n r denote the number of nodes on level r {1,..., l}. Frst, by (11), (1) and (16), for each level r = 0,..., l 1, there s a one-to-one correspondence between (µ(r), σ (r)) and (η () (r), η (4) (r)), where ( ) µ(r) = log σ (r) = log η () (r) σ (r)/, ) log ( η (4) (r)/3 ( η () (r) Combnng these relatons wth unbased estmates gven by η (a) (r) = 1 kn r k t=1 :l()=r j c() ). ( (t)) a, w a =, 4, r < l, we obtan consstent estmates ( ) µ(r) = log η () (r) σ (r)/, (35) ( ) ( ) σ (r) = log η (4) (r)/3 log η () (r), r < l, (36) Second, by (11)-(14), for each node h 1 wth c(h), ( ) ( ) log η (,) h log η () h β h = ( ) ( ) log log log ξ (,) h,j j η () h ( ) η () ρ(h) whenever j c(h). Ths combned wth (15) and (17), the unbased estmates gven above, and the consstent estmates ξ (,) (r) = 1 kn r k t=1 :l()=r j c() ( (t)) ( (t)) w w j and η (,) (r) = 1 kn r k t=1 :l()=r c() ( c() 1) j 1,j c() j 1 <j ( (t)) ( (t)) w j 1 w j 1
24 provde consstent estmates log [ η β(r) (,) (r) ] log [ η () (r) ] = log [ ξ(,) (r) ] log [ η () (r) ] log [ η () (r 1) ] (37) for r = 0,..., l 1. Fnally, usng (9) and (35)-(37), we obtan consstent estmates ( α h, κ h ) = ( α(r), κ (r) ) for 0 r = l(h) < l. Remark 1 The estmatng equaton (35) does not guarantee that σ (r) > 0; n fact, for small wavelet datasets, we have observed that σ (r) may be negatve. For σ (r) to be postve s equvalent to requre that η (4) (r) > 3 ( η () (r) ). (38) As η (4) s the fourth moment and η () the second moment of the same random varable, (38) s a much stronger condton than the usual condton for varance estmaton, namely wth 3 replaced by 1. Remark The estmaton procedure s mmedately modfed to GLG submodels. In case of the homogeneous GLG model, defne η () = exp ( µ 0 + σ 0), η (4) = 3 exp ( µ 0 + σ 0), and n accordance wth (11)-(14) correspondng unbased estmates Thereby η (a) = ( µ 0 = log η ()) σ /, h 1: c(h) η(a) h, a =, 4, c ( ) ( σ = log η (4) /3 log η ()), provde consstent estmates. Appendx C: EM-algorthm for the margnal lkelhoods The EM-algorthm (Dempster, Lard & Rubn 1977, Gao & Song 011) s an teratve estmaton procedure whch apples for steps 1 n Secton 3.. as descrbed below. We start by notcng that the condtonal densty of s 1 gven w 1 s p(s 1 w 1, µ 0, σ 0 ) = p(s 1, w 1 µ 0, σ 0 ) q(w 1 µ 0, σ 0 ) exp ( 1 [ w1 exp(s 1 ) + s 1 + (s 1 µ 0 ) ]) σ0 (39)
25 where n the expresson on the rght hand sde we have omtted a factor whch does not depend on the argument s 1 of the condtonal densty. Note also that for l() = r < l, the condtonal densty of s,c() gven w,c() s p(s,c() w,c(), µ(r 1), σ (r 1), α(r), β(r), κ (r)) t=1 = p(s,c(), w,c() µ(r 1), σ (r 1), α(r), β(r), κ (r)) q(w,c() µ(r 1), σ (r 1), α(r), β(r), κ (r)) ( exp 1 {[ w exp(s ) + s + (s µ(r 1)) ] σ + (r 1) [ wj exp(s j ) + s j + (s j α(r) β(r)s ) ]}) κ. (40) (r) j c() In step 1, suppose ( µ 0, σ 0 ) s the current estmate. We consder the condtonal expectaton wth respect to (39) when (µ 0, σ0 ) s replaced by ( µ 0, σ 0 ). Then the next estmate for (µ 0, σ0 ) s the maxmum pont for the condtonal expectaton of the log-lkelhood whch s based on both w 1 and s 1 ; ths log-lkelhood s gven by [ ] k log p(s (t) 1, w(t) 1 µ 0, σ0) 1 k log(σ 0) + (s(t) 1 µ 0) σ0 where means that an addtve term whch s not dependng on (µ 0, σ0 ) has been omtted n the rght hand sde expresson, cf. (18). It follows mmedately that ths maxmum pont s gven by σ 0 = µ 0 = 1 k [ 1 k k E t=1 k t=1 t=1 [ ] E s (t) 1 w(t) 1, µ 0, σ 0, [ ( s (t) 1 ) w (t) 1, µ 0, σ 0 ] ] µ 0, where the condtonal expectaton s calculated usng (39). We do not have a closed expresson for the margnal densty nor ts moments. Snce the jont densty s the product of a Gaussan densty and a smooth functon, the Gauss-Hermte quadrature rule (see e.g. Press, Teukolsky, Vetterlng & Flannery (00)) s well-suted for approxmatng the ntegrals usng few quadrature nodes. The teraton s repeated wth ( µ 0, σ 0 ) = ( µ 0, σ 0 ) untl convergence s effectvely obtaned, whereby a fnal estmate ( µ 0, σ 0 ) s returned. In step, suppose ( α(r), κ (r)) s the current estmate, whch we use together wth the estmate ( µ(r 1), σ (r 1)) to obtan the next estmate for (α(r), κ(r)): Replacng (µ(r 1), σ (r 1), α(r), β(r), κ(r)) by ( µ(r 1), σ (r 1), α(r), β(r), κ(r)), ths estmate s the maxmum pont for the condtonal expectaton wth respect to (40) of each term 3
26 n the followng sum: k t=1 :l()=r log p(s (t),c(), w(t),c() µ(r 1), σ (r 1), α(r), β(r), κ (r)) 1 k t=1 :l()=r j c() [log(κ (r)) + (s j α(r) β(r)s ) ] κ (r) where addtve terms whch do not depend on (α(r), κ(r)) have been omtted, cf. (1). Now, calculate s(r) defned as the average of the followng condtonal means: s(r) = 1 kn r 1 k t=1 :l()=r It s easly seen that the maxmum pont s gven by β(r) = k t=1 :l()=r j c() k t=1 :l()=r α(r) = s(r) β s(r), [ κ 1 k (r) = E [ s (t) w (t),c(), µ(r 1), σ (r 1), α(r), β(r), κ (r) ]. E [ s (t) j (s(t) s(r)) w (t),c(), µ(r 1), σ (r 1), α(r), β(r), κ (r) ] c() E [ (s (t) kn r 1 t=1 :l()=r [ (s (t) E j 1 c() s(r)) w (t),c(), µ(r 1), σ (r 1), α(r), β(r), κ (r) ] j c() (t)) w (t) β(r)s,c(), µ(r 1), σ (r 1), α(r), β(r), κ (r)] ] α(r). The teraton s repeated wth ( α ( r), κ (r)) = ( α(r), κ (r)) untl convergence s effectvely obtaned, whereby a fnal estmate ( α(r), κ (r)) s returned. Appendx D: Condtonal expectaton of nosy observatons under the GLG model Let the stuaton be as n Secton 5. and consder the GLG model. The jont densty of (s, v ) s found just as n the nose-free case n Secton 3..1, ( [ ]) exp 1 v p(s, v µ ρ(), σρ() ) = p(v s )p(s µ ρ(), σρ() ) = exp(s + (s µ ρ() ) )+σε σρ() πσ ρ() exp(s ) + σε and the margnal densty of the wavelet wth nose s q(v µ ρ(), σρ() ) = p(s, v µ ρ(), σρ() ) ds., 4
27 We do not have a closed form expresson for ths ntegral, but due to the form of the ntegrant we approxmate the ntegral wth the Gauss-Hermte quadrature rule, see e.g. Press et al. (00). The condtonal densty of s gven v s ( [ p(s v, µ ρ(), σρ() ) = p(s, v µ ρ(), σρ() ) exp 1 q(v µ ρ(), σρ() ) = v exp(s )+σ ε ]) + (s µ ρ() ) σρ() c(v µ ρ(), σ ρ() ) exp(s ) + σ ε where c(v µ ρ(), σρ() ) = πσ ρ()q(v µ ρ(), σρ() ). Furthermore, from well-known results about the bvarate normal dstrbuton we obtan Hence E[w s, v, θ] = Corr[w, v s ] whereby we obtan (6). References Var[w s ] Var[v s ] v = Var[w s ] Var[v s ] v = exp(s ) exp(s ) + σε v. E[w v, θ] = E [ E[w s, v, θ] v, θ ] [ exp(s ) = v E exp(s ) + σε ] v, θ Besag, J. (1974). Spatal nteracton and the statstcal analyss of lattce systems (wth dscusson), Journal of the Royal Statstcal Socety: Seres B 36(): Besag, J. (1975). Statstcal analyss of non-lattce data, Statstcan 4(3): Cho, H. & Baranuk, R. (001). Multscale mage segmentaton usng wavelet-doman hdden Markov models, IEEE Transactons on Image Processng 10(9): Crouse, M. S., Nowak, R. D. & Baranuk, R. G. (1998). Wavelet-based statstcal sgnal processng usng hdden Markov models, IEEE Transactons on Sgnal Processng 46(4): Dempster, A. P., Lard, N. M. & Rubn, D. B. (1977). Maxmum lkelhood from ncomplete data va the EM algorthm, Journal of the Royal Statstcal Socety: Seres B 39(1): Durand, J.-B., Gonçalvès, P. & Guédon, Y. (004). Computatonal methods for hdden Markov tree models an applcaton to wavelet trees, IEEE Transactons on Sgnal Processng 5(9): Gao, X. & Song, P. X.-K. (011). Composte lkelhood EM algorthm wth applcatons to multvarate hdden Markov model, Statstca Snca 1(1): Khan, M. E. (01). Varatonal Learnng for Latent Gaussan Models of Dscrete Data, PhD thess, The Unversty of Brtsh Columba. 5
28 Laurtzen, S. L. (1996). Graphcal Models, Clarendon Press, Oxford. Martns, T. G., Smpson, D., Lndgren, F. & Rue, H. (013). Bayesan computng wth INLA: new features, Computatonal Statstcs and Data Analyss 67: Po, D. D.-Y. & Do, M. N. (006). Drectonal multscale modelng of mages usng the contourlet transform, IEEE Transactons on Image Processng 15(6): Press, W. H., Teukolsky, S. A., Vetterlng, W. T. & Flannery, B. P. (00). Numercal Recpes n C++, edn, Cambrdge Unversty Press. R Core Team (013). R: A Language and Envronment for Statstcal Computng, R Foundaton for Statstcal Computng, Venna, Austra. ISBN URL: Romberg, J. K., Cho, H. & Baranuk, R. G. (001). Bayesan tree-structured mage modelng usng wavelet-doman hdden Markov models, IEEE Transactons on Image Processng 10(7): Rue, H. & Held, L. (005). Gaussan Markov Random Felds: Theory and Applcatons, Chapman and Hall, London. Monographs on Statstcs and Appled Probablty, vol Rue, H. & Martno, S. (007). Approxmate Bayesan nference for herarchcal Gaussan Markov random feld models, Journal of Statstcal Plannng and Inference 137(11): Rue, H., Martno, S. & Chopn, N. (009). Approxmate Bayesan nference for latent Gaussan models by usng ntegrated nested Laplace approxmatons, Journal of the Royal Statstcal Socety: Seres B 71(): Sun, J., Gu, D., Chen, Y. & Zhang, S. (004). A multscale edge detecton algorthm based on wavelet doman vector hdden Markov tree model, Pattern Recognton 37(7): Terney, L. & Kadane, J. B. (1986). Accurate approxmatons for posteror moments and margnal denstes, Journal of the Amercan Statstcal Assocaton 81(393):
Random Variables. b 2.
Random Varables Generally the object of an nvestgators nterest s not necessarly the acton n the sample space but rather some functon of t. Techncally a real valued functon or mappng whose doman s the sample
More informationIntroduction to PGMs: Discrete Variables. Sargur Srihari
Introducton to : Dscrete Varables Sargur srhar@cedar.buffalo.edu Topcs. What are graphcal models (or ) 2. Use of Engneerng and AI 3. Drectonalty n graphs 4. Bayesan Networks 5. Generatve Models and Samplng
More informationMgtOp 215 Chapter 13 Dr. Ahn
MgtOp 5 Chapter 3 Dr Ahn Consder two random varables X and Y wth,,, In order to study the relatonshp between the two random varables, we need a numercal measure that descrbes the relatonshp The covarance
More information/ Computational Genomics. Normalization
0-80 /02-70 Computatonal Genomcs Normalzaton Gene Expresson Analyss Model Computatonal nformaton fuson Bologcal regulatory networks Pattern Recognton Data Analyss clusterng, classfcaton normalzaton, mss.
More information3: Central Limit Theorem, Systematic Errors
3: Central Lmt Theorem, Systematc Errors 1 Errors 1.1 Central Lmt Theorem Ths theorem s of prme mportance when measurng physcal quanttes because usually the mperfectons n the measurements are due to several
More informationTests for Two Correlations
PASS Sample Sze Software Chapter 805 Tests for Two Correlatons Introducton The correlaton coeffcent (or correlaton), ρ, s a popular parameter for descrbng the strength of the assocaton between two varables.
More information3/3/2014. CDS M Phil Econometrics. Vijayamohanan Pillai N. Truncated standard normal distribution for a = 0.5, 0, and 0.5. CDS Mphil Econometrics
Lmted Dependent Varable Models: Tobt an Plla N 1 CDS Mphl Econometrcs Introducton Lmted Dependent Varable Models: Truncaton and Censorng Maddala, G. 1983. Lmted Dependent and Qualtatve Varables n Econometrcs.
More informationMeasures of Spread IQR and Deviation. For exam X, calculate the mean, median and mode. For exam Y, calculate the mean, median and mode.
Part 4 Measures of Spread IQR and Devaton In Part we learned how the three measures of center offer dfferent ways of provdng us wth a sngle representatve value for a data set. However, consder the followng
More informationCHAPTER 3: BAYESIAN DECISION THEORY
CHATER 3: BAYESIAN DECISION THEORY Decson makng under uncertanty 3 rogrammng computers to make nference from data requres nterdscplnary knowledge from statstcs and computer scence Knowledge of statstcs
More informationA Comparison of Statistical Methods in Interrupted Time Series Analysis to Estimate an Intervention Effect
Transport and Road Safety (TARS) Research Joanna Wang A Comparson of Statstcal Methods n Interrupted Tme Seres Analyss to Estmate an Interventon Effect Research Fellow at Transport & Road Safety (TARS)
More informationFoundations of Machine Learning II TP1: Entropy
Foundatons of Machne Learnng II TP1: Entropy Gullaume Charpat (Teacher) & Gaétan Marceau Caron (Scrbe) Problem 1 (Gbbs nequalty). Let p and q two probablty measures over a fnte alphabet X. Prove that KL(p
More informationAn Application of Alternative Weighting Matrix Collapsing Approaches for Improving Sample Estimates
Secton on Survey Research Methods An Applcaton of Alternatve Weghtng Matrx Collapsng Approaches for Improvng Sample Estmates Lnda Tompkns 1, Jay J. Km 2 1 Centers for Dsease Control and Preventon, atonal
More informationMultifactor Term Structure Models
1 Multfactor Term Structure Models A. Lmtatons of One-Factor Models 1. Returns on bonds of all maturtes are perfectly correlated. 2. Term structure (and prces of every other dervatves) are unquely determned
More informationECONOMETRICS - FINAL EXAM, 3rd YEAR (GECO & GADE)
ECONOMETRICS - FINAL EXAM, 3rd YEAR (GECO & GADE) May 17, 2016 15:30 Frst famly name: Name: DNI/ID: Moble: Second famly Name: GECO/GADE: Instructor: E-mal: Queston 1 A B C Blank Queston 2 A B C Blank Queston
More informationoccurrence of a larger storm than our culvert or bridge is barely capable of handling? (what is The main question is: What is the possibility of
Module 8: Probablty and Statstcal Methods n Water Resources Engneerng Bob Ptt Unversty of Alabama Tuscaloosa, AL Flow data are avalable from numerous USGS operated flow recordng statons. Data s usually
More informationLinear Combinations of Random Variables and Sampling (100 points)
Economcs 30330: Statstcs for Economcs Problem Set 6 Unversty of Notre Dame Instructor: Julo Garín Sprng 2012 Lnear Combnatons of Random Varables and Samplng 100 ponts 1. Four-part problem. Go get some
More informationAppendix - Normally Distributed Admissible Choices are Optimal
Appendx - Normally Dstrbuted Admssble Choces are Optmal James N. Bodurtha, Jr. McDonough School of Busness Georgetown Unversty and Q Shen Stafford Partners Aprl 994 latest revson September 00 Abstract
More information4. Greek Letters, Value-at-Risk
4 Greek Letters, Value-at-Rsk 4 Value-at-Rsk (Hull s, Chapter 8) Math443 W08, HM Zhu Outlne (Hull, Chap 8) What s Value at Rsk (VaR)? Hstorcal smulatons Monte Carlo smulatons Model based approach Varance-covarance
More informationElements of Economic Analysis II Lecture VI: Industry Supply
Elements of Economc Analyss II Lecture VI: Industry Supply Ka Hao Yang 10/12/2017 In the prevous lecture, we analyzed the frm s supply decson usng a set of smple graphcal analyses. In fact, the dscusson
More informationII. Random Variables. Variable Types. Variables Map Outcomes to Numbers
II. Random Varables Random varables operate n much the same way as the outcomes or events n some arbtrary sample space the dstncton s that random varables are smply outcomes that are represented numercally.
More informationLikelihood Fits. Craig Blocker Brandeis August 23, 2004
Lkelhood Fts Crag Blocker Brandes August 23, 2004 Outlne I. What s the queston? II. Lkelhood Bascs III. Mathematcal Propertes IV. Uncertantes on Parameters V. Mscellaneous VI. Goodness of Ft VII. Comparson
More informationSupplementary material for Non-conjugate Variational Message Passing for Multinomial and Binary Regression
Supplementary materal for Non-conjugate Varatonal Message Passng for Multnomal and Bnary Regresson October 9, 011 1 Alternatve dervaton We wll focus on a partcular factor f a and varable x, wth the am
More informationInterval Estimation for a Linear Function of. Variances of Nonnormal Distributions. that Utilize the Kurtosis
Appled Mathematcal Scences, Vol. 7, 013, no. 99, 4909-4918 HIKARI Ltd, www.m-hkar.com http://dx.do.org/10.1988/ams.013.37366 Interval Estmaton for a Lnear Functon of Varances of Nonnormal Dstrbutons that
More informationInformation Flow and Recovering the. Estimating the Moments of. Normality of Asset Returns
Estmatng the Moments of Informaton Flow and Recoverng the Normalty of Asset Returns Ané and Geman (Journal of Fnance, 2000) Revsted Anthony Murphy, Nuffeld College, Oxford Marwan Izzeldn, Unversty of Lecester
More informationEDC Introduction
.0 Introducton EDC3 In the last set of notes (EDC), we saw how to use penalty factors n solvng the EDC problem wth losses. In ths set of notes, we want to address two closely related ssues. What are, exactly,
More informationA Set of new Stochastic Trend Models
A Set of new Stochastc Trend Models Johannes Schupp Longevty 13, Tape, 21 th -22 th September 2017 www.fa-ulm.de Introducton Uncertanty about the evoluton of mortalty Measure longevty rsk n penson or annuty
More informationCOS 511: Theoretical Machine Learning. Lecturer: Rob Schapire Lecture #21 Scribe: Lawrence Diao April 23, 2013
COS 511: Theoretcal Machne Learnng Lecturer: Rob Schapre Lecture #21 Scrbe: Lawrence Dao Aprl 23, 2013 1 On-Lne Log Loss To recap the end of the last lecture, we have the followng on-lne problem wth N
More informationParallel Prefix addition
Marcelo Kryger Sudent ID 015629850 Parallel Prefx addton The parallel prefx adder presented next, performs the addton of two bnary numbers n tme of complexty O(log n) and lnear cost O(n). Lets notce the
More informationCHAPTER 9 FUNCTIONAL FORMS OF REGRESSION MODELS
CHAPTER 9 FUNCTIONAL FORMS OF REGRESSION MODELS QUESTIONS 9.1. (a) In a log-log model the dependent and all explanatory varables are n the logarthmc form. (b) In the log-ln model the dependent varable
More informationTCOM501 Networking: Theory & Fundamentals Final Examination Professor Yannis A. Korilis April 26, 2002
TO5 Networng: Theory & undamentals nal xamnaton Professor Yanns. orls prl, Problem [ ponts]: onsder a rng networ wth nodes,,,. In ths networ, a customer that completes servce at node exts the networ wth
More informationPrice and Quantity Competition Revisited. Abstract
rce and uantty Competton Revsted X. Henry Wang Unversty of Mssour - Columba Abstract By enlargng the parameter space orgnally consdered by Sngh and Vves (984 to allow for a wder range of cost asymmetry,
More informationBayesian belief networks
CS 2750 achne Learnng Lecture 12 ayesan belef networks los Hauskrecht mlos@cs.ptt.edu 5329 Sennott Square CS 2750 achne Learnng Densty estmaton Data: D { D1 D2.. Dn} D x a vector of attrbute values ttrbutes:
More informationOPERATIONS RESEARCH. Game Theory
OPERATIONS RESEARCH Chapter 2 Game Theory Prof. Bbhas C. Gr Department of Mathematcs Jadavpur Unversty Kolkata, Inda Emal: bcgr.umath@gmal.com 1.0 Introducton Game theory was developed for decson makng
More informationEconomic Design of Short-Run CSP-1 Plan Under Linear Inspection Cost
Tamkang Journal of Scence and Engneerng, Vol. 9, No 1, pp. 19 23 (2006) 19 Economc Desgn of Short-Run CSP-1 Plan Under Lnear Inspecton Cost Chung-Ho Chen 1 * and Chao-Yu Chou 2 1 Department of Industral
More informationA Bootstrap Confidence Limit for Process Capability Indices
A ootstrap Confdence Lmt for Process Capablty Indces YANG Janfeng School of usness, Zhengzhou Unversty, P.R.Chna, 450001 Abstract The process capablty ndces are wdely used by qualty professonals as an
More informationUNIVERSITY OF NOTTINGHAM
UNIVERSITY OF NOTTINGHAM SCHOOL OF ECONOMICS DISCUSSION PAPER 99/28 Welfare Analyss n a Cournot Game wth a Publc Good by Indraneel Dasgupta School of Economcs, Unversty of Nottngham, Nottngham NG7 2RD,
More informationAn Approximate E-Bayesian Estimation of Step-stress Accelerated Life Testing with Exponential Distribution
Send Orders for Reprnts to reprnts@benthamscenceae The Open Cybernetcs & Systemcs Journal, 25, 9, 729-733 729 Open Access An Approxmate E-Bayesan Estmaton of Step-stress Accelerated Lfe Testng wth Exponental
More informationTests for Two Ordered Categorical Variables
Chapter 253 Tests for Two Ordered Categorcal Varables Introducton Ths module computes power and sample sze for tests of ordered categorcal data such as Lkert scale data. Assumng proportonal odds, such
More information15-451/651: Design & Analysis of Algorithms January 22, 2019 Lecture #3: Amortized Analysis last changed: January 18, 2019
5-45/65: Desgn & Analyss of Algorthms January, 09 Lecture #3: Amortzed Analyss last changed: January 8, 09 Introducton In ths lecture we dscuss a useful form of analyss, called amortzed analyss, for problems
More informationECE 586GT: Problem Set 2: Problems and Solutions Uniqueness of Nash equilibria, zero sum games, evolutionary dynamics
Unversty of Illnos Fall 08 ECE 586GT: Problem Set : Problems and Solutons Unqueness of Nash equlbra, zero sum games, evolutonary dynamcs Due: Tuesday, Sept. 5, at begnnng of class Readng: Course notes,
More informationA MODEL OF COMPETITION AMONG TELECOMMUNICATION SERVICE PROVIDERS BASED ON REPEATED GAME
A MODEL OF COMPETITION AMONG TELECOMMUNICATION SERVICE PROVIDERS BASED ON REPEATED GAME Vesna Radonć Đogatovć, Valentna Radočć Unversty of Belgrade Faculty of Transport and Traffc Engneerng Belgrade, Serba
More informationEvaluating Performance
5 Chapter Evaluatng Performance In Ths Chapter Dollar-Weghted Rate of Return Tme-Weghted Rate of Return Income Rate of Return Prncpal Rate of Return Daly Returns MPT Statstcs 5- Measurng Rates of Return
More informationComparison of Singular Spectrum Analysis and ARIMA
Int. Statstcal Inst.: Proc. 58th World Statstcal Congress, 0, Dubln (Sesson CPS009) p.99 Comparson of Sngular Spectrum Analss and ARIMA Models Zokae, Mohammad Shahd Behesht Unverst, Department of Statstcs
More informationCS 286r: Matching and Market Design Lecture 2 Combinatorial Markets, Walrasian Equilibrium, Tâtonnement
CS 286r: Matchng and Market Desgn Lecture 2 Combnatoral Markets, Walrasan Equlbrum, Tâtonnement Matchng and Money Recall: Last tme we descrbed the Hungaran Method for computng a maxmumweght bpartte matchng.
More informationMode is the value which occurs most frequency. The mode may not exist, and even if it does, it may not be unique.
1.7.4 Mode Mode s the value whch occurs most frequency. The mode may not exst, and even f t does, t may not be unque. For ungrouped data, we smply count the largest frequency of the gven value. If all
More informationDependent jump processes with coupled Lévy measures
Dependent jump processes wth coupled Lévy measures Naoufel El-Bachr ICMA Centre, Unversty of Readng May 6, 2008 ICMA Centre Dscusson Papers n Fnance DP2008-3 Copyrght 2008 El-Bachr. All rghts reserved.
More informationInternational ejournals
Avalable onlne at www.nternatonalejournals.com ISSN 0976 1411 Internatonal ejournals Internatonal ejournal of Mathematcs and Engneerng 7 (010) 86-95 MODELING AND PREDICTING URBAN MALE POPULATION OF BANGLADESH:
More informationThe Integration of the Israel Labour Force Survey with the National Insurance File
The Integraton of the Israel Labour Force Survey wth the Natonal Insurance Fle Natale SHLOMO Central Bureau of Statstcs Kanfey Nesharm St. 66, corner of Bach Street, Jerusalem Natales@cbs.gov.l Abstact:
More informationSkewness and kurtosis unbiased by Gaussian uncertainties
Skewness and kurtoss unbased by Gaussan uncertantes Lorenzo Rmoldn Observatore astronomque de l Unversté de Genève, chemn des Mallettes 5, CH-9 Versox, Swtzerland ISDC Data Centre for Astrophyscs, Unversté
More informationA Utilitarian Approach of the Rawls s Difference Principle
1 A Utltaran Approach of the Rawls s Dfference Prncple Hyeok Yong Kwon a,1, Hang Keun Ryu b,2 a Department of Poltcal Scence, Korea Unversty, Seoul, Korea, 136-701 b Department of Economcs, Chung Ang Unversty,
More informationChapter 3 Student Lecture Notes 3-1
Chapter 3 Student Lecture otes 3-1 Busness Statstcs: A Decson-Makng Approach 6 th Edton Chapter 3 Descrbng Data Usng umercal Measures 005 Prentce-Hall, Inc. Chap 3-1 Chapter Goals After completng ths chapter,
More information2) In the medium-run/long-run, a decrease in the budget deficit will produce:
4.02 Quz 2 Solutons Fall 2004 Multple-Choce Questons ) Consder the wage-settng and prce-settng equatons we studed n class. Suppose the markup, µ, equals 0.25, and F(u,z) = -u. What s the natural rate of
More informationAppendix for Solving Asset Pricing Models when the Price-Dividend Function is Analytic
Appendx for Solvng Asset Prcng Models when the Prce-Dvdend Functon s Analytc Ovdu L. Caln Yu Chen Thomas F. Cosmano and Alex A. Hmonas January 3, 5 Ths appendx provdes proofs of some results stated n our
More informationEquilibrium in Prediction Markets with Buyers and Sellers
Equlbrum n Predcton Markets wth Buyers and Sellers Shpra Agrawal Nmrod Megddo Benamn Armbruster Abstract Predcton markets wth buyers and sellers of contracts on multple outcomes are shown to have unque
More informationOn Robust Small Area Estimation Using a Simple. Random Effects Model
On Robust Small Area Estmaton Usng a Smple Random Effects Model N. G. N. PRASAD and J. N. K. RAO 1 ABSTRACT Robust small area estmaton s studed under a smple random effects model consstng of a basc (or
More informationScribe: Chris Berlind Date: Feb 1, 2010
CS/CNS/EE 253: Advanced Topcs n Machne Learnng Topc: Dealng wth Partal Feedback #2 Lecturer: Danel Golovn Scrbe: Chrs Berlnd Date: Feb 1, 2010 8.1 Revew In the prevous lecture we began lookng at algorthms
More informationТеоретические основы и методология имитационного и комплексного моделирования
MONTE-CARLO STATISTICAL MODELLING METHOD USING FOR INVESTIGA- TION OF ECONOMIC AND SOCIAL SYSTEMS Vladmrs Jansons, Vtaljs Jurenoks, Konstantns Ddenko (Latva). THE COMMO SCHEME OF USI G OF TRADITIO AL METHOD
More informationNotes on experimental uncertainties and their propagation
Ed Eyler 003 otes on epermental uncertantes and ther propagaton These notes are not ntended as a complete set of lecture notes, but nstead as an enumeraton of some of the key statstcal deas needed to obtan
More informationOCR Statistics 1 Working with data. Section 2: Measures of location
OCR Statstcs 1 Workng wth data Secton 2: Measures of locaton Notes and Examples These notes have sub-sectons on: The medan Estmatng the medan from grouped data The mean Estmatng the mean from grouped data
More informationSpurious Seasonal Patterns and Excess Smoothness in the BLS Local Area Unemployment Statistics
Spurous Seasonal Patterns and Excess Smoothness n the BLS Local Area Unemployment Statstcs Keth R. Phllps and Janguo Wang Federal Reserve Bank of Dallas Research Department Workng Paper 1305 September
More informationAnalysis of Variance and Design of Experiments-II
Analyss of Varance and Desgn of Experments-II MODULE VI LECTURE - 4 SPLIT-PLOT AND STRIP-PLOT DESIGNS Dr. Shalabh Department of Mathematcs & Statstcs Indan Insttute of Technology Kanpur An example to motvate
More informationSequential equilibria of asymmetric ascending auctions: the case of log-normal distributions 3
Sequental equlbra of asymmetrc ascendng auctons: the case of log-normal dstrbutons 3 Robert Wlson Busness School, Stanford Unversty, Stanford, CA 94305-505, USA Receved: ; revsed verson. Summary: The sequental
More informationApplications of Myerson s Lemma
Applcatons of Myerson s Lemma Professor Greenwald 28-2-7 We apply Myerson s lemma to solve the sngle-good aucton, and the generalzaton n whch there are k dentcal copes of the good. Our objectve s welfare
More informationChapter 5 Student Lecture Notes 5-1
Chapter 5 Student Lecture Notes 5-1 Basc Busness Statstcs (9 th Edton) Chapter 5 Some Important Dscrete Probablty Dstrbutons 004 Prentce-Hall, Inc. Chap 5-1 Chapter Topcs The Probablty Dstrbuton of a Dscrete
More informationMonte Carlo Rendering
Last Tme? Monte Carlo Renderng Monte-Carlo Integraton Probabltes and Varance Analyss of Monte-Carlo Integraton Monte-Carlo n Graphcs Stratfed Samplng Importance Samplng Advanced Monte-Carlo Renderng Monte-Carlo
More informationASSESSING GOODNESS OF FIT OF GENERALIZED LINEAR MODELS TO SPARSE DATA USING HIGHER ORDER MOMENT CORRECTIONS
ASSESSING GOODNESS OF FIT OF GENERALIZED LINEAR MODELS TO SPARSE DATA USING HIGHER ORDER MOMENT CORRECTIONS S. R. PAUL Department of Mathematcs & Statstcs, Unversty of Wndsor, Wndsor, ON N9B 3P4, Canada
More information- contrast so-called first-best outcome of Lindahl equilibrium with case of private provision through voluntary contributions of households
Prvate Provson - contrast so-called frst-best outcome of Lndahl equlbrum wth case of prvate provson through voluntary contrbutons of households - need to make an assumpton about how each household expects
More informationUnderstanding price volatility in electricity markets
Proceedngs of the 33rd Hawa Internatonal Conference on System Scences - 2 Understandng prce volatlty n electrcty markets Fernando L. Alvarado, The Unversty of Wsconsn Rajesh Rajaraman, Chrstensen Assocates
More informationQuiz on Deterministic part of course October 22, 2002
Engneerng ystems Analyss for Desgn Quz on Determnstc part of course October 22, 2002 Ths s a closed book exercse. You may use calculators Grade Tables There are 90 ponts possble for the regular test, or
More informationConsumption Based Asset Pricing
Consumpton Based Asset Prcng Mchael Bar Aprl 25, 208 Contents Introducton 2 Model 2. Prcng rsk-free asset............................... 3 2.2 Prcng rsky assets................................ 4 2.3 Bubbles......................................
More informationA Bayesian Classifier for Uncertain Data
A Bayesan Classfer for Uncertan Data Bao Qn, Yun Xa Department of Computer Scence Indana Unversty - Purdue Unversty Indanapols, USA {baoqn, yxa}@cs.upu.edu Fang L Department of Mathematcal Scences Indana
More informationComparative analysis of CDO pricing models
Comparatve analyss of CDO prcng models ICBI Rsk Management 2005 Geneva 8 December 2005 Jean-Paul Laurent ISFA, Unversty of Lyon, Scentfc Consultant BNP Parbas laurent.jeanpaul@free.fr, http://laurent.jeanpaul.free.fr
More informationIntroduction. Why One-Pass Statistics?
BERKELE RESEARCH GROUP Ths manuscrpt s program documentaton for three ways to calculate the mean, varance, skewness, kurtoss, covarance, correlaton, regresson parameters and other regresson statstcs. Although
More informationCapability Analysis. Chapter 255. Introduction. Capability Analysis
Chapter 55 Introducton Ths procedure summarzes the performance of a process based on user-specfed specfcaton lmts. The observed performance as well as the performance relatve to the Normal dstrbuton are
More informationChapter 3 Descriptive Statistics: Numerical Measures Part B
Sldes Prepared by JOHN S. LOUCKS St. Edward s Unversty Slde 1 Chapter 3 Descrptve Statstcs: Numercal Measures Part B Measures of Dstrbuton Shape, Relatve Locaton, and Detectng Outlers Eploratory Data Analyss
More informationFinance 402: Problem Set 1 Solutions
Fnance 402: Problem Set 1 Solutons Note: Where approprate, the fnal answer for each problem s gven n bold talcs for those not nterested n the dscusson of the soluton. 1. The annual coupon rate s 6%. A
More informationProblem Set 6 Finance 1,
Carnege Mellon Unversty Graduate School of Industral Admnstraton Chrs Telmer Wnter 2006 Problem Set 6 Fnance, 47-720. (representatve agent constructon) Consder the followng two-perod, two-agent economy.
More informationThe convolution computation for Perfectly Matched Boundary Layer algorithm in finite differences
The convoluton computaton for Perfectly Matched Boundary Layer algorthm n fnte dfferences Herman Jaramllo May 10, 2016 1 Introducton Ths s an exercse to help on the understandng on some mportant ssues
More informationGlobal sensitivity analysis of credit risk portfolios
Global senstvty analyss of credt rsk portfolos D. Baur, J. Carbon & F. Campolongo European Commsson, Jont Research Centre, Italy Abstract Ths paper proposes the use of global senstvty analyss to evaluate
More informationComputation of the Compensating Variation within a Random Utility Model Using GAUSS Software
Modern Economy, 211, 2, 383-389 do:1.4236/me.211.2341 Publshed Onlne July 211 (http://www.scrp.org/journal/me) Computaton of the Compensatng Varaton wthn a Random Utlty Model Usng GAUSS Software Abstract
More informationFinancial mathematics
Fnancal mathematcs Jean-Luc Bouchot jean-luc.bouchot@drexel.edu February 19, 2013 Warnng Ths s a work n progress. I can not ensure t to be mstake free at the moment. It s also lackng some nformaton. But
More informationFORD MOTOR CREDIT COMPANY SUGGESTED ANSWERS. Richard M. Levich. New York University Stern School of Business. Revised, February 1999
FORD MOTOR CREDIT COMPANY SUGGESTED ANSWERS by Rchard M. Levch New York Unversty Stern School of Busness Revsed, February 1999 1 SETTING UP THE PROBLEM The bond s beng sold to Swss nvestors for a prce
More informationTesting for Omitted Variables
Testng for Omtted Varables Jeroen Weese Department of Socology Unversty of Utrecht The Netherlands emal J.weese@fss.uu.nl tel +31 30 2531922 fax+31 30 2534405 Prepared for North Amercan Stata users meetng
More informationNew Distance Measures on Dual Hesitant Fuzzy Sets and Their Application in Pattern Recognition
Journal of Artfcal Intellgence Practce (206) : 8-3 Clausus Scentfc Press, Canada New Dstance Measures on Dual Hestant Fuzzy Sets and Ther Applcaton n Pattern Recognton L Xn a, Zhang Xaohong* b College
More informationSpatial Variations in Covariates on Marriage and Marital Fertility: Geographically Weighted Regression Analyses in Japan
Spatal Varatons n Covarates on Marrage and Martal Fertlty: Geographcally Weghted Regresson Analyses n Japan Kenj Kamata (Natonal Insttute of Populaton and Socal Securty Research) Abstract (134) To understand
More informationClearing Notice SIX x-clear Ltd
Clearng Notce SIX x-clear Ltd 1.0 Overvew Changes to margn and default fund model arrangements SIX x-clear ( x-clear ) s closely montorng the CCP envronment n Europe as well as the needs of ts Members.
More informationDiscounted Cash Flow (DCF) Analysis: What s Wrong With It And How To Fix It
Dscounted Cash Flow (DCF Analyss: What s Wrong Wth It And How To Fx It Arturo Cfuentes (* CREM Facultad de Economa y Negocos Unversdad de Chle June 2014 (* Jont effort wth Francsco Hawas; Depto. de Ingenera
More informationPivot Points for CQG - Overview
Pvot Ponts for CQG - Overvew By Bran Bell Introducton Pvot ponts are a well-known technque used by floor traders to calculate ntraday support and resstance levels. Ths technque has been around for decades,
More informationFinal Exam. 7. (10 points) Please state whether each of the following statements is true or false. No explanation needed.
Fnal Exam Fall 4 Econ 8-67 Closed Book. Formula Sheet Provded. Calculators OK. Tme Allowed: hours Please wrte your answers on the page below each queston. (5 ponts) Assume that the rsk-free nterest rate
More informationMonetary Tightening Cycles and the Predictability of Economic Activity. by Tobias Adrian and Arturo Estrella * October 2006.
Monetary Tghtenng Cycles and the Predctablty of Economc Actvty by Tobas Adran and Arturo Estrella * October 2006 Abstract Ten out of thrteen monetary tghtenng cycles snce 1955 were followed by ncreases
More informationThe Mack-Method and Analysis of Variability. Erasmus Gerigk
The Mac-Method and Analyss of Varablty Erasmus Gerg ontents/outlne Introducton Revew of two reservng recpes: Incremental Loss-Rato Method han-ladder Method Mac s model assumptons and estmatng varablty
More informationCyclic Scheduling in a Job shop with Multiple Assembly Firms
Proceedngs of the 0 Internatonal Conference on Industral Engneerng and Operatons Management Kuala Lumpur, Malaysa, January 4, 0 Cyclc Schedulng n a Job shop wth Multple Assembly Frms Tetsuya Kana and Koch
More informationFast Laplacian Solvers by Sparsification
Spectral Graph Theory Lecture 19 Fast Laplacan Solvers by Sparsfcaton Danel A. Spelman November 9, 2015 Dsclamer These notes are not necessarly an accurate representaton of what happened n class. The notes
More informationSIMPLE FIXED-POINT ITERATION
SIMPLE FIXED-POINT ITERATION The fed-pont teraton method s an open root fndng method. The method starts wth the equaton f ( The equaton s then rearranged so that one s one the left hand sde of the equaton
More informationIntroduction. Chapter 7 - An Introduction to Portfolio Management
Introducton In the next three chapters, we wll examne dfferent aspects of captal market theory, ncludng: Brngng rsk and return nto the pcture of nvestment management Markowtz optmzaton Modelng rsk and
More informationCorrelations and Copulas
Correlatons and Copulas Chapter 9 Rsk Management and Fnancal Insttutons, Chapter 6, Copyrght John C. Hull 2006 6. Coeffcent of Correlaton The coeffcent of correlaton between two varables V and V 2 s defned
More informationElton, Gruber, Brown and Goetzmann. Modern Portfolio Theory and Investment Analysis, 7th Edition. Solutions to Text Problems: Chapter 4
Elton, Gruber, Brown and Goetzmann Modern ortfolo Theory and Investment Analyss, 7th Edton Solutons to Text roblems: Chapter 4 Chapter 4: roblem 1 A. Expected return s the sum of each outcome tmes ts assocated
More informationEfficient Sensitivity-Based Capacitance Modeling for Systematic and Random Geometric Variations
Effcent Senstvty-Based Capactance Modelng for Systematc and Random Geometrc Varatons 16 th Asa and South Pacfc Desgn Automaton Conference Nck van der Mejs CAS, Delft Unversty of Technology, Netherlands
More informationTopics on the Border of Economics and Computation November 6, Lecture 2
Topcs on the Border of Economcs and Computaton November 6, 2005 Lecturer: Noam Nsan Lecture 2 Scrbe: Arel Procacca 1 Introducton Last week we dscussed the bascs of zero-sum games n strategc form. We characterzed
More informationQuadratic Games. First version: February 24, 2017 This version: December 12, Abstract
Quadratc Games Ncolas S. Lambert Gorgo Martn Mchael Ostrovsky Frst verson: February 24, 2017 Ths verson: December 12, 2017 Abstract We study general quadratc games wth mult-dmensonal actons, stochastc
More information