Strong consistency of nonparametric Bayes density estimation on compact metric spaces
|
|
- Tracy Lewis
- 5 years ago
- Views:
Transcription
1 Strog cosistecy of oparametric Bayes desity estimatio o compact metric spaces Abhishek Bhattacharya ad David Duso Departmet of Statistical Sciece, Duke Uiversity duso@stat.duke.edu Abstract. This article cosiders a broad class of kerel mixture desity models o compact metric spaces ad maifolds. Followig a Bayesia approach with a oparametric prior o the locatio mixig distributio ad badwidth, sufficiet coditios are obtaied o the kerel, prior ad the uderlyig space for strog posterior cosistecy at ay positive cotiuous desity. The prior is also allowed to deped o the sample size ad sufficiet coditios are obtaied for weak ad strog cosistecy. These coditios are verified o the hypersphere usig a vo Mises-Fisher kerel ad o the plaar shape space usig complex Watso kerels.. Itroductio Desity estimatio o compact metric spaces, such as maifolds, is a fudametal problem i oparametric iferece o o-euclidea spaces. Some applicatios iclude directioal data aalysis, spatial modelig, shape aalysis ad dimesioality reductio problems i which the data lie o a ukow lower dimesioal space. However, the literature o statistical theory ad methods of desity estimatio i o-euclidea spaces is still uder-developed. Our focus is o Bayesia oparametric approaches. For oparametric Bayes desity estimatio o the real lie R, there is a rich literature, with Dirichlet process mixtures of Gaussia kerels providig a commolyused approach ([6]) that leads to dese support ([5]) ad weak ad strog posterior cosistecy ([9]). From the celebrated theorem of [6], weak posterior cosistecy results whe the true desity f 0 is i the Kullback-Leibler (KL) support of the prior, meaig that all KL eighborhoods aroud f 0 are assiged positive probability. I geeral, it is quite difficult to show KL support for ew priors for a desity, though [9] provide useful coditios for a class of kerel mixture priors, with [3] extedig these coditios to geeral compact metric spaces. It is widely accepted that weak cosistecy is a isufficiet property whe the focus is o desity estimatio. For example, if f 0 is a desity with respect to Lebesgue measure, weak cosistecy d Key words ad phrases. Noparametric Bayes; Desity Estimatio; Posterior cosistecy; Sample depedet prior; Riemaia maifold; Hypersphere; Plaar shape space.
2 2 ABHISHEK BHATTACHARYA AND DAVID DUNSON oes ot eve esure that the posterior assigs positive probability to the set of desities with respect to Lebesgue measure. Hece, it is importat to provide stroger results. Util very recetly, essetially all the literature o theory of oparametric Bayes desity estimatio focused o oe-dimesioal Euclidea spaces. A importat developmet i multivariate Euclidea spaces is the article of [20] who provide sufficiet coditios for strog cosistecy i oparametric Bayes desity estimatio from Dirichlet process mixtures of multivariate Gaussia kerels. The theory developed i their paper is specialized ad caot be easily geeralized to arbitrary kerel mixtures o more geeral spaces. We are particularly iterested i desity estimatio i the special case i which the compact metric space M correspods to a Riemaia maifold, such as a uit hypersphere or ladmark-based plaar shape space. I order to exted kerel mixture models used i Euclidea spaces to maifolds M, the kerel eeds to be carefully chose. Oe approach is to itroduce a ivertible coordiate map betwee a subset of M ad a Euclidea space ([]). Uder such a approach, the desity prior o M ca be iduced through a kerel mixture model i a Euclidea space. However, several major problems arise i usig such a approach. Firstly, it is ot possible to cover the etire maifold with a sigle smooth coordiate chart except for very simple maifolds, so uless the data are very cocetrated oe may obtai poor performace. Differet local charts ca be patched together to form a atlas, but this may itroduce artifactual discotiuities i the resultig de sity. Because the coordiate map is ot isometric, the geometry of the maifold ca be heavily distorted. As good choices of coordiate frames ecessarily deped o the observatios, additioal ucertaity is automatically iduced. Due to these ad other shortcomigs of coordiate based methods, we focus o modelig approaches that are coordiate free i the sese that we build desity models with respect to the ivariat volume form o the maifold. I [3], a desity model is preseted o a geeral compact metric space with respect to ay fixed base measure usig a radom mixture of probability kerels. Uder mild coditios o the kerel ad the mixig prior, it is show that the prior probability of ay uiform eighborhood of ay cotiuous desity f 0 is positive ad if f 0 is positive everywhere, it lies i the KL support of the prior. Desity estimatio o the plaar shape space is preseted as a special case. I [2], such a desity model is used to carry out classificatio with features o some o- Euclidea maifold ad oparametric Bayes hypothesis testig with observatios o the maifold. Cosistecy results are proved ad for illustratio, the methods are applied to hyperspheres. Focusig o kerel mixture priors for desities o a compact metric space M, i this article, we provide sufficiet coditios o the kerel, prior ad the uderlyig space to esure strog cosistecy. Theorem 2.4 ad Corollary 2.5 provide sufficiet coditios to esure that all total variatio eighborhoods aroud f 0 will be assiged probability covergig to oe as the sample size icreases. The theoretical developmet relies o the method of sieves ad expoetially cosistet tests reviewed i [8]. However, applyig this framework outside Euclidea spaces is ot stadard ad requires careful use of differetial geometry. To illustrate the theory, we focus o desity estimatio o the uit hypersphere usig vo Mises- Fisher kerels ad o the plaar shape space usig complex Watso kerels. I
3 NONPARAMETRIC BAYES DENSITY ESTIMATION ON MANIFOLDS 3 both these cases, it is show that the kerels satisfy the sufficiet coditios. The results also apply to Gaussia mixture desities o R d wheever the true desity has compact support. Whe the maifold is high-dimesioal, priors satisfyig coditios for strog cosistecy ted to put too little probability ear badwidths close to 0, which is udesirable for applicatios. A gamma prior o the iverse-badwidth, for example, caot be show to satisfy the coditios. Hece, we exted the cosistecy results to cover cases with priors depedig o the sample size. Theorem 2.6 exteds the Schwartz theorem to prove weak cosistecy, while Theorem 2.9 proves strog cosistecy usig such priors. A gamma prior with scale decreasig with at a appropriate rate satisfies the coditios for both weak ad strog posterior cosistecy at a expoetial rate. 2. Cosistecy theorems o compact metric spaces 2.. Weak posterior cosistecy. Let (M, ρ) be a compact metric space, ρ beig the distace metric, ad let X be a radom variable o M (from some measurable space (Ω, B, Q)). We assume that the distributio of X has a desity with respect to some fixed fiite base measure λ o M. The atural choice for such a λ whe M is a Riemaia maifold is the ivariat volume form. We are iterested i modellig this ukow desity via a flexible model. Let K(m; µ, κ) be a probability kerel o M with locatio µ M ad iverse-scale κ [0, ), with K(m; µ, κ)λ(dm) =. The a locatio mixture desity model for X is M defied as (2.) f(m; P, κ) = K(m; µ, κ)p (dµ) M with parameters P i the space M(M) of all probability distributios o M ad κ 0. Kerel mixture models are used routiely i Bayesia desity estimatio i Euclidea spaces, with [4] applyig such a approach to bivariate agular data ad [2, 3] cosiderig kerel mixtures o geeral metric spaces. A prior Π o (P, κ) iduces a prior Π o the space of desities D(M) o M through the model (2.). Give a radom realizatio X,..., X of X, we ca compute the posterior of f. The Schwartz theorem([6]) provides a useful tool i provig that the posterior assigs probability covergig to oe i arbitrarily small eighborhoods of the true desity f 0 as the sample size. Let F 0 deote the probability distributio correspodig to f 0, let KL(f 0 ; f) = M f 0(m) log{f 0 (m)/f(m)}λ(dm) deote the KL divergece of aother desity f from f 0, ad let K ɛ (f 0 ) deote the KL eighborhood {f D(M) : KL(f 0 ; f) < ɛ}. f 0 is said to be i the KL support of Π if Π{K ɛ (f 0 )} > 0 for all ɛ > 0. Propositio 2. (Schwartz). If () f 0 is i the KL support of Π, ad (2) U D(M) is such that there exists a uiformly expoetially cosistet sequece of test fuctios for testig H 0 : f = f 0 versus H : f U c, the Π(U X,..., X ) as a.s. F 0. The posterior probability of U c ca be expressed as (2.2) Π(U c X,..., X ) = f(x i) U c i= f Π(df) 0(X i) f(x i) f Π(df) 0(X i)
4 4 ABHISHEK BHATTACHARYA AND DAVID DUNSON Coditio (), kow as the KL coditio, esures that for ay β > 0, (2.3) lim if exp(β) f(x i ) Π(df) = a.s. f 0 (X i ) while coditio (2) implies that lim exp(β 0) for some β 0 > 0 ad therefore i= U c i= f(x i ) Π(df) = 0 a.s. f 0 (X i ) lim exp(β 0/2)Π(U c X,..., X ) = 0 a.s. Hece Propositio 2. provides coditios for posterior cosistecy at a expoetial rate. Propositio 2.2, proved i [3], derives sufficiet coditios o the kerel ad the prior so that f 0 is i the KL support of Π. They are A The kerel K is cotiuous o M M (κ 0, ) for some κ 0 0. A2 lim sup κ m M f 0(m) K(m; µ, κ)f 0 (µ)λ(dµ) = 0. M A3 For ay P M(M) ad κ > 0, there exists κ κ such that (P, κ) supp(π ) with supp(π ) deotig the weak support of Π. A4 f 0 is strictly positive ad cotiuous everywhere. Propositio 2.2. Uder assumptios A-A4, for ay ɛ > 0, { } Π f : sup f(m) f 0 (m) < ɛ m M > 0, which implies that f 0 is i the KL support of Π. Whe U is a weakly ope eighborhood of f 0, coditio (2) i Propositio 2. is always satisfied. Hece uder assumptios A-A4, from Propositio 2.2, weak posterior cosistecy at a expoetial rate follows. We will provide examples of kerels o some compact maifolds which satisfy A ad A2. A3 imposes a mild support coditio o the prior o the mixig distributio ad badwidth which is easily satisfied by several priors. A commo choice is Π π with Π beig a Dirichlet process DP(w 0 P 0 ) with supp(p 0 ) = M ad π beig a desity o R + givig o-zero probability ear ifity Strog cosistecy. Whe U is a total variatio eighborhood of f 0, [3] ad [] show that coditio (2) of Propositio 2. will ot be satisfied i most cases. I [] (also see [9]), a sieve method is cosidered to obtai sufficiet coditios for the umerator i (2.2) to decay at a expoetial rate ad hece get strog posterior cosistecy at a expoetial rate. This is stated i Propositio 2.3. I its statemet, for F D(M) ad ɛ > 0, the L -metric etropy N(ɛ, F) is defied as the logarithm of the miimum umber of ɛ-sized (or smaller) L subsets eeded to cover F. Propositio 2.3. If there exists a D D(M) such that () for sufficietly large, Π(D) c < exp( β) for some β > 0, ad (2) N(ɛ, D )/ 0 as for ay ɛ > 0, the for ay total variatio eighborhood U of f 0, there exists a β 0 > 0 such that lim sup exp(β 0 ) f(x i) U c f Π(df) = 0 a.s. F 0(X i) 0. Hece if f 0 is i
5 NONPARAMETRIC BAYES DENSITY ESTIMATION ON MANIFOLDS 5 the KL support of Π, the posterior probability of ay total variatio eighborhood of f 0 coverges to almost surely. Theorem 2.4, which is the mai theorem of this paper, describes a D which satisfies coditio (2). We impose the followig additioal restrictios o the kerel K ad the space M. A5 There exist positive costats K, a, A such that for all K K, µ, ν M, sup m M,κ [0,K] K(m; µ, κ) K(m; ν, κ) A K a ρ(µ, ν). A6 There exists positive costats a 2, A 2 such that for all κ, κ 2 [0, K], K K, K(m; µ, κ ) K(m; µ, κ 2 ) A 2 K a2 κ κ 2. sup m,µ M A7 There exist positive costats a 3, A 3, A 4 such that give ay ɛ > 0, M ca be covered by A 3 ɛ a3 + A 4 or fewer subsets of diameter at most ɛ. Theorem 2.4. For a positive sequece {κ } divergig to, defie D = { f(p, κ) : P M(M), κ [0, κ ] }. Uder assumptios A5-A7, give ay ɛ > 0, for sufficietly large, N(ɛ, D ) C(ɛ)κ aa3 for some C(ɛ) ( > 0. Hece N(ɛ, D ) is o(), that is, lim N(ɛ, D )/ = 0, wheever κ = o (aa3) ). As a corollary, we derive coditios o the prior Π o (P, κ) uder which strog posterior cosistecy at a expoetial rate follows. Corollary 2.5. Uder assumptios A-A7 ad A8 Π (M(M) ( a, )) < exp( β) for some a < (a a 3 ) ad β > 0, the posterior probability of ay total variatio eighborhood of f 0 coverges to a.s. F 0. Whe we choose Π = Π π with a Dirichlet process Π as i Sectio 2., a choice for π for which assumptios A3 ad A8 are satisfied is a Weibull desity with shape parameter exceedig a a 3. Remark 2.. A gamma prior o κ satisfies A3 but ot A8 (uless a a 3 < ). However that does ot prove that it is ot eligible for strog cosistecy because Corollary 2.5 provides oly sufficiet coditios. Whe the uderlyig space is o-compact (but separable) such as R d, Corollary 2.5 applies to ay true desity f 0 with compact support, say M. The the kerel ca be chose to have o-compact support, such as Gaussia, but the prior o the locatio mixig distributio eeds to have support i M(M). We may eve weake assumptio A5 to A5 sup κ [0,K] K(µ, κ) K(ν, κ) A K a ρ(µ, ν) where f g deotes the L distace. The proof of Theorem 2.4 ca be easily modified to show cosistecy uder this assumptio ad is left to the reader. I such a case, we are modellig a compactly supported desity with a mixture desity possibly havig full support but with locatios draw from a compact domai. Usig a locatio mixture of Gaussia kerels o R d, a ad a 3 from Assumptios A5 ad A7 ca be show to be d/2 ad d respectively. Hece we ca take π to
6 6 ABHISHEK BHATTACHARYA AND DAVID DUNSON be Weibull with shape parameter exceedig d 2 /2 which ca be the gamma prior i oe dimesio. Remark 2.2. Ulike i [9] ad [20], Corollary 2.5 imposes o support restrictio o the scale parameter. It will be exteded to cover desities with o-compact support, i particular R d i later works. Sice most of the o-euclidea maifolds arisig i applicatios are compact, that is ot a high priority Cosistecy with sample size-depedet priors. Whe the dimesio of the maifold is large, as is the case i shape aalysis with a large umber of ladmarks, the costraits o the shape parameter i the proposed Weibull prior o the iverse badwidth become overly-restrictive. I particular, for strog posterior cosistecy, the shape parameter eeds to be very large i high-dimesioal cases, implyig a prior o the badwidth that places very small probability i eighborhoods close to zero, which is udesirable i may applicatios. By istead allowig the prior to deped o sample size, we ca potetially obtai priors that may have better small sample operatig characteristics, while still leadig to strog cosistecy. However, for -depedet priors, the KL coditio is o loger sufficiet to esure that (2.3) holds ad hece the Schwartz theorem breaks dow. I this sectio, we will modify the coditios ad derive weak ad strog cosistecy results for -depedet priors. As recommeded i earlier sectios, we let P ad κ be idepedet uder Π. The, assumig P Π is a costat prior, we focus o the case i which the iverse-badwidth has a sample size-depedet prior distributio o R +, κ π. Deote the resultig sequece of iduced priors o D(M) as Π. Theorem 2.6 proves weak posterior cosistecy uder the followig assumptios o the prior. A9 The prior Π has full support. A0 For ay β > 0, there exists a κ 0 0, such that for all κ κ 0, lim if exp(β)π (κ) =. Theorem 2.6. Uder assumptios A ad A2 o the kerel, A9 ad A0 o the prior ad A4 o the true desity f 0, the posterior probability of ay weak eighborhood of f 0 coverges to oe a.s. F 0. The proof is immediate from the followig two lemmas. Lemma 2.7. Uder assumptios A-A2, A4 ad A9-A0, for ay β > 0, a.s. F 0. lim if exp(β) f(x i ) f 0 (X i ) Π (df) = Lemma 2.8. If there exists a uiformly expoetially cosistet sequece of test fuctios for testig H 0 : f = f 0 versus H : f U c, ad Π (U c ) > 0 for all, the for some β 0 > 0, a.s. F 0. lim exp(β 0) U c f(x i ) f 0 (X i ) Π (df) = 0
7 NONPARAMETRIC BAYES DENSITY ESTIMATION ON MANIFOLDS 7 The proof of Lemma 2.8 is related to that of Lemma [0] which is stated for a costat prior Π but with the set U c depedig o, they call this V. There it is assumed that lim if Π(V ) > 0 but that is ot ecessary as log as Π(V ) > 0 for all > C with C a sufficietly large costat. A gamma prior π (κ) exp( β κ)κ α, α, β > 0, deoted by Gam(α, β ) satisfies assumptio A0 as log as β is o(). For strog cosistecy, we impose the followig additioal coditio o π. Let a ad a 3 be as i assumptios A5 ad A7. A For some β 0 > 0 ad a < (a a 3 ), lim exp(β 0)π {( a, )} = 0. Theorem 2.9. Uder assumptios A-A2, A4-A7 ad A9-A, the posterior probability of ay total variatio eighborhood of f 0 coverges to a.s F 0. The proof is very similar to that of Corollary 2.5 ad hece is omitted. A Gam(α, β ) prior satisfies A whe (aa3) is o(β ). Hece, for example, we have weak ad strog posterior cosistecy with β = b /{log()} b2 for ay b, b 2 > 0. I the subsequet sectios, we cosider desity estimatio o two specific compact maifolds, amely the hypersphere ad the plaar shape space. We costruct mixture models usig suitable kerels which satisfy the requiremets for weak ad strog cosistecy. 3. Applicatio to uit hypersphere Let M be the uit sphere S d embedded i R d+. It is a compact Riemaia maifold of dimesio d ad a compact metric space uder the chord distace ρ(u, v) = u v 2,. 2 deotig the L 2 -orm. To defie a probability desity model as i (2.) with respect to the volume form V, we eed a suitable kerel which satisfies the assumptios i Sectio 2. Oe of the most commoly used probability desities o this space is the vo Mises-Fisher (vmf) desity which is give by (3.) vmf(m; µ, κ) = c (κ) exp(κm T µ), with c beig the ormalizig costat which ca be derived to be (3.2) 2π d/2 Γ( d 2 ) exp(κt)( t 2 ) d/2 dt. The vmf desity o S was first derived i [7] ad the desity i case of S 2 was give by [7]. [8] geeralized this distributio to S d ad examied may of its properties. It ca be show that the parameter µ is the extrisic mea (as defied i [4]), ad hece ca be iterpreted as the distributio locatio. The parameter κ is a measure of cocetratio, with κ = 0 correspodig to the uiform distributio havig costat desity equal to / V (dm). As κ diverges to, S d the vmf distributio coverges to a poit mass at µ i a L sese uiformly. This is proved i Theorem 3.. Theorem 3.. The vmf kerel satisfies assumptio A with κ 0 = 0 ad assumptio A2 for ay cotiuous f 0.
8 8 ABHISHEK BHATTACHARYA AND DAVID DUNSON Hece from Propositio 2.2, weak posterior cosistecy follows usig the locatio mixture desity model (2.) with a Dirichlet Process prior o P ad a idepedet gamma prior o κ. I the d = 2 special case, [4] proposed a closely related model but did ot cosider theoretical properties. Theorem 3.2 verifies the assumptios for strog cosistecy. Theorem 3.2. The vmf kerel o S d satisfies assumptio A5 with a = d/2 + ad A6 with a 2 = d/2. The compact metric-space (S d, ρ) satisfies assumptio A7 with a 3 = d. As a result a Weibull prior o κ with shape parameter exceedig (d + d 2 /2) satisfies the coditio of Corollary 2.5 ad strog posterior cosistecy follows. The proofs of Theorems 3. ad 3.2 use the followig lemma which establishes certai properties of the ormalizig costat. Lemma 3.3. Defie c(κ) = exp( κ)c(κ), κ 0. The c is decreasig ad for κ, c(κ) Cκ d/2 for some appropriate positive costat C. Whe d is large, as is ofte the case for spherical data, a more appropriate prior o κ for which weak ad strog cosistecies hold ca be Gam(α, β ) as metioed at the ed of Plaar Shape Space 4.. Backgroud. Let M be the plaar shape space Σ k 2 which is defied as follows. Cosider a set of k ladmark locatios, k > 2, o a 2D image, ot all poits beig the same. We refer to such a set as a k-ad. The similarity shape of this k-ad is what remais after removig the Euclidea rigid body motios of traslatio, rotatio ad scalig. We use the followig shape represetatio first proposed by [2]. Deote the k-ad by a complex k-vector z i C k. To remove the effect of traslatio from z let z c = z z, with z = ( k j= z j)/k beig the cetroid. The cetered k-ad z c lies i a k dimesioal complex subspace, ad hece we ca use k complex coordiates. The effect of scalig is the removed by ormalizig the coordiates of z c to obtai a poit w o the complex uit sphere CS k 2 i C k. Sice w cotais the shape iformatio of z alog with rotatio, it is called the preshape of z. The similarity shape of z is the orbit of w uder all rotatios i 2D which is [w] = {e iθ w : θ ( π, π]}. This represets a shape as the set of all itersectio poits of a uique complex lie passig through the origi with CS k 2 ad the plaar shape space Σ k 2 is the the set of all such shapes. Hece Σ k 2 ca be idetified with the space of all complex lies passig through the origi i C k which is the complex projective space ad is a compact Riemaia maifold of dimesio 2k 4. The Σ k 2 ca be embedded ito the space of all order k complex Hermitia matrices via the embeddig J([w]) = ww, deotig the complex cojugate traspose. This embeddig iduces a distace o Σ k 2 called the extrisic distace which geerates the maifold topology ad is give by d E ([u], [v]) = J([u]) J([v]) = 2( u v 2 ) ([u], [v] Σ k 2). For more details, see [3] ad the refereces cited therei.
9 NONPARAMETRIC BAYES DENSITY ESTIMATION ON MANIFOLDS Desity model. We defie a locatio-mixture desity o Σ k 2 as i (2.) with respect to the Riemaia volume form V ad the kerel beig a complex Watso desity. This complex Watso desity was used i [5] for parametric desity modellig ad is give by (4.) (4.2) CW(m; µ, κ) = c (κ) exp{κ( z ν 2 )} (m = [z], µ = [ν]) ) k 3 with c(κ) = π k 2 κ ( 2 k κ r exp( κ). r! It is show i [3] that the complex Watso kerel satisfies assumptios A ad A2 i 2. Usig a Dirichlet Process prior o the locatio mixig distributio ad a idepedet gamma prior o the iverse-scale parameter, Propositio 2.2 implies that the desity model (2.) has full support i the space of all positive cotiuous desities o Σ k 2 i uiform ad KL sese ad hece the posterior is weakly cosistet. Theorem 4. verifies that the complex Watso kerel also satisfies the regularity coditios i A5 ad A6. Theorem 4.. The complex Watso kerel CW(m; µ, κ) o the compact metric space Σ k 2 edowed with the extrisic distace d E satisfies assumptio A5 with a = k ad A6 with a 2 = 3k 8. The proof uses Lemma 4.2 which verifies certai properties of the ormalizig costat. Lemma 4.2. Let c(κ) be the ormalizig costat for CW(µ, κ) as defied i (4.2). The c is decreasig o [0, ) with If we defie lim c(κ) = πk 2 κ 0 (k 2)! it follows that c is icreasig with k 3 c(κ) = exp( κ) lim c(κ) = 0, lim κ 0 ad lim c(κ) = 0. κ r=0 κ r r!, c(κ) = ad κ c(κ) (k 2)! exp( κ)κ k 2. r=0 Proof. Follows from direct computatios. Theorem 4.3 verifies that assumptio A7 holds o Σ k 2. Theorem 4.3. The compact metric space (Σ k 2, d E ) satisfies assumptio A7 with a 3 = 2k 3. As a result, Corollary 2.5 implies that strog posterior cosistecy holds with Π = (DP )(ω 0 P 0 ) π, for Weibull π with shape parameter exceedig (2k 3)(k ). Alteratively oe may use a gamma prior o κ with iverse-scale icreasig with at a suitable rate ad we have cosistecy usig Theorems 2.6 ad 2.9.
10 0 ABHISHEK BHATTACHARYA AND DAVID DUNSON 5. Summary We cosider kerel mixture desity models o geeral compact metric spaces ad obtai sufficiet coditios o the kerel, priors ad the space for the desity estimate to be strogly cosistet. Thereby we exted the existig literature o strog posterior cosistecy o R usig Gaussia kerels to more geeral o- Euclidea maifolds. The coditios are verified for specific kerels o two importat maifolds, amely the hypersphere ad the plaar shape space. We also allow the prior to deped o the sample size ad obtai sufficiet coditios for weak ad strog cosistecy. The assumptio that the true desity is positive everywhere ca be relaxed if the locatios for the mixture desity model are draw from the support of the truth. 6. Appedix 6.. Proof of Theorem 2.4. I this proof ad the subsequet oes, we shall use a geeral symbol C for ay costat ot depedig o (but possibly o ɛ). Proof. Give δ > 0 ( δ (ɛ, )), cover M by N ( N (δ )) may disjoit subsets of diameter at most δ : M = N i= E i. Assumptio A7 implies that for δ sufficietly small, N Cδ a3. Pick µ i E i, i =,..., N, ad defie for a probability P, (6.) N P = P (E i )δ µi, P (E) = (P (E ),..., P (E N )) T. i= Deotig the L -orm as., for ay κ κ, (6.2) (6.3) N f(p, κ) f(p, κ) K(µ, κ) K(µ i, κ) P (dµ) i= E i C sup m M K(m; µ, κ) K(m; µ i, κ) P (dµ) i E i Cκ a δ. The iequality i (6.3) follows from (6.2) usig Assumptio A5. For κ, κ κ, P M(M), (6.4) f(p, κ) f(p, κ) C sup m,µ M K(m; µ, κ) K(m; µ, κ) Cκ a2 κ κ, the iequality i (6.4) followig from Assumptio A6. Give δ 2 > 0 ( δ 2 (ɛ, )), cover [0, κ ] by fiitely may subsets of legth at most δ 2, the umber of such subsets required beig at most κ δ2. Call the collectio of these subsets W (δ 2, ). Lettig S d = {x [0, ] d : x i }, S d is compact uder the L -metric ( x L = x i, x R d ), ad hece give ay δ 3 > 0 ( δ 3 (ɛ)), ca be covered by fiitely may subsets of the cube [0, ] d each of diameter at most δ 3. I particular cover S d with cubes of side legth δ 3 /d lyig partially or totally i S d. The a upper boud o the umber N 2 N 2 (δ 3, d) of such cubes ca be show to be λ(s d (+δ 3)) (δ 3/d), λ deotig the Lebesgue measure o R d ad S d d (r) = {x [0, ) d :
11 NONPARAMETRIC BAYES DENSITY ESTIMATION ON MANIFOLDS xi r}. Sice λ(s d (r)) = r d /d!, hece N 2 (δ 3, d) dd d! ( ) d + δ3. Let W(δ 3, d) deote the partitio of S d as costructed above. Let d = N (δ ). For i N 2 (δ 3, d ), j κ δ 2, defie D ij = {f(p, κ) : P (E) W i, κ W j }, with W i ad W j beig elemets of W(δ 3, d ) ad W (δ 2, ) respectively. We claim that this subset of D has L diameter of at most ɛ. For f(p, κ), f( P, κ) i this set, f(p, κ) f( P, κ) (6.5) f(p, κ) f(p, κ) + f(p, κ) f( P, κ) + + f( P, κ) f( P, κ) + f( P, κ) f( P, κ). From iequality (6.3), it follows that the first ad third terms i (6.5) are at most Cκ a δ. The secod term ca be bouded by d i= δ 3 P (E i ) P (E i ) < δ 3 ad from the iequality i (6.4), the fourth term is bouded by Cκ a2 δ 2. Hece the claim holds if we choose δ = Cκ a, δ 2 = Cκ a2, ad δ 3 = C. The umber of such subsets coverig D is at most N 2 (δ 3, d )κ δ2. From Assumptio A7, it follows that for sufficietly large, d = N (δ ) Cκ aa3. Usig the Stirlig s formula, we ca boud log(n 2 (δ 3, d )) by Cd. Also κ δ2 is bouded by Cκ a2+, so that N(ɛ, D ) C + C log(κ ) + Cd Cκ aa3 for sufficietly large. This completes the proof Proof of Lemma 2.7. Proof. Uder assumptios A ad A2, from the proof of Propositio 2.2, it follows that give ɛ > 0, for ay κ 0 0, there exist κ 2 > κ > κ 0 ad a weakly ope eighborhood W of F 0 (all depedig o ɛ), such that K ɛ (f 0 ) cotais {f(p, κ) : P W, κ (κ, κ 2 )}. Hece f(x i ) f 0 (X i ) Π (df) W (κ,κ 2) K ɛ(f 0) f(x i ) f 0 (X i ) Π (df) f(x i ; P, κ) π (κ)π (dp )dκ. f 0 (X i ) By the law of large umbers, for ay f K ɛ (f 0 ), log{(f 0 /f)(x i )} KL(f 0 ; f) < ɛ i
12 2 ABHISHEK BHATTACHARYA AND DAVID DUNSON a.s. F0 as. Therefore for ay P W ad κ (κ, κ 2 ), f(x i ; P, κ) lim if exp(2ɛ) f 0 (X i ) lim if exp[[2ɛ (/) log{f 0 (X i )/f(x i ; P, κ)}]] = a.s. F0. i Also from Assumptio A0, for κ 0 sufficietly large, lim if exp(ɛ)π (κ) = ad hece lim if exp(3ɛ) f(x i ; P, κ) π (κ) = a.s. F0. f 0 (X i ) By Fubii-Toelli theorem, there exists a Ω 0 Ω with probability such that for ay ω Ω 0, f(x i (ω); P, κ) lim if exp(3ɛ) π (κ) = f 0 (X i (ω)) for all (P, κ) W (κ, κ 2 ) outside of a Π (dp ) dκ measure 0 subset. By Assumptio A9, Π (W) > 0. Therefore usig the Fatou s lemma, we coclude that f(x i ) lim if exp(3ɛ) f 0 (X i ) Π (df) W (κ,κ 2) lim if{exp(3ɛ) Sice ɛ was arbitrary, the proof is completed Proof of Lemma 3.3. Proof. Express c(κ) as C f(x i ; P, κ) π (κ)}π (dp )dκ = a.s. F0. f 0 (X i ) exp{ κ( t)}( t 2 ) d/2 dt ad it is clear that it is decreasig. This expressio suggests that c(κ) C C = C 0 0 if κ. This completes the proof. 0 exp{ κ( t)}( t 2 ) d/2 dt exp{ κ( t 2 )}( t 2 ) d/2 dt exp( κu)u d/2 ( u) /2 du C 0 exp( κu)u d/2 du κ = Cκ d/2 exp( v)v d/2 dv 0 C { exp( v)v d/2 dv } κ d/2 0 =
13 NONPARAMETRIC BAYES DENSITY ESTIMATION ON MANIFOLDS Proof of Theorem 3.. Proof. Deote by M the uit sphere S d ad by ρ the chord distace o it. Express the vmf kerel as K(m; µ, κ) = c (κ) exp [ κ { ρ 2 (m, µ)/2 }] (m, µ M; κ [0, )). Sice ρ is cotiuous o the product space M M ad c is cotiuous ad ovaishig o [0, ), K is cotiuous o M M [0, ) ad assumptio A follows. For a give cotiuous fuctio φ o M, m M, κ 0, defie I(m, κ) = φ(m) K(m; µ, κ)φ(µ)v (dµ) = K(m; µ, κ){φ(m) φ(µ)}v (dµ). M The showig assumptio A2 for f 0 = φ is equivalet to showig M lim ( sup I(m, κ) ) = 0. κ m M To simplify I(m, κ), make a chage of coordiates µ µ = U(m) T µ, µ θ Θ d (0, π) d (0, 2π) where U(m) is a orthogoal matrix with first colum equal to m ad θ = (θ,..., θ d ) T are the spherical coordiates of µ µ(θ) which are give by µ j = cos θ j si θ h, j =,..., d, µ d+ = h<j d si θ j. j= Usig these coordiates, the volume form ca be writte as V (dµ) = V (d µ) = si d (θ ) si d 2 (θ 2 )... si(θ d )dθ... dθ d ad hece I(m, κ) equals c { (κ) exp κ cos(θ ) }{ φ(m) φ (U(m) µ) } si d (θ )... si(θ d )dθ... dθ d Θ d = c (κ) exp(κt) { φ(m) φ (U(m) µ) } ( t 2 ) d/2 (6.6) Θ d (,) si d 2 (θ 2 )... si(θ d )dθ 2... dθ d dt where t = cos(θ ), µ = µ ( θ(t) ) ad θ(t) = (arccos(t), θ 2,..., θ d ) T. I the itegrad i (6.6), the distace betwee m ad U(m) µ is 2( t). Substitute t = κ s i the itegral with s (0, 2κ). Defie Φ(s, κ) = sup { φ(m) φ( m) : m, m M, ρ(m, m) 2κ s }. The φ(m) φ (U(m) µ) Φ(s, κ).
14 4 ABHISHEK BHATTACHARYA AND DAVID DUNSON Sice φ is uiformly cotiuous o (M, ρ), therefore Φ is bouded o (R + ) 2 ad lim κ Φ(s, κ) = 0. Hece from (6.6), we deduce that sup m M I(m, κ) c (κ)κ exp(κ s)φ(s, κ)(κ s(2 κ s)) d/2 (6.7) Θ d (0,2κ) From Lemma 3.3, it follows that si d 2 (θ 2 )... si(θ d )dθ 2... dθ d ds Cκ d/2 c (κ) Φ(s, κ)e s s d/2 ds. lim sup κ d/2 c (κ) <. κ This i tur, usig the Lebesgue Domiated Covergece Theorem implies that the expressio i (6.7) coverges to 0 as κ. This verifies assumptio A2 ad completes the proof Proof of Theorem 3.2. I the proof, B d (r) deotes the ball of radius r aroud 0 i R d : B d (r) = {x R d : x 2 r} ad B d refers to B d (). Proof. It is clear from (3.) ad (3.2) that the vmf kerel K is cotiuously differetiable o R d+ R d+ [0, ). Hece sup K(m; µ, κ) K(m; ν, κ) sup m S d,κ [0,K] m S d,x B d+,κ [0,K] x K(m; x, κ) 2 µ ν 2. Sice x K(m; x, κ) = κ c (κ) exp{ κ( m T x)}m, its orm is bouded by κ c (κ). Lemma 3.3 implies that this i tur is bouded by K c (K) CK d/2+ for κ K ad K. This proves assumptio A5 with a = d/2 +. To verify A6, give κ, κ 2 K, use the iequality, sup K(m; µ, κ ) K(m; µ, κ 2 ) sup m,µ S κ K(m; µ, κ) κ κ 2. d By direct computatios, oe ca show that 0 m,µ S d,κ K K(m; µ, κ) = κ κ c(κ) c 2 (κ) exp{ κ( m T µ)} c (κ) exp{ κ( m T µ)}( m T µ), c(κ) = C exp{ κ( t)}( t)( t 2 ) d/2 dt, κ κ c(κ) C c(κ).
15 NONPARAMETRIC BAYES DENSITY ESTIMATION ON MANIFOLDS 5 Therefore, usig Lemma 3.3, κ K(m; µ, κ) C c (κ) C c (K) CK d/2 for ay κ K ad K. Hece A6 is verified with a 2 = d/2. Fially to verify A7, ote that S d B d+ [, ] d+ which ca be covered by fiitely may cubes of side legth ɛ/(d + ). Each such cube has L 2 diameter ɛ. Hece their itersectios with S d provides a fiite ɛ-cover for this maifold. If ɛ <, such a cube itersects with S d oly if it lies etirely i B d+ ( + ɛ) B d+ ( ɛ) c. The umber of such cubes, ad hece the ɛ-cover size ca be bouded by Cɛ (d+) {( + ɛ) d+ ( ɛ) d+ } Cɛ d for some C > 0 ot depedig o ɛ. This verifies A7 for appropriate positive costats A 3, A 4 ad a 3 = d ad completes the proof Proof of Theorem 4.. Proof. Express the complex Watso kerel as ( ) κ K(m; µ, κ) = c (κ) exp 2 d2 E(m, µ). Give κ 0, defie The φ (t) 2κ, so that which implies that (6.8) ( ) κ φ(t) = exp 2 t2, t [0, 2]. φ(t) φ(s) 2κ s t, s, t [0, 2] K(m; µ, κ) K(m; ν, κ) c (κ) 2κ d E (m, µ) d E (m, ν) 2κc (κ)d E (µ, ν). For κ K, from Lemma 4.2, it follows that κc (κ) Kc (K) = π 2 k K k c (K) provided K. Hece for ay K, π 2 k K k c () sup κc (κ) CK k κ [0,K] ad from iequality (6.8), a = k follows. (6.9) By direct computatio, oe ca show that κ K(m; µ, κ) = πk 2 exp { 2 κd2 E(m, µ) κ } c 2 (κ)κ 2 k[ r=k κ r r! { k 2 r 2 d2 E(m, µ) }].
16 6 ABHISHEK BHATTACHARYA AND DAVID DUNSON Deote by S the sum i the secod lie of (6.9) ad by T r its rth term, r k. Sice d 2 E (m, µ) 2, it ca be show that { k 2 if k r 2k 4, T r r k + 2 if 2k 3 r, so that S (k 2) 2k 4 r=k κ r r! + r=2k 3 κ r k 3 = (k 2)κ k 2 κ r (r + k )! + κ2k 4 r=0 Cκ k 2 e κ + κ 2k 4 e κ. r! (r k + 2) r=0 κ r (r + k ) (r + 2k 3)! Plug the above iequality i (6.9) to get K(m; µ, κ) κ Cc 2 (κ)κ 2 k exp { 2 κd2 E(m, µ) } (Cκ k 2 + κ 2k 4 ) (6.0) Cc 2 (κ)(c + κ k 2 ). For κ K ad K, usig Lemma 4.2, we boud the expressio i (6.0) by (6.) Cc 2 (K)(C + K k 2 ) = CK 2k 6 c 2 (K)(C + K k 2 ) CK 2k 6 c 2 ()(C + K k 2 ) CK 3k 8 for K sufficietly large. Sice K is a cotiuously differetiable i κ, from (6.) it follows that there exists K > 0 such that for all K K, κ, κ 2 K, sup K(m; µ, κ ) K(m; µ, κ 2 ) sup K(m; µ, κ) m,µ Σ k 2 m,µ Σ k 2,κ [0,K] κ κ κ 2 CK 3k 8 κ κ 2. This proves Assumptio A6 with a 2 = 3k 8 ad completes the proof Proof of Theorem 4.3. I the proof, C i, i =, 2,... deote positive costats possibly depedig o k. Proof. The preshape sphere CS k 2, as a real maifold, ca be idetified with the real uit sphere S 2k 3. Edow it with the chord distace iduced by the L 2 - orm u 2 = k u i 2 (u = (u,..., u k ) T ). i= The from Theorem 3.2, it follows that give ay δ > 0, CS k 2 ca be covered by fiitely may subsets of diameter less tha or equal to δ, the umber of such subsets beig bouded by C δ (2k 3) + C 2. The extrisic distace d E o Σ k 2 ca be bouded by the chord distace o CS k 2 as follows. For u, v CS k 2, u v 2 2 = 2 2Re(u v) 2 2 u v = 2( u v ) ( + u v )( u v ) = 2 d2 E([u], [v]).
17 NONPARAMETRIC BAYES DENSITY ESTIMATION ON MANIFOLDS 7 Hece d E ([u], [v]) 2 u v 2, so that give ay ɛ > 0, the shape image of a δ-cover for CS k 2 with δ = ɛ/ 2 provides a ɛ-cover for Σ k 2. Hece the ɛ-coverig size for Σ k 2 ca be bouded by C ɛ (2k 3) + C 2. This completes the proof. Refereces [] A. R. Barro. Uiformly powerful goodess of fit tests. A. Statist., 7:07 24, 989. [2] A. Bhattacharya ad D. Duso. Noparametric Bayes classificatio ad testig o maifolds with applicatios o hypersphere Discussio Paper, Departmet of Statistical Sciece, Duke Uiversity. [3] A. Bhattacharya ad D. Duso. Noparametric Bayesia desity estimatio o maifolds with applicatios to plaar shapes. Biometrika, 200. I Press. [4] R. N. Bhattacharya ad V. Patragearu. Large sample theory of itrisic ad extrisic sample meas o maifolds. A. Statist., 3: 29, [5] I. L. Dryde ad K. V. Mardia. Statistical Shape Aalysis. Wiley N.Y., 998. [6] M. D. Escobar ad M. West. Bayesia desity-estimatio ad iferece usig mixtures. J. Am. Statist. Assoc., 90: , 995. [7] R. A. Fisher. Dispersio o a sphere. Proc. of the Royal Soc. of Lodo Ser. A - Math. ad Phy. Sci., 30: , 953. [8] S. Ghosal. Bayesia Noparametrics. Cambridge Uiversity Press, 200. I Press. [9] S. Ghosal, J. K. Ghosh, ad R. V. Ramamoorthi. Posterior cosistecy of dirichlet mixtures i desity estimatio. A. Statist., 27:43 58, 999. [0] J.K. Ghosh ad R.V. Ramamoorthi. Bayesia Noparametrics. Spriger, N.Y., [] M. Hirsch. Differetial Topology. Spriger Verlag, New York, 976. [2] D. G. Kedall. Shape maifolds, procrustea metrics, ad complex projective spaces. Bull. of the Lodo Math. Soc., 6:8 2, 984. [3] L. LeCam. Covergece of estimates uder dimesioality restrictios. A. Statist., :38 53, 973. [4] K. P. Leox, D. B. Dahl, M. Vaucci, ad J. W. Tsai. Desity estimatio for protei coformatio agles usig a bivariate vo Mises distributio ad Bayesia oparametrics. J. Am. Statist. Assoc., 04: , [5] A. Y. Lo. O a class of Bayesia oparametric estimates.. desity estimates. A. Statist., 2:35 357, 984. [6] L. Schwartz. O Bayes procedures. Z. Wahrsch. Verw. Gebiete, 4:0 26, 965. [7] R.V. vo Mises. Uber die Gazzahligkeit der Atomgewicht ud verwadte Frage. Physik Z, 9: , 98. [8] G.S. Watso ad E.J. Williams. Costructio of sigificace tests o the circle ad sphere. Biometrika, 43:344 52, 953. [9] Y. Wu ad S. Ghosal. Kullback-Leibler property of kerel mixture priors i Bayesia desity estimatio. Elec J. Statist., 2:298 33, [20] Y. Wu ad S. Ghosal. L - cosistecy of dirichlet mixtures i multivariate bayesia desity estimatio o bayes procedures To Appear. Departmet of Statistical Sciece, Duke Uiversity, Durham, NC, USA
5. Best Unbiased Estimators
Best Ubiased Estimators http://www.math.uah.edu/stat/poit/ubiased.xhtml 1 of 7 7/16/2009 6:13 AM Virtual Laboratories > 7. Poit Estimatio > 1 2 3 4 5 6 5. Best Ubiased Estimators Basic Theory Cosider agai
More informationSequences and Series
Sequeces ad Series Matt Rosezweig Cotets Sequeces ad Series. Sequeces.................................................. Series....................................................3 Rudi Chapter 3 Exercises........................................
More informationLecture 9: The law of large numbers and central limit theorem
Lecture 9: The law of large umbers ad cetral limit theorem Theorem.4 Let X,X 2,... be idepedet radom variables with fiite expectatios. (i) (The SLLN). If there is a costat p [,2] such that E X i p i i=
More information14.30 Introduction to Statistical Methods in Economics Spring 2009
MIT OpeCourseWare http://ocwmitedu 430 Itroductio to Statistical Methods i Ecoomics Sprig 009 For iformatio about citig these materials or our Terms of Use, visit: http://ocwmitedu/terms 430 Itroductio
More informationBayes Estimator for Coefficient of Variation and Inverse Coefficient of Variation for the Normal Distribution
Iteratioal Joural of Statistics ad Systems ISSN 0973-675 Volume, Number 4 (07, pp. 7-73 Research Idia Publicatios http://www.ripublicatio.com Bayes Estimator for Coefficiet of Variatio ad Iverse Coefficiet
More informationRafa l Kulik and Marc Raimondo. University of Ottawa and University of Sydney. Supplementary material
Statistica Siica 009: Supplemet 1 L p -WAVELET REGRESSION WITH CORRELATED ERRORS AND INVERSE PROBLEMS Rafa l Kulik ad Marc Raimodo Uiversity of Ottawa ad Uiversity of Sydey Supplemetary material This ote
More informationAsymptotics: Consistency and Delta Method
ad Delta Method MIT 18.655 Dr. Kempthore Sprig 2016 1 MIT 18.655 ad Delta Method Outlie Asymptotics 1 Asymptotics 2 MIT 18.655 ad Delta Method Cosistecy Asymptotics Statistical Estimatio Problem X 1,...,
More informationCombining imperfect data, and an introduction to data assimilation Ross Bannister, NCEO, September 2010
Combiig imperfect data, ad a itroductio to data assimilatio Ross Baister, NCEO, September 00 rbaister@readigacuk The probability desity fuctio (PDF prob that x lies betwee x ad x + dx p (x restrictio o
More informationIntroduction to Probability and Statistics Chapter 7
Itroductio to Probability ad Statistics Chapter 7 Ammar M. Sarha, asarha@mathstat.dal.ca Departmet of Mathematics ad Statistics, Dalhousie Uiversity Fall Semester 008 Chapter 7 Statistical Itervals Based
More informationMaximum Empirical Likelihood Estimation (MELE)
Maximum Empirical Likelihood Estimatio (MELE Natha Smooha Abstract Estimatio of Stadard Liear Model - Maximum Empirical Likelihood Estimator: Combiatio of the idea of imum likelihood method of momets,
More informationA Bayesian perspective on estimating mean, variance, and standard-deviation from data
Brigham Youg Uiversity BYU ScholarsArchive All Faculty Publicatios 006--05 A Bayesia perspective o estimatig mea, variace, ad stadard-deviatio from data Travis E. Oliphat Follow this ad additioal works
More information18.S096 Problem Set 5 Fall 2013 Volatility Modeling Due Date: 10/29/2013
18.S096 Problem Set 5 Fall 2013 Volatility Modelig Due Date: 10/29/2013 1. Sample Estimators of Diffusio Process Volatility ad Drift Let {X t } be the price of a fiacial security that follows a geometric
More information5 Statistical Inference
5 Statistical Iferece 5.1 Trasitio from Probability Theory to Statistical Iferece 1. We have ow more or less fiished the probability sectio of the course - we ow tur attetio to statistical iferece. I statistical
More information1 Estimating sensitivities
Copyright c 27 by Karl Sigma 1 Estimatig sesitivities Whe estimatig the Greeks, such as the, the geeral problem ivolves a radom variable Y = Y (α) (such as a discouted payoff) that depeds o a parameter
More informationLecture 4: Parameter Estimation and Confidence Intervals. GENOME 560 Doug Fowler, GS
Lecture 4: Parameter Estimatio ad Cofidece Itervals GENOME 560 Doug Fowler, GS (dfowler@uw.edu) 1 Review: Probability Distributios Discrete: Biomial distributio Hypergeometric distributio Poisso distributio
More informationpoint estimator a random variable (like P or X) whose values are used to estimate a population parameter
Estimatio We have oted that the pollig problem which attempts to estimate the proportio p of Successes i some populatio ad the measuremet problem which attempts to estimate the mea value µ of some quatity
More informationFINM6900 Finance Theory How Is Asymmetric Information Reflected in Asset Prices?
FINM6900 Fiace Theory How Is Asymmetric Iformatio Reflected i Asset Prices? February 3, 2012 Referece S. Grossma, O the Efficiecy of Competitive Stock Markets where Traders Have Diverse iformatio, Joural
More informationChapter 8. Confidence Interval Estimation. Copyright 2015, 2012, 2009 Pearson Education, Inc. Chapter 8, Slide 1
Chapter 8 Cofidece Iterval Estimatio Copyright 2015, 2012, 2009 Pearso Educatio, Ic. Chapter 8, Slide 1 Learig Objectives I this chapter, you lear: To costruct ad iterpret cofidece iterval estimates for
More informationStatistics for Economics & Business
Statistics for Ecoomics & Busiess Cofidece Iterval Estimatio Learig Objectives I this chapter, you lear: To costruct ad iterpret cofidece iterval estimates for the mea ad the proportio How to determie
More informationMonopoly vs. Competition in Light of Extraction Norms. Abstract
Moopoly vs. Competitio i Light of Extractio Norms By Arkadi Koziashvili, Shmuel Nitza ad Yossef Tobol Abstract This ote demostrates that whether the market is competitive or moopolistic eed ot be the result
More informationSELECTING THE NUMBER OF CHANGE-POINTS IN SEGMENTED LINE REGRESSION
1 SELECTING THE NUMBER OF CHANGE-POINTS IN SEGMENTED LINE REGRESSION Hyue-Ju Kim 1,, Bibig Yu 2, ad Eric J. Feuer 3 1 Syracuse Uiversity, 2 Natioal Istitute of Agig, ad 3 Natioal Cacer Istitute Supplemetary
More informationAn Empirical Study of the Behaviour of the Sample Kurtosis in Samples from Symmetric Stable Distributions
A Empirical Study of the Behaviour of the Sample Kurtosis i Samples from Symmetric Stable Distributios J. Marti va Zyl Departmet of Actuarial Sciece ad Mathematical Statistics, Uiversity of the Free State,
More informationThe Limit of a Sequence (Brief Summary) 1
The Limit of a Sequece (Brief Summary). Defiitio. A real umber L is a it of a sequece of real umbers if every ope iterval cotaiig L cotais all but a fiite umber of terms of the sequece. 2. Claim. A sequece
More informationA New Constructive Proof of Graham's Theorem and More New Classes of Functionally Complete Functions
A New Costructive Proof of Graham's Theorem ad More New Classes of Fuctioally Complete Fuctios Azhou Yag, Ph.D. Zhu-qi Lu, Ph.D. Abstract A -valued two-variable truth fuctio is called fuctioally complete,
More informationECON 5350 Class Notes Maximum Likelihood Estimation
ECON 5350 Class Notes Maximum Likelihood Estimatio 1 Maximum Likelihood Estimatio Example #1. Cosider the radom sample {X 1 = 0.5, X 2 = 2.0, X 3 = 10.0, X 4 = 1.5, X 5 = 7.0} geerated from a expoetial
More informationSolutions to Problem Sheet 1
Solutios to Problem Sheet ) Use Theorem.4 to prove that p log for all real x 3. This is a versio of Theorem.4 with the iteger N replaced by the real x. Hit Give x 3 let N = [x], the largest iteger x. The,
More informationx satisfying all regularity conditions. Then
AMS570.01 Practice Midterm Exam Sprig, 018 Name: ID: Sigature: Istructio: This is a close book exam. You are allowed oe-page 8x11 formula sheet (-sided). No cellphoe or calculator or computer is allowed.
More informationUnbiased estimators Estimators
19 Ubiased estimators I Chapter 17 we saw that a dataset ca be modeled as a realizatio of a radom sample from a probability distributio ad that quatities of iterest correspod to features of the model distributio.
More informationParametric Density Estimation: Maximum Likelihood Estimation
Parametric Desity stimatio: Maimum Likelihood stimatio C6 Today Itroductio to desity estimatio Maimum Likelihood stimatio Itroducto Bayesia Decisio Theory i previous lectures tells us how to desig a optimal
More informationSampling Distributions and Estimation
Cotets 40 Samplig Distributios ad Estimatio 40.1 Samplig Distributios 40. Iterval Estimatio for the Variace 13 Learig outcomes You will lear about the distributios which are created whe a populatio is
More informationResearch Article The Probability That a Measurement Falls within a Range of n Standard Deviations from an Estimate of the Mean
Iteratioal Scholarly Research Network ISRN Applied Mathematics Volume 0, Article ID 70806, 8 pages doi:0.540/0/70806 Research Article The Probability That a Measuremet Falls withi a Rage of Stadard Deviatios
More informationNOTES ON ESTIMATION AND CONFIDENCE INTERVALS. 1. Estimation
NOTES ON ESTIMATION AND CONFIDENCE INTERVALS MICHAEL N. KATEHAKIS 1. Estimatio Estimatio is a brach of statistics that deals with estimatig the values of parameters of a uderlyig distributio based o observed/empirical
More informationr i = a i + b i f b i = Cov[r i, f] The only parameters to be estimated for this model are a i 's, b i 's, σe 2 i
The iformatio required by the mea-variace approach is substatial whe the umber of assets is large; there are mea values, variaces, ad )/2 covariaces - a total of 2 + )/2 parameters. Sigle-factor model:
More informationMath 312, Intro. to Real Analysis: Homework #4 Solutions
Math 3, Itro. to Real Aalysis: Homework #4 Solutios Stephe G. Simpso Moday, March, 009 The assigmet cosists of Exercises 0.6, 0.8, 0.0,.,.3,.6,.0,.,. i the Ross textbook. Each problem couts 0 poits. 0.6.
More informationInferential Statistics and Probability a Holistic Approach. Inference Process. Inference Process. Chapter 8 Slides. Maurice Geraghty,
Iferetial Statistics ad Probability a Holistic Approach Chapter 8 Poit Estimatio ad Cofidece Itervals This Course Material by Maurice Geraghty is licesed uder a Creative Commos Attributio-ShareAlike 4.0
More informationFourier Transform in L p (R) Spaces, p 1
Ge. Math. Notes, Vol. 3, No., March 20, pp.4-25 ISSN 229-784; Copyright c ICSS Publicatio, 200 www.i-csrs.org Available free olie at http://www.gema.i Fourier Trasform i L p () Spaces, p Devedra Kumar
More information4.5 Generalized likelihood ratio test
4.5 Geeralized likelihood ratio test A assumptio that is used i the Athlete Biological Passport is that haemoglobi varies equally i all athletes. We wish to test this assumptio o a sample of k athletes.
More informationRandom Sequences Using the Divisor Pairs Function
Radom Sequeces Usig the Divisor Pairs Fuctio Subhash Kak Abstract. This paper ivestigates the radomess properties of a fuctio of the divisor pairs of a atural umber. This fuctio, the atecedets of which
More informationOnline appendices from Counterparty Risk and Credit Value Adjustment a continuing challenge for global financial markets by Jon Gregory
Olie appedices from Couterparty Risk ad Credit Value Adjustmet a APPENDIX 8A: Formulas for EE, PFE ad EPE for a ormal distributio Cosider a ormal distributio with mea (expected future value) ad stadard
More informationGame Theory. Lecture Notes By Y. Narahari. Department of Computer Science and Automation Indian Institute of Science Bangalore, India July 2012
Game Theory Lecture Notes By Y. Narahari Departmet of Computer Sciece ad Automatio Idia Istitute of Sciece Bagalore, Idia July 01 Chapter 4: Domiat Strategy Equilibria Note: This is a oly a draft versio,
More informationNORMALIZATION OF BEURLING GENERALIZED PRIMES WITH RIEMANN HYPOTHESIS
Aales Uiv. Sci. Budapest., Sect. Comp. 39 2013) 459 469 NORMALIZATION OF BEURLING GENERALIZED PRIMES WITH RIEMANN HYPOTHESIS We-Bi Zhag Chug Ma Pig) Guagzhou, People s Republic of Chia) Dedicated to Professor
More informationEXERCISE - BINOMIAL THEOREM
BINOMIAL THOEREM / EXERCISE - BINOMIAL THEOREM LEVEL I SUBJECTIVE QUESTIONS. Expad the followig expressios ad fid the umber of term i the expasio of the expressios. (a) (x + y) 99 (b) ( + a) 9 + ( a) 9
More information0.1 Valuation Formula:
0. Valuatio Formula: 0.. Case of Geeral Trees: q = er S S S 3 S q = er S S 4 S 5 S 4 q 3 = er S 3 S 6 S 7 S 6 Therefore, f (3) = e r [q 3 f (7) + ( q 3 ) f (6)] f () = e r [q f (5) + ( q ) f (4)] = f ()
More informationKernel Density Estimation. Let X be a random variable with continuous distribution F (x) and density f(x) = d
Kerel Desity Estimatio Let X be a radom variable wit cotiuous distributio F (x) ad desity f(x) = d dx F (x). Te goal is to estimate f(x). Wile F (x) ca be estimated by te EDF ˆF (x), we caot set ˆf(x)
More informationOnline appendices from The xva Challenge by Jon Gregory. APPENDIX 10A: Exposure and swaption analogy.
APPENDIX 10A: Exposure ad swaptio aalogy. Sorese ad Bollier (1994), effectively calculate the CVA of a swap positio ad show this ca be writte as: CVA swap = LGD V swaptio (t; t i, T) PD(t i 1, t i ). i=1
More informationExam 1 Spring 2015 Statistics for Applications 3/5/2015
8.443 Exam Sprig 05 Statistics for Applicatios 3/5/05. Log Normal Distributio: A radom variable X follows a Logormal(θ, σ ) distributio if l(x) follows a Normal(θ, σ ) distributio. For the ormal radom
More information1 Random Variables and Key Statistics
Review of Statistics 1 Radom Variables ad Key Statistics Radom Variable: A radom variable is a variable that takes o differet umerical values from a sample space determied by chace (probability distributio,
More informationStandard Deviations for Normal Sampling Distributions are: For proportions For means _
Sectio 9.2 Cofidece Itervals for Proportios We will lear to use a sample to say somethig about the world at large. This process (statistical iferece) is based o our uderstadig of samplig models, ad will
More informationEVEN NUMBERED EXERCISES IN CHAPTER 4
Joh Riley 7 July EVEN NUMBERED EXERCISES IN CHAPTER 4 SECTION 4 Exercise 4-: Cost Fuctio of a Cobb-Douglas firm What is the cost fuctio of a firm with a Cobb-Douglas productio fuctio? Rather tha miimie
More informationHopscotch and Explicit difference method for solving Black-Scholes PDE
Mälardale iversity Fiacial Egieerig Program Aalytical Fiace Semiar Report Hopscotch ad Explicit differece method for solvig Blac-Scholes PDE Istructor: Ja Röma Team members: A Gog HaiLog Zhao Hog Cui 0
More informationWe analyze the computational problem of estimating financial risk in a nested simulation. In this approach,
MANAGEMENT SCIENCE Vol. 57, No. 6, Jue 2011, pp. 1172 1194 iss 0025-1909 eiss 1526-5501 11 5706 1172 doi 10.1287/msc.1110.1330 2011 INFORMS Efficiet Risk Estimatio via Nested Sequetial Simulatio Mark Broadie
More informationModels of Asset Pricing
4 Appedix 1 to Chapter Models of Asset Pricig I this appedix, we first examie why diversificatio, the holdig of may risky assets i a portfolio, reduces the overall risk a ivestor faces. The we will see
More informationAY Term 2 Mock Examination
AY 206-7 Term 2 Mock Examiatio Date / Start Time Course Group Istructor 24 March 207 / 2 PM to 3:00 PM QF302 Ivestmet ad Fiacial Data Aalysis G Christopher Tig INSTRUCTIONS TO STUDENTS. This mock examiatio
More informationLimits of sequences. Contents 1. Introduction 2 2. Some notation for sequences The behaviour of infinite sequences 3
Limits of sequeces I this uit, we recall what is meat by a simple sequece, ad itroduce ifiite sequeces. We explai what it meas for two sequeces to be the same, ad what is meat by the -th term of a sequece.
More informationEstimating Proportions with Confidence
Aoucemets: Discussio today is review for midterm, o credit. You may atted more tha oe discussio sectio. Brig sheets of otes ad calculator to midterm. We will provide Scatro form. Homework: (Due Wed Chapter
More informationMixed and Implicit Schemes Implicit Schemes. Exercise: Verify that ρ is unimodular: ρ = 1.
Mixed ad Implicit Schemes 3..4 The leapfrog scheme is stable for the oscillatio equatio ad ustable for the frictio equatio. The Euler forward scheme is stable for the frictio equatio but ustable for the
More informationLecture 4: Probability (continued)
Lecture 4: Probability (cotiued) Desity Curves We ve defied probabilities for discrete variables (such as coi tossig). Probabilities for cotiuous or measuremet variables also are evaluated usig relative
More informationBinomial Model. Stock Price Dynamics. The Key Idea Riskless Hedge
Biomial Model Stock Price Dyamics The value of a optio at maturity depeds o the price of the uderlyig stock at maturity. The value of the optio today depeds o the expected value of the optio at maturity
More informationTopic 14: Maximum Likelihood Estimation
Toic 4: November, 009 As before, we begi with a samle X = (X,, X of radom variables chose accordig to oe of a family of robabilities P θ I additio, f(x θ, x = (x,, x will be used to deote the desity fuctio
More informationA random variable is a variable whose value is a numerical outcome of a random phenomenon.
The Practice of Statistics, d ed ates, Moore, ad Stares Itroductio We are ofte more iterested i the umber of times a give outcome ca occur tha i the possible outcomes themselves For example, if we toss
More informationThe Valuation of the Catastrophe Equity Puts with Jump Risks
The Valuatio of the Catastrophe Equity Puts with Jump Risks Shih-Kuei Li Natioal Uiversity of Kaohsiug Joit work with Chia-Chie Chag Outlie Catastrophe Isurace Products Literatures ad Motivatios Jump Risk
More informationSUPPLEMENTAL MATERIAL
A SULEMENTAL MATERIAL Theorem (Expert pseudo-regret upper boud. Let us cosider a istace of the I-SG problem ad apply the FL algorithm, where each possible profile A is a expert ad receives, at roud, a
More information. (The calculated sample mean is symbolized by x.)
Stat 40, sectio 5.4 The Cetral Limit Theorem otes by Tim Pilachowski If you have t doe it yet, go to the Stat 40 page ad dowload the hadout 5.4 supplemet Cetral Limit Theorem. The homework (both practice
More informationCalculation of the Annual Equivalent Rate (AER)
Appedix to Code of Coduct for the Advertisig of Iterest Bearig Accouts. (31/1/0) Calculatio of the Aual Equivalet Rate (AER) a) The most geeral case of the calculatio is the rate of iterest which, if applied
More informationChapter 8: Estimation of Mean & Proportion. Introduction
Chapter 8: Estimatio of Mea & Proportio 8.1 Estimatio, Poit Estimate, ad Iterval Estimate 8.2 Estimatio of a Populatio Mea: σ Kow 8.3 Estimatio of a Populatio Mea: σ Not Kow 8.4 Estimatio of a Populatio
More informationModels of Asset Pricing
APPENDIX 1 TO CHAPTER4 Models of Asset Pricig I this appedix, we first examie why diversificatio, the holdig of may risky assets i a portfolio, reduces the overall risk a ivestor faces. The we will see
More informationEstimating Forward Looking Distribution with the Ross Recovery Theorem
roceedigs of the Asia acific Idustrial Egieerig & Maagemet Systems Coferece 5 Estimatig Forward Lookig Distributio with the Ross Recovery Theorem Takuya Kiriu Graduate School of Sciece ad Techology Keio
More informationCHAPTER 2 PRICING OF BONDS
CHAPTER 2 PRICING OF BONDS CHAPTER SUARY This chapter will focus o the time value of moey ad how to calculate the price of a bod. Whe pricig a bod it is ecessary to estimate the expected cash flows ad
More informationThe material in this chapter is motivated by Experiment 9.
Chapter 5 Optimal Auctios The material i this chapter is motivated by Experimet 9. We wish to aalyze the decisio of a seller who sets a reserve price whe auctioig off a item to a group of bidders. We begi
More informationStochastic Processes and their Applications in Financial Pricing
Stochastic Processes ad their Applicatios i Fiacial Pricig Adrew Shi Jue 3, 1 Cotets 1 Itroductio Termiology.1 Fiacial.............................................. Stochastics............................................
More informationEstimation of Parameters of Three Parameter Esscher Transformed Laplace Distribution
Iteratioal Joural of Statistics ad Systems ISSN 0973-675 Volume 1, Number (017), pp. 669-675 Research Idia Publicatios http://www.ripublicatio.com Estimatio of Parameters of Three Parameter Esscher Trasformed
More informationConsistent non-parametric Bayesian estimation for a time-inhomogeneous Brownian motion Gugushvili, S.; Spreij, P.J.C.
UvA-DARE Digital Academic Repository) Cosistet o-parametric Bayesia estimatio for a time-ihomogeeous Browia motio Gugushvili, S.; Spreij, P.J.C. Published i: ESAIM-Probability ad Statistics DOI:.5/ps/2339
More informationMinhyun Yoo, Darae Jeong, Seungsuk Seo, and Junseok Kim
Hoam Mathematical J. 37 (15), No. 4, pp. 441 455 http://dx.doi.org/1.5831/hmj.15.37.4.441 A COMPARISON STUDY OF EXPLICIT AND IMPLICIT NUMERICAL METHODS FOR THE EQUITY-LINKED SECURITIES Mihyu Yoo, Darae
More informationModels of Asset Pricing
APPENDIX 1 TO CHAPTER 4 Models of Asset Pricig I this appedix, we first examie why diversificatio, the holdig of may risky assets i a portfolio, reduces the overall risk a ivestor faces. The we will see
More informationMonetary Economics: Problem Set #5 Solutions
Moetary Ecoomics oblem Set #5 Moetary Ecoomics: oblem Set #5 Solutios This problem set is marked out of 1 poits. The weight give to each part is idicated below. Please cotact me asap if you have ay questios.
More informationii. Interval estimation:
1 Types of estimatio: i. Poit estimatio: Example (1) Cosider the sample observatios 17,3,5,1,18,6,16,10 X 8 X i i1 8 17 3 5 118 6 16 10 8 116 8 14.5 14.5 is a poit estimate for usig the estimator X ad
More informationAnomaly Correction by Optimal Trading Frequency
Aomaly Correctio by Optimal Tradig Frequecy Yiqiao Yi Columbia Uiversity September 9, 206 Abstract Uder the assumptio that security prices follow radom walk, we look at price versus differet movig averages.
More informationToday: Finish Chapter 9 (Sections 9.6 to 9.8 and 9.9 Lesson 3)
Today: Fiish Chapter 9 (Sectios 9.6 to 9.8 ad 9.9 Lesso 3) ANNOUNCEMENTS: Quiz #7 begis after class today, eds Moday at 3pm. Quiz #8 will begi ext Friday ad ed at 10am Moday (day of fial). There will be
More informationResearch Paper Number From Discrete to Continuous Time Finance: Weak Convergence of the Financial Gain Process
Research Paper Number 197 From Discrete to Cotiuous Time Fiace: Weak Covergece of the Fiacial Gai Process Darrell Duffie ad Philip Protter November, 1988 Revised: September, 1991 Forthcomig: Mathematical
More information1. Suppose X is a variable that follows the normal distribution with known standard deviation σ = 0.3 but unknown mean µ.
Chapter 9 Exercises Suppose X is a variable that follows the ormal distributio with kow stadard deviatio σ = 03 but ukow mea µ (a) Costruct a 95% cofidece iterval for µ if a radom sample of = 6 observatios
More informationMoving frame and integrable system of the discrete centroaffine curves in R 3
Movig frame ad itegrable system of the discrete cetroaffie curves i R 3 Yu Yag, Yahua Yu Departmet of Mathematics, Northeaster Uiversity, Sheyag 0004, P R Chia arxiv:6006530v2 [mathdg] 27 Nov 206 Abstract
More informationAMS Portfolio Theory and Capital Markets
AMS 69.0 - Portfolio Theory ad Capital Markets I Class 6 - Asset yamics Robert J. Frey Research Professor Stoy Brook iversity, Applied Mathematics ad Statistics frey@ams.suysb.edu http://www.ams.suysb.edu/~frey/
More informationSummary. Recap. Last Lecture. .1 If you know MLE of θ, can you also know MLE of τ(θ) for any function τ?
Last Lecture Biostatistics 60 - Statistical Iferece Lecture Cramer-Rao Theorem Hyu Mi Kag February 9th, 03 If you kow MLE of, ca you also kow MLE of τ() for ay fuctio τ? What are plausible ways to compare
More informationDESCRIPTION OF MATHEMATICAL MODELS USED IN RATING ACTIVITIES
July 2014, Frakfurt am Mai. DESCRIPTION OF MATHEMATICAL MODELS USED IN RATING ACTIVITIES This documet outlies priciples ad key assumptios uderlyig the ratig models ad methodologies of Ratig-Agetur Expert
More informationCAPITAL ASSET PRICING MODEL
CAPITAL ASSET PRICING MODEL RETURN. Retur i respect of a observatio is give by the followig formula R = (P P 0 ) + D P 0 Where R = Retur from the ivestmet durig this period P 0 = Curret market price P
More informationDepartment of Mathematics, S.R.K.R. Engineering College, Bhimavaram, A.P., India 2
Skewess Corrected Cotrol charts for two Iverted Models R. Subba Rao* 1, Pushpa Latha Mamidi 2, M.S. Ravi Kumar 3 1 Departmet of Mathematics, S.R.K.R. Egieerig College, Bhimavaram, A.P., Idia 2 Departmet
More informationAppendix 1 to Chapter 5
Appedix 1 to Chapter 5 Models of Asset Pricig I Chapter 4, we saw that the retur o a asset (such as a bod) measures how much we gai from holdig that asset. Whe we make a decisio to buy a asset, we are
More informationDiscriminating Between The Log-normal and Gamma Distributions
Discrimiatig Betwee The Log-ormal ad Gamma Distributios Debasis Kudu & Aubhav Maglick Abstract For a give data set the problem of selectig either log-ormal or gamma distributio with ukow shape ad scale
More informationSubject CT5 Contingencies Core Technical. Syllabus. for the 2011 Examinations. The Faculty of Actuaries and Institute of Actuaries.
Subject CT5 Cotigecies Core Techical Syllabus for the 2011 Examiatios 1 Jue 2010 The Faculty of Actuaries ad Istitute of Actuaries Aim The aim of the Cotigecies subject is to provide a groudig i the mathematical
More informationThese characteristics are expressed in terms of statistical properties which are estimated from the sample data.
0. Key Statistical Measures of Data Four pricipal features which characterize a set of observatios o a radom variable are: (i) the cetral tedecy or the value aroud which all other values are buched, (ii)
More information43. A 000 par value 5-year bod with 8.0% semiaual coupos was bought to yield 7.5% covertible semiaually. Determie the amout of premium amortized i the 6 th coupo paymet. (A).00 (B).08 (C).5 (D).5 (E).34
More informationAverage Distance and Vertex-Connectivity
Average Distace ad Vertex-Coectivity Peter Dakelma, Simo Mukwembi, Heda C. Swart School of Mathematical Scieces Uiversity of KwaZulu-Natal, Durba, 4041 South Africa March 17, 013 Abstract The average distace
More informationof Asset Pricing R e = expected return
Appedix 1 to Chapter 5 Models of Asset Pricig EXPECTED RETURN I Chapter 4, we saw that the retur o a asset (such as a bod) measures how much we gai from holdig that asset. Whe we make a decisio to buy
More informationCAPITAL PROJECT SCREENING AND SELECTION
CAPITAL PROJECT SCREEIG AD SELECTIO Before studyig the three measures of ivestmet attractiveess, we will review a simple method that is commoly used to scree capital ivestmets. Oe of the primary cocers
More informationCAUCHY'S FORMULA AND EIGENVAULES (PRINCIPAL STRESSES) IN 3-D
GG303 Lecture 19 11/5/0 1 CAUCHY'S FRMULA AN EIGENVAULES (PRINCIPAL STRESSES) IN 3- I II Mai Topics A Cauchy s formula Pricipal stresses (eigevectors ad eigevalues) Cauchy's formula A Relates tractio vector
More informationWe learned: $100 cash today is preferred over $100 a year from now
Recap from Last Week Time Value of Moey We leared: $ cash today is preferred over $ a year from ow there is time value of moey i the form of willigess of baks, busiesses, ad people to pay iterest for its
More informationSTAT 135 Solutions to Homework 3: 30 points
STAT 35 Solutios to Homework 3: 30 poits Sprig 205 The objective of this Problem Set is to study the Stei Pheomeo 955. Suppose that θ θ, θ 2,..., θ cosists of ukow parameters, with 3. We wish to estimate
More informationInstitute of Actuaries of India Subject CT5 General Insurance, Life and Health Contingencies
Istitute of Actuaries of Idia Subject CT5 Geeral Isurace, Life ad Health Cotigecies For 2017 Examiatios Aim The aim of the Cotigecies subject is to provide a groudig i the mathematical techiques which
More informationLecture 5: Sampling Distribution
Lecture 5: Samplig Distributio Readigs: Sectios 5.5, 5.6 Itroductio Parameter: describes populatio Statistic: describes the sample; samplig variability Samplig distributio of a statistic: A probability
More informationBootstrapping high-frequency jump tests
Bootstrappig high-frequecy jump tests Prosper Dovoo Departmet of Ecoomics, Cocordia Uiversity Sílvia Goçalves Departmet of Ecoomics, Uiversity of Wester Otario Ulrich Houyo CREATES, Departmet of Ecoomics
More information