STAT 330(Winter ) Mathematical Statistics

Μέγεθος: px
Εμφάνιση ξεκινά από τη σελίδα:

Download "STAT 330(Winter ) Mathematical Statistics"

Transcript

1 Sprig 3 TABLE OF CONTENTS STAT 33Witer 3-35 Mathematical Statistics Prof. M. Molkaraie Uiversity of Waterloo L A TEXer: W. KONG Last Revisio: April 3, 4 Table of Cotets Review. Probability Spaces Raom Variables The Gamma Fuctio Expectatio a Variace 4. Expectatio Variace Momet Geeratig Fuctios MGFs 6 3. Liear Combiatios Characteristic Fuctio Joit Distributios 8 4. Joit Expectatio a Variace Correlatio Coefficiet Coitioal Distributios 5. Coitioal Expectatio Multivariable Distributios 3 6. Multiomial Distributio Bivariate Normal Distributio Fuctios of Raom Variables to- Bivariate Trasformatios Momet-Geeratig Fuctio Metho Covergece of Raom Variables 8 8. Useful Limit Theorems Delta Metho Poit Estimatio 9. Metho of Momets Maximum Likelihoo Estimatio Notable Fuctios a Matrices Covex Fuctios These otes are curretly a work i progress, a as such may be icomplete or cotai errors. i

2 Sprig 3 ACKNOWLEDGMENTS ACKNOWLEDGMENTS: Special thaks to Michael Baker a his L A TEX formatte otes. They were the ispiratio for the structure of these otes. ii

3 Sprig 3 ABSTRACT Abstract The purpose of these otes is to provie a secoary referece for the material covere i STAT 33. Reaers shoul ote that early /3 of the class is spet reviewig cocepts leare i STAT 3/3 but later material ca prove to be sigificatly more ifficult. The author recommes that stuets who eroll i this shoul have a very goo backgrou i calculus as that is the core of the computatios oe i this course. iii

4 Sprig 3 REVIEW Overview Review Joit, Margial, a Coitioal Distributios 3 Fuctios of RVs 4 Covergece i P & i D 5 Poit Estimatio a Maximum Likelihoo 6 Hypothesis Testig Recommee Reaigs: - Itro to Probability a Mathematical Statistics Bai & Eglehart - Statistical Iferece Casella & Berger Test o Jue th Test o July 7th Review We briefly go over some basic cocepts itrouce i STAT 3 a STAT 3. Probability Spaces Defiitio.. Recall that a probability space is compose of a set S, calle the sample space or the set of all possible outcomes also sometimes give by Ω where E S is calle a evet, a sigma algebra Σ, geerate by S, a a probability fuctio P : Σ R where is usually. Axiom. Here are the properties of the probability fuctio Kolmogorov Axioms: P A, A S P S 3 If A A i are isjoit a I is coutable the P A P A i i I i I Note that 3 is also kow as σ aitivity. Defiitio.. We efie the coitioal probability P A B P A B P B iepeet or A B if P A P A B P A B P AP B. where P B, a we say that A a B are Note. Iepeece Disjoit. Raom Variables Defiitio.3. A raom variable is a fuctio X : S R with the followig properties a otatios: X x} w : w S, Xw x} P X x} P w : w S, Xw x} F X x where the seco form F X : R EXT [, ], is kow as the cf or cumulative istributio fuctio.

5 Sprig 3 REVIEW Propositio.. The cf has the followig properties: F is o-ecreasig F X F X.5 x < x F X x F X x 3 F X is right cotiuous 4 P a < X b P X b P X a F X b F X a, for a < b 5 P X b F X b lim x b F Xx, equal to if X is cotiuous Example.. Cosier T x e x, x R. By observatio it satisfies,, a 3. To check, ote that T x x e x + e x > Defiitio.4. For iscrete raom variables, say X, i aitio to a cf, we efie a probability mass fuctio, calle a pmf: Propositio.. Here are some properties of the pmf: f X x P X x f X x P X X x P X x k P X k Example.. Here is a small list of some iscrete istributios: Uiform [U ifa, b], Geometric [Geop], Poisso [P oissoλ], Biomial [Bi, p] Example.3. Suppose we have a re balls a b black balls a Let X the # of re balls i selectios without replacemet x a+b The PMF is Hyper-Geometric P X x a x b b Let X the # of re balls i selectios with replacemet a The PMF is Bi, a+b. Asie. m+ r r m k k k k k Calle the Vaermoe ietity Example.4. Suppose f X x p x l p. We will show that x N f X x it is clearly o-egative. Observe that x p x x l p l p p x x x a sice we have x l x p x x l p x, x < l p l p

6 Sprig 3 REVIEW Defiitio.5. For cotiuous raom variables, istea of a pmf P X X k we have a pf f X x calle a probability esity fuctio. Cotiuous raom variables still have a cf, eote by F X x P X x. Cotiuous raom variables also have the followig properties: f X x fx x 3 F X x x f Xt t Defiitio.6. The uiform istributio X Uiform[a, b] has cf x x a F X x a b a x x a b a a < x b x > b Example.5. Cosier the pf This is a vali pf provie that f X x θ x θ+ x x < f X x x θ θ θ θ >.3 The Gamma Fuctio Defiitio.7. The gamma fuctio Γα is efie by a has the followig properties. Γα α Γα Γ!, N 3 Γ π Γα y α e y y y α e y y y Defiitio.8. The gamma istributio X Gammaα, β is efie usig the pf f X x xα e x β, x, α >, β > Γαβα 3

7 Sprig 3 EXPECTATION AND VARIANCE a ote that I x α e x β Γαβ α x Γαβ α x α e x β x Γαβ α β α y α e y βy β α Γαβ α Γα Γα y α e y y with x β y x βy βy x. So the gamma istributio is a vali istributio. Defiitio.9. The Weibull istributio X Weibullθ, β is give by the pf f X x β θ β xβ e x θ β β x β θ β xβ exp, x >, θ >, β > θ a ote that for β, we have a Expoetialθ istributio. To see that it is a vali pf, observe that I f X xx β θ β xβ e x θ β x e y y usig y x β θ y βx β x. Suppose that θ. The θ β f X x βx β e xβ, F X x e xβ, x Expectatio a Variace We briefly go over the efiitios a properties of expectatio a variace.. Expectatio Defiitio.. The expectatio of a raom variable X eote as E[X], EX, EX, µ X or µ is efie as EX x Z xp X x i the iscrete case a EX xf X xx for the cotiuous case. We will illustrate examples a properties of expectatio i the cotiuous case from this poit forwar. For geeral fuctios of raom variables, gx, we have EgX 4 gxf X xx

8 Sprig 3 EXPECTATION AND VARIANCE a for joit expectatios EXY we have EXY xyf XY x, yxy Summary. Some properties of expectatio are as follows. Liearity of Expectatio: Ea gx + b gy aex + bey eve if X is epeet o Y X Y EXY EXEY. Variace Defiitio.. We efie the variace of a raom variable X as E[X E[X] ] E[X ] E [X] EX µ X which usually eote as V arx, σ X or σ. Note that EX EX a these are equal whe X is a costat. Defiitio.3. We efie the followig momets arou X k th momet: E[X k ] k th momet arou the mea cetral momet: E [X µ k] 3 k th factorial momet: E [ x k] E[XX...X k + ] Example.. Suppose that X N,, the EX k+, k N sice the itegra is the prouct of a symmetric eve a atisymmetric o fuctio. Summary. Here are some properties of the variace fuctio. V arax + b a V arx V arax + by a V arx + b V arx + abcovx, Y Example.. If X P oisθ the E [ X k] θ k. To see this, we use the efiitio below. usig this result, we ca euce that [ E x k] E[XX...X k + ] e θ x< e θ k x< e θ x< e θ y< θ k e θ θ k y< x k θ k x! x k θ k x! θ k x kx k... θ k y!, y x k EX θ, EXX θ EX EX V arx θ y! 5

9 Sprig 3 3 MOMENT GENERATING FUNCTIONS MGFS Example.3. If X Gammaα, β the E[X p ] β p Γα+p Γα a to see this, we use the efiitio agai E[X p ] β p Γα x p xα e x β Γαβ α x x α+p e x β Γαβ α x y α+p β α+p Γαβ α e y βy, y x β y α+p β p e y y Γα β p Γα + p Γα y α+p e y y We the use this to get E[X] βα a E[X ] β αα with V arx β α. Note that if we kow E[X] a V ar[x], we ca solve for α a β. 3 Momet Geeratig Fuctios MGFs Defiitio 3.. A momet geeratig fuctio of X is create by the followig mappig Example 3.. Let X Bi, p. The E [ e tx] e tx p x p x x x X M X t E [ e tx] M X t x e t p x p x [ pe t + p ] x Example 3.. If X P oisθ the M X t e θet. To see this, we go by efiitio. E [ e tx] x< e tx e θ θ x x! e θ e t θ x x! x< e θ e θet e θet As a sie remark ote that if X Bi, p a, p with p θ the X P oisθ. We also shoul get that their momet geeratig fuctios shoul coverge. Example 3.3. If X Gammaα, β the M X t βt α. To see this, we also go by efiitio M X t E [ e tx] e tx xα e x β Γαβ α x Γαβ α x α e x t β x Γαβ α y α β α β t α β t α e y y α e y y Γα β α β t α βt α y, y β t β t x 6

10 Sprig 3 3 MOMENT GENERATING FUNCTIONS MGFS Example 3.4. Suppose that Z N,. The M Z t e t. As above, we go by efiitio. M Z t e tx π e x x π e x t e t x e t π e x t x e t 3. Liear Combiatios Propositio 3.. Give the MGF of X, we ca compute the MGF of ay liear combiatio of X, say Y ax + b. Proof. We ca o this irectly. M Y t E [ e Y t] [ E e ax+bt] e bt M X at Corollary 3.. If Y Nµ, σ, what is M Y t? Well if X N,, the Y µ + σx. Hece M Y t e µt e σ t e tµ+σ t Summary 3. Recall that Here are some properties of the MGF: M X e tx tx k k! k E [ e tx] k t k k! E [ x k] M X t k ktk k! E [ x k] M X E[X] 3 M X t kk t k k k! E [ x k] M X E[X ] 4 Iuctively, we ca get M X E[X ] 5 M X M Y F X F Y oly i this course; geerally this is ot true 6 If Y X i, the M Y t M X i t Example 3.5. If X Gammaα, β the M Xt αβ βt α E[X] M X αβ M Xt αβα + β βt α E[X ] M X αβ α + V ar[x] αβ α + α β αβ Example 3.6. Suppose that M X t. Fi the MGF of Y X a E[Y ], V ar[y ]. What is the istributio of Y? By observatio, M Y t e t e 4t, E[Y ], V ar[y ] 4 a the istributio of Y is N, 4. 7

11 Sprig 3 4 JOINT DISTRIBUTIONS 3. Characteristic Fuctio Defiitio 3.. The characteristic fuctio of a raom variable X is the Fourier trasform of the pf/pmf: I ω X x e iωx f X xx, e iωx where it always exists a has all of the properties of the MGF. 4 Joit Distributios Example 4.. Cosier rollig two ice, D a D. Let X D + D a Y D D. The P XY X 5, Y 3 P X 5, Y a P X 7, Y 4 4 y P X 7, Y y Summary 4. Here are some basic properties of the margials of a joit istributio i the iscrete case: F F X x P X x lim y F xy x, y F xy x, x y f xyx, y 3 P X X x y P X x, Y y, P Y Y y x P X x, Y y a ow i the cotiuous case: f XY x, y x y F XY x, y x F XY x, y y f XY s, t s t 3 f Y y f XY s, t s, f X x f XY s, t t Example 4.. Suppose that we have ActSc stuets, 9 Stats stuet a 6 Maths stuets. We select 5 stuets without replacemet. Let X # of ActSc stuets a Y # of Stats stuets. The joit PMF of X a Y is the margial of X is P X X x P XY X x, Y y y 9 x y x y 9 6 x y 5 x y 5 5 x, x, y, x + y y 9 6 y 5 x y 5 x 5 x 5 5 a similarly the margial of Y is P Y Y y x 9 x y x y y 5 5 x 6 x 5 x y 9 6 y 5 y 5 5 8

12 Sprig 3 4 JOINT DISTRIBUTIONS Example 4.3. Let Let s check if f XY x, y. I x + y x y Let s try to compute P X 3, Y. I 3 x + y x y y y f XY y y x x + y x, y otherwise x + xy y + xy 3 y y y y y y + y + 3 y + y Note that the cf of this pf is x, y xy F X,Y x, y x + y x, y x, y I the lecture here, we reviewe how to itegrate over arbitrary regios so I will oly give the importat etails Summary 5. If we are aske to compute P fx, Y < c for some costat c a raom variables r.v.s X a Y, isolate Y, raw the regio of itegratio a erive the appropriate itegrals. For example, if x, y, the a P r X + Y < P r Y < X x x y f XY x, y y x P r XY P r Y P Y > f XY x, y y x X X x y x where i the seco example, x y a y x. If X Y the f XY x, yx, y f X xf Y yx, y A A Exercise 4.. Give f XY ke y y, a < x < y <, What is k? As: k What is P X 3, Y 3? As: e 3 e e 3 What is P X < Y? As: 3 What is P X + Y? Hit: P X + Y P X + Y <, As: e 4 Are X a Y iepeet? As: No! Check the margials. Defiitio 4.. We efie the support of a r.v. as x : f X x > }. Propositio 4.. If X Y the gx hy for ay fuctios g a h. Example 4.4. Repeat of a previous example Suppose that we have ActSc stuets, 9 Stats stuet a 6 Maths stuets. We select 5 stuets without replacemet. Let X # of ActSc stuets a Y # of Stats stuets. Are X a Y iepeet? No, they re epeet Example 4.5. Let f XY x, y 3 y x for x, y. Are X a Y iepeet? Yes, check the margials 9

13 Sprig 3 4 JOINT DISTRIBUTIONS Example 4.6. Let f XY x, y θx+y e θ x!y!. This splits ito two iepeet poisso r.v.s. X a Y. Example 4.7. Let f XY x, y π where x y a y. Calculatig the margials gives us f Y y π y a f X x 4 π x. It is clear that X is ot iepeet of Y. Remark 4.. I geeral, X X... X are iepeet if a oly if f XX...X x, x,..., x f Xi x i Remark 4.. Give f XY Z x, y, z gx, yhy, z, we remark that X Z if Y is give. 4. Joit Expectatio a Variace Propositio 4.. If X X... X, the for ay set of equatios h i }. E [h i X i ] E [h i X i ] Defiitio 4.. Defie CovX, Y E[XY ] E[X]E[Y ] E[XY ] µ X µ Y. If X Y the CovX, Y. We also say that if E[XY ] E[X]E[Y ] the X a Y are ucorrelate. However, if for all fuctios f, g we have that the X Y. E[fXgY ] E[fX]E[gY ] Propositio 4.3. Suppose that X is ucorrelate to Y a that Y αx E[αX ] αe[x]e[x] E[X ] E[X] X is a costat so X a Y caot be liearly epeet still caot say that they are iepeet. Propositio 4.4. If X X... X the [ ] V ar a i X i a i V ar[x i ] a i σx i 4. Correlatio Coefficiet Defiitio 4.3. The correlatio coefficiet ρ for two r.v.s is efie as ρ XY CovX, Y σ X σ Y, ρ XY Example 4.8. Recall the pf f XY x, y x + y o x, y a otherwise. We showe that the margials were f X x x +, f Y y y + for x, y a otherwise. It ca be show that E[XY ] 3, E[X] 7 E[Y ], V arx V ary 44 σ X σ Y a so ρ Propositio 4.5. ρ XY for ay r.v.s X a Y.

14 Sprig 3 5 CONDITIONAL DISTRIBUTIONS Proof. Cosier [ X µx E a so CovX,Y σ X σ Y. σ X + Y µ Y σ Y ] [ σx E X µ X ] + [ σy E Y µ Y ] + E[X µ X Y µ Y ] σ X σ Y σ X σx + σ Y σy + CovX, Y σ X σ Y [ ]. A similar metho ca be costructe usig E X µx σ X Y µ Y σ Y i the above to get CovX,Y σ X σ Y 5 Coitioal Distributios Defiitio 5.. For r.v.s X a Y, f X Y x y f XY x, y, p X Y x y p XY x, y a f Y, p Y > f Y y p Y y Example 5.. Cosier f XY x, y π o y, x y a otherwise. We compute the margials to be f X x 4 π x a f Y x π y. It is easy to show that f X Y x y y, f Y Xy x Remark 5.. Prouct Rule We ca express the joit i the followig way x f XY x, y f X Y x y f Y y f Y X y x f X x Example 5.. Suppose that Y P oisµ a X Y y Biy, p. What is the margial of X? The joit istributio is p XY x, y e µ µ y [ ] y! y! x!y x! px p y x e µ µp x µ p y x x!y x! so a X P oisµp. P Hp X x e µ µp x µ p y x yx e µ x! µpx x!y x! yx e µ e µ p µp x x! e µp µp x x! µ p y x y x! Example 5.3. Give P XY x, y θx+y e θ x!y! for x, y,,,... It ca be show that P X x P XY x, y θx e θ, P Y X y x θy e θ x! y! y

15 Sprig 3 5 CONDITIONAL DISTRIBUTIONS Example 5.4. Suppose that Y Gamma α, θ a X Y y Weiy p, p. What is fx? We kow that It ca be show that f Y y Gammaα, β xα e x β β α Γα, Weiθ, β β θ β xβ e x β θ, x θα Γα yα e θy, f X Y x y This gives a equatio for f XY i the form of a itegratig gives us f X x p y p p x p e x y p p f XY x, y pyθα Γα xp y α e θy e yx P f XY x, y y pθ α x p Γαθ + x p α+ t α e t t, t yθ + x p Γα + pθα x p Γαθ + x p α+ pyx p e yxp, x, y 5. Coitioal Expectatio Defiitio 5.. E[gY x] y gyf XY y x E[gY X x] a if X Y the E[gY X x] E[gY ]. Variace is efie i a similar way: V ar[y X x] E[Y X x] E [Y X x]. Example 5.5. Let f Y X y x x, x y x. We wat to compute the variace. First, E[Y X x] sice the term i the itegral is a o fuctio. The, E[Y X x] So V ar[y X x] 3 x. x x x y x x y x Propositio 5.. The ouble expectatio formula states y x y x y y x 3 3 x 3 x E[X] E E[X Y ] V ar[x] E[V arx Y ] + V are[x Y Example 5.6. If P Uif[, ] a Y P p Bi, p the E[E[Y P ]] E[P ] E[P ] 5 a V ar[e[y P ] V ar[p ] Some examples we skip here because they are trivial

16 Sprig 3 6 MULTIVARIABLE DISTRIBUTIONS Example 5.7. Give f XY 6xy x y < x, y < otherwise we ca show that E[XY ] 3, f X Y 6x x y 4 3y with f Y y4 3y, < y < Defiitio 5.3. The joit MGF of XY is efie as a i geeral, with Propositio 5.. As y, F XY x, y F X x. Example 5.8. Give we ca show that M XY t E [ e tx+ty ] M k Xit,.., t k E [e ] k l txi M k Xit, t,..., t k E [ e tx] M X t f XY M XY t, t e y < x < y < otherwise Propositio 5.3. If X k } are a set of iepeet raom variables, t + t t M X k t,..., t M Xk t k Exercise 5.. Show that if X,..., X are ii N, r.v.s, the Y X N,. First remark that V ary V ar [ X ]. We ca further calculate the MGF of Y as a so Y X N,. M Y t ] E [e x t e t e t t e Theorem 5.. If Y,..., Y N, a they are iepeet, the Ȳ µ σ / N, 6 Multivariable Distributios Here, we examie various istributios that comprise of multiple variables. 6. Multiomial Distributio Defiitio 6.. Let X i be the umber of times i comes before total repetitios, a p i be the probability of gettig the item i. The! P X x,..., X k x k x!...x k! px... px k k where x i, p i. We say that X,..., X k Mult, p,..., p k. 3

17 Sprig 3 6 MULTIVARIABLE DISTRIBUTIONS Propositio. Some properties iclue:. M X t p e t p t k k. CovX i, X j p i p j + p k+ 6. Bivariate Normal Distributio Defiitio 6.. If X a X have the followig joit PDF: f XX x, x exp } π Σ / x µt Σ x µ, x x µ σ, µ, Σ ρσ σ x µ ρσ σ σ the X X, X t BivNµ, Σ. Note that the matrix Σ must be positive efiite. Remark 6.. If ρ the f XX exp πσ σ σ σ x µ σ e πσ }} Nµ,σ x µ x µ t σ x µ σ e πσ }} Nµ,σ σ x µ x µ } So X a X are iepeet. This is special to oly the bivariate ormal r.v. Note. I geeral, if X Nµ, σ a X Nµ, σ the if ρ XX it is ot always true that X X. This is oly the case if X a X, collectively, are bivariate ormal. Summary 6. Here are some values that may be useful i the computatio of f X,X : a so f X,X x, x Σ σ σ ρ, Σ / σ σ ρ Σ σ σ ρ πσ σ exp ρ σ σ ρ [ πσ σ exp x µ ρ ρ σ ρσ σ ρσ σ σ [ x µ σ x µ x µ ρσ σ + x µ σ ] } σ + x µ σ ρx ]} µ x µ σ σ Fact 6.. The momet geeratig fuctio is M X t, t E where X Nµ, σ, X Nµ, σ a [ e tt X ] E [ e tx+tx]... e µt t+ tt Σt M X M X t,, M X M X, t Propositio 6.. If C C C t the C t X NC t µ, C t ΣC a Y AX + b Y NAµ + b, AΣA t. Remark 6.. For a coitio istributio X X x with X, X beig joitly bivariate, we have X X x Nµ + ρ σ σ x µ, σ ρ This ca be oe by puttig the joit over of the margial of X. For the sake of saity, I will ot be bashig through the computatio of this. 4

18 Sprig 3 7 FUNCTIONS OF RANDOM VARIABLES Fact 6.. E[X X ] E[E[X X X ]] Example 6.. Suppose that X X are BIV µ, Σ. The a so E[X X X ] X µ + ρ σ σ X µ. Thus, E[X X X x ] x E[X X x ] x µ + ρ σ σ x µ E[X X ] E[E[X X X ]] E[X ]µ + ρ σ σ E[X ] µ µ µ + ρσ σ a so we ca represet the covariace of X a X as CovX, X µ µ + ρσ σ µ µ ρσ σ 7 Fuctios of Raom Variables Example 7.. Suppose that X Z a f Z z π e z /. Remark that So takig erivatives, we have a ote that X Gam,. F X x P X x P Z x P x Z x F Z x F Z x Fact 7.. If Z,..., Z are iepeet N, the f X x x f Zx / πx / e x/ X Z Z χ a E[X]. Example 7.. Suppose that f XY 3y 3y x y otherwise Fi the pf of T XY. Now sice P T t P XY < t P XY > t the we calculate P XY > t as P XY > t y t t y 3y x y + t t 3t What is the pf of T? By irect computatio, this is What is the pf of S Y X. Well, the cf is F S s f T 3 3t, t y y s 3y x y s a so the pf is s F Ss f S s s Example 7.3. Suppose that X,..., X are ii with pf f X a cf F X. Let Y maxx,.., X a T mix,.., X. So F Y y P Y y P X y,..., X y 5 F Xi y FXy f Y y f X yfx y

19 Sprig 3 7 FUNCTIONS OF RANDOM VARIABLES a F T t P T < t P T t F Xi t F X t f T t F X t f X t Example 7.4. If each X i was expλ i the F Xi x e λix a so a T exp λ i. F T t e λit, t F T t e λit, t Example 7.5. Suppose that Z a Z are i.i.. r.v.s that are N,. What is the istributio of X Z Z? Well, ote that Z Z N, so Z Z χ 7. -to- Bivariate Trasformatios If we are give a X, Y bivariate vector r.v.s a f X,Y x, y is kow, the let A x, y, f XY > }, B u, v, u h x, y, v h x, y} If U h X, Y, V h X, Y a X w U, V, Y w U, V the g UV u, v f XY x, y x, y u, v f XY w u, v, w u, v x, y u, v Example 7.6. Suppose that a the U X + Y, V X Y g UV u, v f XY x, y e x +y π π e u +v 4 X U + V π e u, Y U V π e v Example 7.7. Suppose that X Uif[, a Y Uif[,. Usig the Box-Muller trasformatio, if U l X cos πy, V l X si πy it ca be show that U, V are iepeet N,. Also the Jacobia is J x π. Now ote that U + V l x X exp Example 7.8. Suppose that we have U +V f XY x, y so J π e U +V. e y < x < y < o/w If U X + Y a V X. The X V, Y U V a the support is < v < u <. Our Jacobia is J 6

20 Sprig 3 7 FUNCTIONS OF RANDOM VARIABLES a so g UV u, v e u v < v < u < o/w g U u g V v u/ v e u e v v e u/ e u e u e v u e v e v e v e v Example 7.9. Suppose that we have f XY x, y e x y < x, y < o/w a U X + Y, V X the X V a Y U V with J. The support is < v < u < a g UV u, v e v u v e u. Defiitio 7.. If Z N,, X χ, a Y χ X m the Z/ t a X/ Y/m F,m. Remark 7.. If W F,m the V W F m,. X Example 7.. To compute the pf of t let U X a V Z/. The X U a Z V U. We ca use the Jacobia metho above to compute the pf. 7. Momet-Geeratig Fuctio Metho Fact 7.. If X, X,..., X are iepeet a X i has MGF M Xi t the if Y X i we have M Y t M Xi t a if the X i s are i.i.. the M Y t M X t Example 7.. Suppose that X Nµ, σ a Y ax + b where M X t e µt e σ t /. The M Y t E[e ty ] e bt E[e atx ] e bt e aµt+ σ a t e aµ+bt e a σ t Y Naµ + b, a σ Now if X i Nµ i, σ i a Y a ix i the M Y t E[e t aixi ] E[e taixi ] e aiµit e a i σ i t e t aiµi e t Corollary 7.. Suppose that we have X i Nµ, σ where X,..., X are i.i.. the X i Nµ, σ, X a i σ i Y N a i µ i, a i µ i X i Nµ, σ Fact 7.3. We have Example 7.. We kow that Xi µ σ } } χ Y χ m i Xi X χ mi σ }} from other χ Xi + X σ } } χ 7

21 Sprig 3 8 CONVERGENCE OF RANDOM VARIABLES Proof is a exercise. Corollary 7.. X a S Xi X are iepeet. Corcha s Theorem Fact 7.4. We have that if X i Nµ, σ a X a S are efie as above, the X µ s/ t Fact 7.5. If X i Nµ, σ a Y j Nµ, σ are i.i.. for i,..., a j,..., m the S X /σ S Y /σ F 8 Covergece of Raom Variables Covergece ca take place from strogest to weakest: Everywhere Almost surely i L, L,... See PMATH 45 I istributio I probability We will examie the last two efiitios of covergece. Defiitio 8.. The sequece X, X,..., X coverges i probability to X if for ay ɛ > we have We eote this by X p X. lim P X X ɛ lim P X X < ɛ Defiitio 8.. We say that X : Ω A } coverges i istributio to X : Ω B if for ay ɛ > we have lim P X k P X k lim P X P X < ɛ, k A B A example woul be the cetral limit theorem. Alteratively, this is equivalet to lim F X x F X x at all parts where F X x is cotiuous. We the write X X. Propositio 8.. If X p X the X X. Example 8.. Suppose that X k } k are i.i.. Uif[, ]. Let X max k X k a X mi k X k. What is the limitig istributio of X? First remark that the support of X is,. The ote that for < x < we have P X x P X > x P k X k > x x 8

22 Sprig 3 8 CONVERGENCE OF RANDOM VARIABLES So x F x P X x x < x < x lim F x x e x x > What is the limitig istributio of X? Similar to above, the support of X is, a P X x P X > x P a i the limit, we have the same istributio i. That is lim F x X x x e x x > P k X k x x 3 What is the limitig istributio of X? This ca be show to have limitig cf of lim F x x < x X 4 Similarly, what is the limitig istributio of X? This ca be show to have limitig cf of lim F x x < x X Defiitio 8.3. Give a sequece of r.v.s. X }, with correspoig cfs F x} if lim F x < b x x b the X b. Theorem 8.. If X b the X p b. Proof. By irect evaluatio, so takig limits gives us P X b > ɛ P X < b ɛ + P X > b + ɛ P X b ɛ + P X > b + ɛ F b ɛ + F b + ɛ lim b > ɛ lim b ɛ + lim b + ɛ + 9

23 Sprig 3 8 CONVERGENCE OF RANDOM VARIABLES Example 8.. Give X i } i.i.. r.v.s, with f Xi x e x θ x θ o/w Let Y mi i X i a show that Y p θ. It is easier to show that Y as require. P Y x θ. Remark that the support of Y is θ,. We the have x < θ e x θ x θ Fact 8.. Markov s Iequality For ay k N, lim P Y x x < θ x θ Y P X > C E[ X k ] C k P X > C E[ X ] V arx + E[X] C C, k Propositio 8.. A property of the arithmetic mea of raom variables is X p µ. θ Proof. We have P X µ > ɛ ɛ E[ X µ ] ɛ V ar X σ ɛ Remark 8.. If X X the X X but X p X. Theorem 8.. Cetral Limit Theorem σ X µ N, where X } are i.i.. r.v.s. with X µ, σ Proof. No. Observe that for the cf of ay r.v. X we have M X t e t /, f l M X, Now if A σ X µ a Y i Xi µ σ the sice Now from above, a hece lim M Y f M X M X, f M X M X M X M X σ E[e ta ] E [e t ] Yi X i µ t t f Y l M Y t + Ot3 M Y t e t / N,. e t Y i t MY σ X i µ X i µ σ t t e t / M Y e t/ Proof. No. Alteratively, usig otatio from the previous proof, M A t M Yi/ t M Y t

24 Sprig 3 8 CONVERGENCE OF RANDOM VARIABLES Usig a st orer Taylor series, t lim M Y lim + t e t / Corollary 8.. If X i } are i.i.. P oisµ a Y X i the Y µ µ N, If X i } are i.i.. χ mea of χ k is k a variace is k a Y X i the Y N, 8. Useful Limit Theorems p D. If X a the gx p D ga. That is g is cotiuous at a.. Slutsky s Theorem Suppose that X X a Y p b. The, a X + Y b X Y X + b b X c X /Y X/b, b Example 8.3. Suppose X, X,..., X are i.i. X i Uif[,. We showe that X p e X p e a X Z exp. Remark 8.. F X X Uif[, ] Example 8.4. If X i } are P oisµ the Z X µ X µ X X }} N, X N, µ }} p a similarly X µ N, µ 8. Delta Metho Propositio 8.3. Suppose that for X, X,..., X we have X θ N, σ If gx is ifferetiable at θ a g θ the gx gθ N, g θ σ

25 Sprig 3 9 POINT ESTIMATION 9 Poit Estimatio Suppose that we observe X,..., X i.i.. from fx, θ a θ is ukow. The goal is to estimate θ. Defiitio 9.. The t statistic is a fuctio of ata that oes t epe o θ or µ or ay ukow parameter. We eote it by T X T X,..., X as a raom variable a t tx,..., x as its value. The followig are ifferet methos for poit estimatio.. Metho of Momets. Maximum Likelihoo 3. Bayes Estimatio 9. Metho of Momets Here, we wat to set the sample/observe k th momet equal to the theoretical momet. That is we wat M k for l,,..., l}. Example 9.. If X,..., X are i.i.. P oisµ the E[X i ] µ a Xi k E[X l ] ˆµ MM X i Example 9.. If X,..., X are i.i.. a f X θ e x/θ x θ otherwise The E[X i ] θ a Example 9.3. If X,..., X are i.i.. Nµ, σ the ˆθ MM N X i Example 9.4. If X,..., X are i.i.. a The we ca show E[X] ˆµ MM f X X i, ˆσ MM + ˆµ MM θe θ x otherwise, θ > θ θ + θ E[X] E[X] X i ˆθ MM X X Example 9.5. Suppose that X Gamα, β the E[X] αβ a V arx αβ. So ˆ αβ MM X i, αβ ˆ MM + αβmm ˆ X i

26 Sprig 3 9 POINT ESTIMATION Example 9.6. If X,..., X are i.i.. Uif[, θ] the Remark that ˆθ MLE maxx,..., X. ˆθ MM ] X i, E [ˆθMM θ 9. Maximum Likelihoo Estimatio Defiitio 9.. Suppose that X,..., X are i.i.. from fx, θ. We call Lθ, X fx i, θ the likelihoo of θ a l ll the log-likelihoo fuctio. The MLE estimate is Example 9.7. If X,..., X are i.i.. a The it ca be show that If we set lθ θ the ˆθ ML ˆθ MLE argmax Lθ argmax lθ f X Example 9.8. Suppose that X,..., X P oisθ. The θ e x/θ x θ otherwise lθ l θ + l e x+...+x/θ l θ x x θ Lθ e θ θ xi x i! ˆθ ML x i lθ θ + l θ x i l x i! a so l θ + x i θ ˆθ ML x i Example 9.9. Recall that if fx, θ θx θ, < x <, θ > the It ca be show that a so ˆθ MM X X θ Lθ θ x i lθ l θ + θ l x i l θ θ + l x i ˆθ ML l x i Example 9.. Suppose that X,..., X Exp/θ a i.i... The Lθ θ e θ xi lθ lθ θ 3 x i

27 Sprig 3 9 POINT ESTIMATION a hece l θ θ + θ Example 9.. Suppose that X,..., X Berp a i.i... The a so Note that x i ˆθ ML x i x Lp p xi p xi lp l p l p p [ l p x i p + + x i + l p p ˆp ML x i ] x i p < Example 9.. Suppose that X,..., X are i.i.. Nµ, σ. It ca be show that a hece Lθ πσ xi e x i µ σ lθ l π l σ x i µ l µ σ l σ σ + σ 3 x i µ ˆµ ML x i σ x i µ ˆσ ML x i ˆµ ML Example 9.3. Suppose that X,..., X are i.i.. Uif[, θ]. The it ca be show that with f X have a hece ˆθ ML maxx,..., x. Lθ /θ x, x,.., x [, θ] /θ Imaxx o/w,...,x θ Propositio 9.. E[X a ] V ar[x] a equality hols whe a E[X]. /θ x θ o/w we Proof. We have E[X E[X] + E[X] a ] V ar[x] + E[X] a + E [X E[X] E[X] a] V ar[x] }} 9.3 Notable Fuctios a Matrices Defiitio 9.3. The score fuctio is The iformatio fuctio is Iθ θ Sθ l fx, θ θ Sθ l fx, θ θ 4

28 Sprig 3 9 POINT ESTIMATION The Fisher iformatio matrix is Jθ E [Iθ] Summary 7. Some properties iclue:. Sˆθ ML. E [ θ l fx, θ] a This follows from the fact that [ ] E l fx, θ θ θ l fx, θ fx, θx θ θ fx, θ fx, θ fx, θx fx, θx θ [ ] 3. E θ l fx, θ E [ θ l fx, θ ] a To see this, we take the partial with respect to θ of θ l fx, θ fx, θx to get θ l fx, θ fx, θx + [ ] E l fx, θ θ θ l fx, θ fx, θx θ θ l fx, θ l fx, θ fx, θx θ }} [ ] E l fx, θ E θ [ ] [ 4. If X,..., X are i.i.. the E θ l fx, θ E θ l fx, θ ] a This follows from the efiitio of Jθ with Jθ J θ. E[ θ l fx,θ] [ ] l fx, θ θ Propositio 9.. Cramer-Rao Lower Bou Suppose that T X,..., X is a estimator for θ. Remark that if T is ubiase if E[T X] θ. If E[T X] θ the E[T X] is biase. Also, if X,..., X are samples from fx, θ the V art θ E[T ] E [ θ l fx, θ ] [ ] E θ l fx, θ Proof. First remark that CovX, Y V arxv ary. Set X T X a Y θ l fx, θ. The Cov T X, θ [ ] [ ] l fx, θ E T X l fx, θ E l fx, θ E[T X] θ θ }} E[T X] θ T X fx, θx θ 5

29 Sprig 3 9 POINT ESTIMATION Sice V ar [ [ ] θ l fx, θ] E θ l fx, θ because E [ θ l fx, θ] the V ar[t X] θ E[T X] E [ θ l fx, θ ] J θ Example 9.4. Suppose that X P oisµ. The a with the C-R Cramer-Rao bou as Previously, we showe that a so the ML estimator is efficiet. Remark 9.. ˆθ ML ˆθ ML θ N l fx, µ µ µ µ + x l µ l x! + x µ µ l fx, µ x µ Iµ x E[X] Jµ µ µ µ p θ asymptotically This will also imply that ˆθ ML θ N ˆµ ML V art µ X i, Jθ asymptotically ormal µ V ar[µ ML ] µ µ, J θ N, Jθ a ˆθ ML N θ, Jθ. 9.4 Covex Fuctios Defiitio 9.4. We say that a fuctio f is covex if x, x a, b a λ [, ] we have fλx + λx λfx + λfx f > Remark 9.. If f is covex the f is cocave. Propositio 9.3. Jese s iequality If X is a r.v. a f is covex the E[fX] f E[X] Proof. Suppose that the iequality is true for k N. The k k p i p i fx i p k fx k + + p k fx i + p k k p k fx k + p k q i fx i 6

30 Sprig 3 9 POINT ESTIMATION a usig iuctio o the latter term we get k p i fx i p k fx k + + p k f f p k x k + p k k f p i x i k q i fx i k q i fx i Example 9.5. If Y x l x the because Y is cocave i x the l X i l X i X i This shows that the geometric mea is always less tha the arithmetic mea. Note 3. For the fial exam, pay attetio to the tutorial cotet o X i. Metho of Momets for Gamma Q where MM with V armm > V arml. x i, ML maxx,..., X 7

31 Sprig 3 INDEX Iex -to- bivariate trasformatios, 6 bivariate ormal istributio, 4 Box-Muller trasformatio, 6 cetral limit theorem, 8, cetral momet, 5 characteristic fuctio, 8 coitioal istributios, coitioal expectatio, covergece i istributio, 8 covergece i probability, 8 covex fuctios, 6 Corcha s theorem, 8 correlatio coefficiet, Cramer-Rao lower bou, 5 cumulative istributio fuctio, elta metho, expectatio, 4 Fisher iformatio matrix, 5 fuctios of raom variables, 5 gamma istributio, 3 gamma fuctio, 3 iformatio fuctio, 4 Jacobia, 6 Jese s iequality, 6 joit istributios, 8 Kolmogorov axioms, limitig istributio, 9 Markov s iequality, maximum likelihoo estimatio, 3 metho of momets, momet geeratig fuctio, 6 momets, 5 multiomial istributio, 3 poit estimatio, probability mass fuctio, probability space, score fuctio, 4 σ aitivity, Slutsky s theorem, support, 9 uiform istributio, 3 Vaermoe ietity, variace, 4 Weibull istributio, 4 8

Homework for 1/27 Due 2/5

Homework for 1/27 Due 2/5 Name: ID: Homework for /7 Due /5. [ 8-3] I Example D of Sectio 8.4, the pdf of the populatio distributio is + αx x f(x α) =, α, otherwise ad the method of momets estimate was foud to be ˆα = 3X (where

Διαβάστε περισσότερα

Lecture 17: Minimum Variance Unbiased (MVUB) Estimators

Lecture 17: Minimum Variance Unbiased (MVUB) Estimators ECE 830 Fall 2011 Statistical Sigal Processig istructor: R. Nowak, scribe: Iseok Heo Lecture 17: Miimum Variace Ubiased (MVUB Estimators Ultimately, we would like to be able to argue that a give estimator

Διαβάστε περισσότερα

Last Lecture. Biostatistics Statistical Inference Lecture 19 Likelihood Ratio Test. Example of Hypothesis Testing.

Last Lecture. Biostatistics Statistical Inference Lecture 19 Likelihood Ratio Test. Example of Hypothesis Testing. Last Lecture Biostatistics 602 - Statistical Iferece Lecture 19 Likelihood Ratio Test Hyu Mi Kag March 26th, 2013 Describe the followig cocepts i your ow words Hypothesis Null Hypothesis Alterative Hypothesis

Διαβάστε περισσότερα

Advanced Statistics. Chen, L.-A. Distribution of order statistics: Review : Let X 1,..., X k be random variables with joint p.d.f f(x 1,...

Advanced Statistics. Chen, L.-A. Distribution of order statistics: Review : Let X 1,..., X k be random variables with joint p.d.f f(x 1,... Avace Statistics Che, L.-A. Distributio of orer statistics: Review : Let X,..., X k be raom variables with joit p..f f(x,..., x k a Y h (X,..., X k, Y h (X,..., X k,..., Y k h k (X,..., X k be - trasformatio

Διαβάστε περισσότερα

Solution Series 9. i=1 x i and i=1 x i.

Solution Series 9. i=1 x i and i=1 x i. Lecturer: Prof. Dr. Mete SONER Coordinator: Yilin WANG Solution Series 9 Q1. Let α, β >, the p.d.f. of a beta distribution with parameters α and β is { Γ(α+β) Γ(α)Γ(β) f(x α, β) xα 1 (1 x) β 1 for < x

Διαβάστε περισσότερα

1. For each of the following power series, find the interval of convergence and the radius of convergence:

1. For each of the following power series, find the interval of convergence and the radius of convergence: Math 6 Practice Problems Solutios Power Series ad Taylor Series 1. For each of the followig power series, fid the iterval of covergece ad the radius of covergece: (a ( 1 x Notice that = ( 1 +1 ( x +1.

Διαβάστε περισσότερα

Other Test Constructions: Likelihood Ratio & Bayes Tests

Other Test Constructions: Likelihood Ratio & Bayes Tests Other Test Constructions: Likelihood Ratio & Bayes Tests Side-Note: So far we have seen a few approaches for creating tests such as Neyman-Pearson Lemma ( most powerful tests of H 0 : θ = θ 0 vs H 1 :

Διαβάστε περισσότερα

LAD Estimation for Time Series Models With Finite and Infinite Variance

LAD Estimation for Time Series Models With Finite and Infinite Variance LAD Estimatio for Time Series Moels With Fiite a Ifiite Variace Richar A. Davis Colorao State Uiversity William Dusmuir Uiversity of New South Wales 1 LAD Estimatio for ARMA Moels fiite variace ifiite

Διαβάστε περισσότερα

Solutions: Homework 3

Solutions: Homework 3 Solutios: Homework 3 Suppose that the radom variables Y,, Y satisfy Y i = βx i + ε i : i,, where x,, x R are fixed values ad ε,, ε Normal0, σ ) with σ R + kow Fid ˆβ = MLEβ) IND Solutio: Observe that Y

Διαβάστε περισσότερα

FREE VIBRATION OF A SINGLE-DEGREE-OF-FREEDOM SYSTEM Revision B

FREE VIBRATION OF A SINGLE-DEGREE-OF-FREEDOM SYSTEM Revision B FREE VIBRATION OF A SINGLE-DEGREE-OF-FREEDOM SYSTEM Revisio B By Tom Irvie Email: tomirvie@aol.com February, 005 Derivatio of the Equatio of Motio Cosier a sigle-egree-of-freeom system. m x k c where m

Διαβάστε περισσότερα

Statistics 104: Quantitative Methods for Economics Formula and Theorem Review

Statistics 104: Quantitative Methods for Economics Formula and Theorem Review Harvard College Statistics 104: Quantitative Methods for Economics Formula and Theorem Review Tommy MacWilliam, 13 tmacwilliam@college.harvard.edu March 10, 2011 Contents 1 Introduction to Data 5 1.1 Sample

Διαβάστε περισσότερα

SUPERPOSITION, MEASUREMENT, NORMALIZATION, EXPECTATION VALUES. Reading: QM course packet Ch 5 up to 5.6

SUPERPOSITION, MEASUREMENT, NORMALIZATION, EXPECTATION VALUES. Reading: QM course packet Ch 5 up to 5.6 SUPERPOSITION, MEASUREMENT, NORMALIZATION, EXPECTATION VALUES Readig: QM course packet Ch 5 up to 5. 1 ϕ (x) = E = π m( a) =1,,3,4,5 for xa (x) = πx si L L * = πx L si L.5 ϕ' -.5 z 1 (x) = L si

Διαβάστε περισσότερα

2 Composition. Invertible Mappings

2 Composition. Invertible Mappings Arkansas Tech University MATH 4033: Elementary Modern Algebra Dr. Marcel B. Finan Composition. Invertible Mappings In this section we discuss two procedures for creating new mappings from old ones, namely,

Διαβάστε περισσότερα

true value θ. Fisher information is meaningful for families of distribution which are regular: W (x) f(x θ)dx

true value θ. Fisher information is meaningful for families of distribution which are regular: W (x) f(x θ)dx Fisher Iformatio April 6, 26 Debdeep Pati Fisher Iformatio Assume X fx θ pdf or pmf with θ Θ R. Defie I X θ E θ [ θ log fx θ 2 ] where θ log fx θ is the derivative of the log-likelihood fuctio evaluated

Διαβάστε περισσότερα

p n r.01.05.10.15.20.25.30.35.40.45.50.55.60.65.70.75.80.85.90.95

p n r.01.05.10.15.20.25.30.35.40.45.50.55.60.65.70.75.80.85.90.95 r r Table 4 Biomial Probability Distributio C, r p q This table shows the probability of r successes i idepedet trials, each with probability of success p. p r.01.05.10.15.0.5.30.35.40.45.50.55.60.65.70.75.80.85.90.95

Διαβάστε περισσότερα

L.K.Gupta (Mathematic Classes) www.pioeermathematics.com MOBILE: 985577, 4677 + {JEE Mai 04} Sept 0 Name: Batch (Day) Phoe No. IT IS NOT ENOUGH TO HAVE A GOOD MIND, THE MAIN THING IS TO USE IT WELL Marks:

Διαβάστε περισσότερα

Probability theory STATISTICAL MODELING OF MULTIVARIATE EXTREMES, FMSN15/MASM23 TABLE OF FORMULÆ. Basic probability theory

Probability theory STATISTICAL MODELING OF MULTIVARIATE EXTREMES, FMSN15/MASM23 TABLE OF FORMULÆ. Basic probability theory Lud Istitute of Techology Cetre for Mathematical Scieces Mathematical Statistics STATISTICAL MODELING OF MULTIVARIATE EXTREMES, FMSN5/MASM3 Probability theory Basic probability theory TABLE OF FORMULÆ

Διαβάστε περισσότερα

4.6 Autoregressive Moving Average Model ARMA(1,1)

4.6 Autoregressive Moving Average Model ARMA(1,1) 84 CHAPTER 4. STATIONARY TS MODELS 4.6 Autoregressive Moving Average Model ARMA(,) This section is an introduction to a wide class of models ARMA(p,q) which we will consider in more detail later in this

Διαβάστε περισσότερα

n r f ( n-r ) () x g () r () x (1.1) = Σ g() x = Σ n f < -n+ r> g () r -n + r dx r dx n + ( -n,m) dx -n n+1 1 -n -1 + ( -n,n+1)

n r f ( n-r ) () x g () r () x (1.1) = Σ g() x = Σ n f < -n+ r> g () r -n + r dx r dx n + ( -n,m) dx -n n+1 1 -n -1 + ( -n,n+1) 8 Higher Derivative of the Product of Two Fuctios 8. Leibiz Rule about the Higher Order Differetiatio Theorem 8.. (Leibiz) Whe fuctios f ad g f g are times differetiable, the followig epressio holds. r

Διαβάστε περισσότερα

Exam Statistics 6 th September 2017 Solution

Exam Statistics 6 th September 2017 Solution Exam Statstcs 6 th September 17 Soluto Maura Mezzett Exercse 1 Let (X 1,..., X be a raom sample of... raom varables. Let f θ (x be the esty fucto. Let ˆθ be the MLE of θ, θ be the true parameter, L(θ be

Διαβάστε περισσότερα

6. MAXIMUM LIKELIHOOD ESTIMATION

6. MAXIMUM LIKELIHOOD ESTIMATION 6 MAXIMUM LIKELIHOOD ESIMAION [1] Maximum Likelihood Estimator (1) Cases in which θ (unknown parameter) is scalar Notational Clarification: From now on, we denote the true value of θ as θ o hen, view θ

Διαβάστε περισσότερα

SOLUTIONS TO MATH38181 EXTREME VALUES AND FINANCIAL RISK EXAM

SOLUTIONS TO MATH38181 EXTREME VALUES AND FINANCIAL RISK EXAM SOLUTIONS TO MATH38181 EXTREME VALUES AND FINANCIAL RISK EXAM Solutions to Question 1 a) The cumulative distribution function of T conditional on N n is Pr T t N n) Pr max X 1,..., X N ) t N n) Pr max

Διαβάστε περισσότερα

ST5224: Advanced Statistical Theory II

ST5224: Advanced Statistical Theory II ST5224: Advanced Statistical Theory II 2014/2015: Semester II Tutorial 7 1. Let X be a sample from a population P and consider testing hypotheses H 0 : P = P 0 versus H 1 : P = P 1, where P j is a known

Διαβάστε περισσότερα

Στα επόμενα θεωρούμε ότι όλα συμβαίνουν σε ένα χώρο πιθανότητας ( Ω,,P) Modes of convergence: Οι τρόποι σύγκλισης μιας ακολουθίας τ.μ.

Στα επόμενα θεωρούμε ότι όλα συμβαίνουν σε ένα χώρο πιθανότητας ( Ω,,P) Modes of convergence: Οι τρόποι σύγκλισης μιας ακολουθίας τ.μ. Στα πόμνα θωρούμ ότι όλα συμβαίνουν σ ένα χώρο πιθανότητας ( Ω,,). Modes of covergece: Οι τρόποι σύγκλισης μιας ακολουθίας τ.μ. { } ίναι οι ξής: σ μια τ.μ.. Ισχυρή σύγκλιση strog covergece { } lim = =.

Διαβάστε περισσότερα

Introduction of Numerical Analysis #03 TAGAMI, Daisuke (IMI, Kyushu University)

Introduction of Numerical Analysis #03 TAGAMI, Daisuke (IMI, Kyushu University) Itroductio of Numerical Aalysis #03 TAGAMI, Daisuke (IMI, Kyushu Uiversity) web page of the lecture: http://www2.imi.kyushu-u.ac.jp/~tagami/lec/ Strategy of Numerical Simulatios Pheomea Error modelize

Διαβάστε περισσότερα

Solve the difference equation

Solve the difference equation Solve the differece equatio Solutio: y + 3 3y + + y 0 give tat y 0 4, y 0 ad y 8. Let Z{y()} F() Taig Z-trasform o both sides i (), we get y + 3 3y + + y 0 () Z y + 3 3y + + y Z 0 Z y + 3 3Z y + + Z y

Διαβάστε περισσότερα

Problem Set 3: Solutions

Problem Set 3: Solutions CMPSCI 69GG Applied Information Theory Fall 006 Problem Set 3: Solutions. [Cover and Thomas 7.] a Define the following notation, C I p xx; Y max X; Y C I p xx; Ỹ max I X; Ỹ We would like to show that C

Διαβάστε περισσότερα

MATH 38061/MATH48061/MATH68061: MULTIVARIATE STATISTICS Solutions to Problems on Matrix Algebra

MATH 38061/MATH48061/MATH68061: MULTIVARIATE STATISTICS Solutions to Problems on Matrix Algebra MATH 38061/MATH48061/MATH68061: MULTIVARIATE STATISTICS Solutios to Poblems o Matix Algeba 1 Let A be a squae diagoal matix takig the fom a 11 0 0 0 a 22 0 A 0 0 a pp The ad So, log det A t log A t log

Διαβάστε περισσότερα

COMMON RANDOM FIXED POINT THEOREMS IN SYMMETRIC SPACES

COMMON RANDOM FIXED POINT THEOREMS IN SYMMETRIC SPACES Iteratioal Joural of Avacemets i Research & Techology, Volume, Issue, Jauary-03 ISSN 78-7763 COMMON RANDOM FIXED POINT THEOREMS IN SYMMETRIC SPACES Dr Neetu Vishwakarma a Dr M S Chauha Sagar Istitute of

Διαβάστε περισσότερα

3.4 SUM AND DIFFERENCE FORMULAS. NOTE: cos(α+β) cos α + cos β cos(α-β) cos α -cos β

3.4 SUM AND DIFFERENCE FORMULAS. NOTE: cos(α+β) cos α + cos β cos(α-β) cos α -cos β 3.4 SUM AND DIFFERENCE FORMULAS Page Theorem cos(αβ cos α cos β -sin α cos(α-β cos α cos β sin α NOTE: cos(αβ cos α cos β cos(α-β cos α -cos β Proof of cos(α-β cos α cos β sin α Let s use a unit circle

Διαβάστε περισσότερα

The Heisenberg Uncertainty Principle

The Heisenberg Uncertainty Principle Chemistry 460 Sprig 015 Dr. Jea M. Stadard March, 015 The Heiseberg Ucertaity Priciple A policema pulls Werer Heiseberg over o the Autobah for speedig. Policema: Sir, do you kow how fast you were goig?

Διαβάστε περισσότερα

Solutions to Exercise Sheet 5

Solutions to Exercise Sheet 5 Solutions to Eercise Sheet 5 jacques@ucsd.edu. Let X and Y be random variables with joint pdf f(, y) = 3y( + y) where and y. Determine each of the following probabilities. Solutions. a. P (X ). b. P (X

Διαβάστε περισσότερα

Statistical Inference I Locally most powerful tests

Statistical Inference I Locally most powerful tests Statistical Inference I Locally most powerful tests Shirsendu Mukherjee Department of Statistics, Asutosh College, Kolkata, India. shirsendu st@yahoo.co.in So far we have treated the testing of one-sided

Διαβάστε περισσότερα

C.S. 430 Assignment 6, Sample Solutions

C.S. 430 Assignment 6, Sample Solutions C.S. 430 Assignment 6, Sample Solutions Paul Liu November 15, 2007 Note that these are sample solutions only; in many cases there were many acceptable answers. 1 Reynolds Problem 10.1 1.1 Normal-order

Διαβάστε περισσότερα

Lecture 3: Asymptotic Normality of M-estimators

Lecture 3: Asymptotic Normality of M-estimators Lecture 3: Asymptotic Istructor: Departmet of Ecoomics Staford Uiversity Prepared by Webo Zhou, Remi Uiversity Refereces Takeshi Amemiya, 1985, Advaced Ecoometrics, Harvard Uiversity Press Newey ad McFadde,

Διαβάστε περισσότερα

On Generating Relations of Some Triple. Hypergeometric Functions

On Generating Relations of Some Triple. Hypergeometric Functions It. Joural of Math. Aalysis, Vol. 5,, o., 5 - O Geeratig Relatios of Some Triple Hypergeometric Fuctios Fadhle B. F. Mohse ad Gamal A. Qashash Departmet of Mathematics, Faculty of Educatio Zigibar Ade

Διαβάστε περισσότερα

ECE598: Information-theoretic methods in high-dimensional statistics Spring 2016

ECE598: Information-theoretic methods in high-dimensional statistics Spring 2016 ECE598: Information-theoretic methods in high-dimensional statistics Spring 06 Lecture 7: Information bound Lecturer: Yihong Wu Scribe: Shiyu Liang, Feb 6, 06 [Ed. Mar 9] Recall the Chi-squared divergence

Διαβάστε περισσότερα

INTEGRATION OF THE NORMAL DISTRIBUTION CURVE

INTEGRATION OF THE NORMAL DISTRIBUTION CURVE INTEGRATION OF THE NORMAL DISTRIBUTION CURVE By Tom Irvie Email: tomirvie@aol.com March 3, 999 Itroductio May processes have a ormal probability distributio. Broadbad radom vibratio is a example. The purpose

Διαβάστε περισσότερα

Ordinal Arithmetic: Addition, Multiplication, Exponentiation and Limit

Ordinal Arithmetic: Addition, Multiplication, Exponentiation and Limit Ordinal Arithmetic: Addition, Multiplication, Exponentiation and Limit Ting Zhang Stanford May 11, 2001 Stanford, 5/11/2001 1 Outline Ordinal Classification Ordinal Addition Ordinal Multiplication Ordinal

Διαβάστε περισσότερα

= λ 1 1 e. = λ 1 =12. has the properties e 1. e 3,V(Y

= λ 1 1 e. = λ 1 =12. has the properties e 1. e 3,V(Y Stat 50 Homework Solutions Spring 005. (a λ λ λ 44 (b trace( λ + λ + λ 0 (c V (e x e e λ e e λ e (λ e by definition, the eigenvector e has the properties e λ e and e e. (d λ e e + λ e e + λ e e 8 6 4 4

Διαβάστε περισσότερα

SOLUTIONS TO MATH38181 EXTREME VALUES AND FINANCIAL RISK EXAM

SOLUTIONS TO MATH38181 EXTREME VALUES AND FINANCIAL RISK EXAM SOLUTIONS TO MATH38181 EXTREME VALUES AND FINANCIAL RISK EXAM Solutions to Question 1 a) The cumulative distribution function of T conditional on N n is Pr (T t N n) Pr (max (X 1,..., X N ) t N n) Pr (max

Διαβάστε περισσότερα

Aquinas College. Edexcel Mathematical formulae and statistics tables DO NOT WRITE ON THIS BOOKLET

Aquinas College. Edexcel Mathematical formulae and statistics tables DO NOT WRITE ON THIS BOOKLET Aquinas College Edexcel Mathematical formulae and statistics tables DO NOT WRITE ON THIS BOOKLET Pearson Edexcel Level 3 Advanced Subsidiary and Advanced GCE in Mathematics and Further Mathematics Mathematical

Διαβάστε περισσότερα

IIT JEE (2013) (Trigonomtery 1) Solutions

IIT JEE (2013) (Trigonomtery 1) Solutions L.K. Gupta (Mathematic Classes) www.pioeermathematics.com MOBILE: 985577, 677 (+) PAPER B IIT JEE (0) (Trigoomtery ) Solutios TOWARDS IIT JEE IS NOT A JOURNEY, IT S A BATTLE, ONLY THE TOUGHEST WILL SURVIVE

Διαβάστε περισσότερα

Homework 4.1 Solutions Math 5110/6830

Homework 4.1 Solutions Math 5110/6830 Homework 4. Solutios Math 5/683. a) For p + = αp γ α)p γ α)p + γ b) Let Equilibria poits satisfy: p = p = OR = γ α)p ) γ α)p + γ = α γ α)p ) γ α)p + γ α = p ) p + = p ) = The, we have equilibria poits

Διαβάστε περισσότερα

Lecture 21: Properties and robustness of LSE

Lecture 21: Properties and robustness of LSE Lecture 21: Properties and robustness of LSE BLUE: Robustness of LSE against normality We now study properties of l τ β and σ 2 under assumption A2, i.e., without the normality assumption on ε. From Theorem

Διαβάστε περισσότερα

Bayesian statistics. DS GA 1002 Probability and Statistics for Data Science.

Bayesian statistics. DS GA 1002 Probability and Statistics for Data Science. Bayesian statistics DS GA 1002 Probability and Statistics for Data Science http://www.cims.nyu.edu/~cfgranda/pages/dsga1002_fall17 Carlos Fernandez-Granda Frequentist vs Bayesian statistics In frequentist

Διαβάστε περισσότερα

Parameter Estimation Fitting Probability Distributions Bayesian Approach

Parameter Estimation Fitting Probability Distributions Bayesian Approach Parameter Estimatio Fittig Probability Distributios Bayesia Approach MIT 18.443 Dr. Kempthore Sprig 2015 1 MIT 18.443 Parameter EstimatioFittig Probability DistributiosBayesia Ap Outlie Bayesia Approach

Διαβάστε περισσότερα

The Simply Typed Lambda Calculus

The Simply Typed Lambda Calculus Type Inference Instead of writing type annotations, can we use an algorithm to infer what the type annotations should be? That depends on the type system. For simple type systems the answer is yes, and

Διαβάστε περισσότερα

Chapter 6: Systems of Linear Differential. be continuous functions on the interval

Chapter 6: Systems of Linear Differential. be continuous functions on the interval Chapter 6: Systems of Linear Differential Equations Let a (t), a 2 (t),..., a nn (t), b (t), b 2 (t),..., b n (t) be continuous functions on the interval I. The system of n first-order differential equations

Διαβάστε περισσότερα

Biorthogonal Wavelets and Filter Banks via PFFS. Multiresolution Analysis (MRA) subspaces V j, and wavelet subspaces W j. f X n f, τ n φ τ n φ.

Biorthogonal Wavelets and Filter Banks via PFFS. Multiresolution Analysis (MRA) subspaces V j, and wavelet subspaces W j. f X n f, τ n φ τ n φ. Chapter 3. Biorthogoal Wavelets ad Filter Baks via PFFS 3.0 PFFS applied to shift-ivariat subspaces Defiitio: X is a shift-ivariat subspace if h X h( ) τ h X. Ex: Multiresolutio Aalysis (MRA) subspaces

Διαβάστε περισσότερα

Matrices and Determinants

Matrices and Determinants Matrices and Determinants SUBJECTIVE PROBLEMS: Q 1. For what value of k do the following system of equations possess a non-trivial (i.e., not all zero) solution over the set of rationals Q? x + ky + 3z

Διαβάστε περισσότερα

Section 8.3 Trigonometric Equations

Section 8.3 Trigonometric Equations 99 Section 8. Trigonometric Equations Objective 1: Solve Equations Involving One Trigonometric Function. In this section and the next, we will exple how to solving equations involving trigonometric functions.

Διαβάστε περισσότερα

Homework 8 Model Solution Section

Homework 8 Model Solution Section MATH 004 Homework Solution Homework 8 Model Solution Section 14.5 14.6. 14.5. Use the Chain Rule to find dz where z cosx + 4y), x 5t 4, y 1 t. dz dx + dy y sinx + 4y)0t + 4) sinx + 4y) 1t ) 0t + 4t ) sinx

Διαβάστε περισσότερα

Example of the Baum-Welch Algorithm

Example of the Baum-Welch Algorithm Example of the Baum-Welch Algorithm Larry Moss Q520, Spring 2008 1 Our corpus c We start with a very simple corpus. We take the set Y of unanalyzed words to be {ABBA, BAB}, and c to be given by c(abba)

Διαβάστε περισσότερα

Econ 2110: Fall 2008 Suggested Solutions to Problem Set 8 questions or comments to Dan Fetter 1

Econ 2110: Fall 2008 Suggested Solutions to Problem Set 8  questions or comments to Dan Fetter 1 Eon : Fall 8 Suggested Solutions to Problem Set 8 Email questions or omments to Dan Fetter Problem. Let X be a salar with density f(x, θ) (θx + θ) [ x ] with θ. (a) Find the most powerful level α test

Διαβάστε περισσότερα

Phys460.nb Solution for the t-dependent Schrodinger s equation How did we find the solution? (not required)

Phys460.nb Solution for the t-dependent Schrodinger s equation How did we find the solution? (not required) Phys460.nb 81 ψ n (t) is still the (same) eigenstate of H But for tdependent H. The answer is NO. 5.5.5. Solution for the tdependent Schrodinger s equation If we assume that at time t 0, the electron starts

Διαβάστε περισσότερα

Second Order Partial Differential Equations

Second Order Partial Differential Equations Chapter 7 Second Order Partial Differential Equations 7.1 Introduction A second order linear PDE in two independent variables (x, y Ω can be written as A(x, y u x + B(x, y u xy + C(x, y u u u + D(x, y

Διαβάστε περισσότερα

Homework 3 Solutions

Homework 3 Solutions Homework 3 Solutions Igor Yanovsky (Math 151A TA) Problem 1: Compute the absolute error and relative error in approximations of p by p. (Use calculator!) a) p π, p 22/7; b) p π, p 3.141. Solution: For

Διαβάστε περισσότερα

CHAPTER 25 SOLVING EQUATIONS BY ITERATIVE METHODS

CHAPTER 25 SOLVING EQUATIONS BY ITERATIVE METHODS CHAPTER 5 SOLVING EQUATIONS BY ITERATIVE METHODS EXERCISE 104 Page 8 1. Find the positive root of the equation x + 3x 5 = 0, correct to 3 significant figures, using the method of bisection. Let f(x) =

Διαβάστε περισσότερα

A Two-Sided Laplace Inversion Algorithm with Computable Error Bounds and Its Applications in Financial Engineering

A Two-Sided Laplace Inversion Algorithm with Computable Error Bounds and Its Applications in Financial Engineering Electronic Companion A Two-Sie Laplace Inversion Algorithm with Computable Error Bouns an Its Applications in Financial Engineering Ning Cai, S. G. Kou, Zongjian Liu HKUST an Columbia University Appenix

Διαβάστε περισσότερα

Example Sheet 3 Solutions

Example Sheet 3 Solutions Example Sheet 3 Solutions. i Regular Sturm-Liouville. ii Singular Sturm-Liouville mixed boundary conditions. iii Not Sturm-Liouville ODE is not in Sturm-Liouville form. iv Regular Sturm-Liouville note

Διαβάστε περισσότερα

EE512: Error Control Coding

EE512: Error Control Coding EE512: Error Control Coding Solution for Assignment on Finite Fields February 16, 2007 1. (a) Addition and Multiplication tables for GF (5) and GF (7) are shown in Tables 1 and 2. + 0 1 2 3 4 0 0 1 2 3

Διαβάστε περισσότερα

6.1. Dirac Equation. Hamiltonian. Dirac Eq.

6.1. Dirac Equation. Hamiltonian. Dirac Eq. 6.1. Dirac Equation Ref: M.Kaku, Quantum Field Theory, Oxford Univ Press (1993) η μν = η μν = diag(1, -1, -1, -1) p 0 = p 0 p = p i = -p i p μ p μ = p 0 p 0 + p i p i = E c 2 - p 2 = (m c) 2 H = c p 2

Διαβάστε περισσότερα

Theorem 8 Let φ be the most powerful size α test of H

Theorem 8 Let φ be the most powerful size α test of H Testing composite hypotheses Θ = Θ 0 Θ c 0 H 0 : θ Θ 0 H 1 : θ Θ c 0 Definition 16 A test φ is a uniformly most powerful (UMP) level α test for H 0 vs. H 1 if φ has level α and for any other level α test

Διαβάστε περισσότερα

Srednicki Chapter 55

Srednicki Chapter 55 Srednicki Chapter 55 QFT Problems & Solutions A. George August 3, 03 Srednicki 55.. Use equations 55.3-55.0 and A i, A j ] = Π i, Π j ] = 0 (at equal times) to verify equations 55.-55.3. This is our third

Διαβάστε περισσότερα

Nowhere-zero flows Let be a digraph, Abelian group. A Γ-circulation in is a mapping : such that, where, and : tail in X, head in

Nowhere-zero flows Let be a digraph, Abelian group. A Γ-circulation in is a mapping : such that, where, and : tail in X, head in Nowhere-zero flows Let be a digraph, Abelian group. A Γ-circulation in is a mapping : such that, where, and : tail in X, head in : tail in X, head in A nowhere-zero Γ-flow is a Γ-circulation such that

Διαβάστε περισσότερα

α β

α β 6. Eerg, Mometum coefficiets for differet velocit distributios Rehbock obtaied ) For Liear Velocit Distributio α + ε Vmax { } Vmax ε β +, i which ε v V o Give: α + ε > ε ( α ) Liear velocit distributio

Διαβάστε περισσότερα

Lecture 2. Soundness and completeness of propositional logic

Lecture 2. Soundness and completeness of propositional logic Lecture 2 Soundness and completeness of propositional logic February 9, 2004 1 Overview Review of natural deduction. Soundness and completeness. Semantics of propositional formulas. Soundness proof. Completeness

Διαβάστε περισσότερα

A Note on Intuitionistic Fuzzy. Equivalence Relation

A Note on Intuitionistic Fuzzy. Equivalence Relation International Mathematical Forum, 5, 2010, no. 67, 3301-3307 A Note on Intuitionistic Fuzzy Equivalence Relation D. K. Basnet Dept. of Mathematics, Assam University Silchar-788011, Assam, India dkbasnet@rediffmail.com

Διαβάστε περισσότερα

Diane Hu LDA for Audio Music April 12, 2010

Diane Hu LDA for Audio Music April 12, 2010 Diae Hu LDA for Audio Music April, 00 Terms Model Terms (per sog: Variatioal Terms: p( α Γ( i α i i Γ(α i p( p(, β p(c, A j Σ i α i i i ( V / ep β (i j ij (3 q( γ Γ( i γ i i Γ(γ i q( φ q( ω { } (c A T

Διαβάστε περισσότερα

k A = [k, k]( )[a 1, a 2 ] = [ka 1,ka 2 ] 4For the division of two intervals of confidence in R +

k A = [k, k]( )[a 1, a 2 ] = [ka 1,ka 2 ] 4For the division of two intervals of confidence in R + Chapter 3. Fuzzy Arithmetic 3- Fuzzy arithmetic: ~Addition(+) and subtraction (-): Let A = [a and B = [b, b in R If x [a and y [b, b than x+y [a +b +b Symbolically,we write A(+)B = [a (+)[b, b = [a +b

Διαβάστε περισσότερα

Sixth Term Examination Papers MATHEMATICS LIST OF FORMULAE AND STATISTICAL TABLES

Sixth Term Examination Papers MATHEMATICS LIST OF FORMULAE AND STATISTICAL TABLES Sixth Term Examiatio Papers MATHEMATICS LIST OF FORMULAE AND STATISTICAL TABLES Pure Mathematics Mesuratio Surface area of sphere = 4πr Area of curved surface of coe = πr slat height Trigoometry a = b

Διαβάστε περισσότερα

Partial Differential Equations in Biology The boundary element method. March 26, 2013

Partial Differential Equations in Biology The boundary element method. March 26, 2013 The boundary element method March 26, 203 Introduction and notation The problem: u = f in D R d u = ϕ in Γ D u n = g on Γ N, where D = Γ D Γ N, Γ D Γ N = (possibly, Γ D = [Neumann problem] or Γ N = [Dirichlet

Διαβάστε περισσότερα

Reminders: linear functions

Reminders: linear functions Reminders: linear functions Let U and V be vector spaces over the same field F. Definition A function f : U V is linear if for every u 1, u 2 U, f (u 1 + u 2 ) = f (u 1 ) + f (u 2 ), and for every u U

Διαβάστε περισσότερα

Bessel function for complex variable

Bessel function for complex variable Besse fuctio for compex variabe Kauhito Miuyama May 4, 7 Besse fuctio The Besse fuctio Z ν () is the fuctio wich satisfies + ) ( + ν Z ν () =. () Three kids of the soutios of this equatio are give by {

Διαβάστε περισσότερα

Inverse trigonometric functions & General Solution of Trigonometric Equations. ------------------ ----------------------------- -----------------

Inverse trigonometric functions & General Solution of Trigonometric Equations. ------------------ ----------------------------- ----------------- Inverse trigonometric functions & General Solution of Trigonometric Equations. 1. Sin ( ) = a) b) c) d) Ans b. Solution : Method 1. Ans a: 17 > 1 a) is rejected. w.k.t Sin ( sin ) = d is rejected. If sin

Διαβάστε περισσότερα

Fourier Series. MATH 211, Calculus II. J. Robert Buchanan. Spring Department of Mathematics

Fourier Series. MATH 211, Calculus II. J. Robert Buchanan. Spring Department of Mathematics Fourier Series MATH 211, Calculus II J. Robert Buchanan Department of Mathematics Spring 2018 Introduction Not all functions can be represented by Taylor series. f (k) (c) A Taylor series f (x) = (x c)

Διαβάστε περισσότερα

Presentation of complex number in Cartesian and polar coordinate system

Presentation of complex number in Cartesian and polar coordinate system 1 a + bi, aεr, bεr i = 1 z = a + bi a = Re(z), b = Im(z) give z = a + bi & w = c + di, a + bi = c + di a = c & b = d The complex cojugate of z = a + bi is z = a bi The sum of complex cojugates is real:

Διαβάστε περισσότερα

5.4 The Poisson Distribution.

5.4 The Poisson Distribution. The worst thing you can do about a situation is nothing. Sr. O Shea Jackson 5.4 The Poisson Distribution. Description of the Poisson Distribution Discrete probability distribution. The random variable

Διαβάστε περισσότερα

Degenerate Perturbation Theory

Degenerate Perturbation Theory R.G. Griffi BioNMR School page 1 Degeerate Perturbatio Theory 1.1 Geeral Whe cosiderig the CROSS EFFECT it is ecessary to deal with degeerate eergy levels ad therefore degeerate perturbatio theory. The

Διαβάστε περισσότερα

FORMULAS FOR STATISTICS 1

FORMULAS FOR STATISTICS 1 FORMULAS FOR STATISTICS 1 X = 1 n Sample statistics X i or x = 1 n x i (sample mean) S 2 = 1 n 1 s 2 = 1 n 1 (X i X) 2 = 1 n 1 (x i x) 2 = 1 n 1 Xi 2 n n 1 X 2 x 2 i n n 1 x 2 or (sample variance) E(X)

Διαβάστε περισσότερα

Ψηφιακή Επεξεργασία Εικόνας

Ψηφιακή Επεξεργασία Εικόνας ΠΑΝΕΠΙΣΤΗΜΙΟ ΙΩΑΝΝΙΝΩΝ ΑΝΟΙΚΤΑ ΑΚΑΔΗΜΑΪΚΑ ΜΑΘΗΜΑΤΑ Ψηφιακή Επεξεργασία Εικόνας Φιλτράρισμα στο πεδίο των συχνοτήτων Διδάσκων : Αναπληρωτής Καθηγητής Νίκου Χριστόφορος Άδειες Χρήσης Το παρόν εκπαιδευτικό

Διαβάστε περισσότερα

Estimation for ARMA Processes with Stable Noise. Matt Calder & Richard A. Davis Colorado State University

Estimation for ARMA Processes with Stable Noise. Matt Calder & Richard A. Davis Colorado State University Estimation for ARMA Processes with Stable Noise Matt Calder & Richard A. Davis Colorado State University rdavis@stat.colostate.edu 1 ARMA processes with stable noise Review of M-estimation Examples of

Διαβάστε περισσότερα

Outline. Detection Theory. Background. Background (Cont.)

Outline. Detection Theory. Background. Background (Cont.) Outlie etectio heory Chapter7. etermiistic Sigals with Ukow Parameters afiseh S. Mazloum ov. 3th Backgroud Importace of sigal iformatio Ukow amplitude Ukow arrival time Siusoidal detectio Classical liear

Διαβάστε περισσότερα

Finite Field Problems: Solutions

Finite Field Problems: Solutions Finite Field Problems: Solutions 1. Let f = x 2 +1 Z 11 [x] and let F = Z 11 [x]/(f), a field. Let Solution: F =11 2 = 121, so F = 121 1 = 120. The possible orders are the divisors of 120. Solution: The

Διαβάστε περισσότερα

Μια εισαγωγή στα Μαθηματικά για Οικονομολόγους

Μια εισαγωγή στα Μαθηματικά για Οικονομολόγους Μια εισαγωγή στα Μαθηματικά για Οικονομολόγους Μαθηματικά Ικανές και αναγκαίες συνθήκες Έστω δυο προτάσεις Α και Β «Α είναι αναγκαία συνθήκη για την Β» «Α είναι ικανή συνθήκη για την Β» Α is ecessary for

Διαβάστε περισσότερα

Uniform Convergence of Fourier Series Michael Taylor

Uniform Convergence of Fourier Series Michael Taylor Uniform Convergence of Fourier Series Michael Taylor Given f L 1 T 1 ), we consider the partial sums of the Fourier series of f: N 1) S N fθ) = ˆfk)e ikθ. k= N A calculation gives the Dirichlet formula

Διαβάστε περισσότερα

SOLVING CUBICS AND QUARTICS BY RADICALS

SOLVING CUBICS AND QUARTICS BY RADICALS SOLVING CUBICS AND QUARTICS BY RADICALS The purpose of this handout is to record the classical formulas expressing the roots of degree three and degree four polynomials in terms of radicals. We begin with

Διαβάστε περισσότερα

Μηχανική Μάθηση Hypothesis Testing

Μηχανική Μάθηση Hypothesis Testing ΕΛΛΗΝΙΚΗ ΔΗΜΟΚΡΑΤΙΑ ΠΑΝΕΠΙΣΤΗΜΙΟ ΚΡΗΤΗΣ Μηχανική Μάθηση Hypothesis Testing Γιώργος Μπορμπουδάκης Τμήμα Επιστήμης Υπολογιστών Procedure 1. Form the null (H 0 ) and alternative (H 1 ) hypothesis 2. Consider

Διαβάστε περισσότερα

6.3 Forecasting ARMA processes

6.3 Forecasting ARMA processes 122 CHAPTER 6. ARMA MODELS 6.3 Forecasting ARMA processes The purpose of forecasting is to predict future values of a TS based on the data collected to the present. In this section we will discuss a linear

Διαβάστε περισσότερα

EN40: Dynamics and Vibrations

EN40: Dynamics and Vibrations EN40: Dyamics a Vibratios School of Egieerig Brow Uiversity Solutios to Differetial Equatios of Motio for Vibratig Systems Here, we summarize the solutios to the most importat ifferetial equatios of motio

Διαβάστε περισσότερα

Chapter 5, 6 Multiple Random Variables ENCS Probability and Stochastic Processes

Chapter 5, 6 Multiple Random Variables ENCS Probability and Stochastic Processes Chapter 5, 6 Multiple Random Variables ENCS6161 - Probability and Stochastic Processes Concordia University ENCS6161 p.1/47 Vector Random Variables A vector r.v. X is a function X : S R n, where S is the

Διαβάστε περισσότερα

Durbin-Levinson recursive method

Durbin-Levinson recursive method Durbin-Levinson recursive method A recursive method for computing ϕ n is useful because it avoids inverting large matrices; when new data are acquired, one can update predictions, instead of starting again

Διαβάστε περισσότερα

Fractional Colorings and Zykov Products of graphs

Fractional Colorings and Zykov Products of graphs Fractional Colorings and Zykov Products of graphs Who? Nichole Schimanski When? July 27, 2011 Graphs A graph, G, consists of a vertex set, V (G), and an edge set, E(G). V (G) is any finite set E(G) is

Διαβάστε περισσότερα

Tridiagonal matrices. Gérard MEURANT. October, 2008

Tridiagonal matrices. Gérard MEURANT. October, 2008 Tridiagonal matrices Gérard MEURANT October, 2008 1 Similarity 2 Cholesy factorizations 3 Eigenvalues 4 Inverse Similarity Let α 1 ω 1 β 1 α 2 ω 2 T =......... β 2 α 1 ω 1 β 1 α and β i ω i, i = 1,...,

Διαβάστε περισσότερα

b. Use the parametrization from (a) to compute the area of S a as S a ds. Be sure to substitute for ds!

b. Use the parametrization from (a) to compute the area of S a as S a ds. Be sure to substitute for ds! MTH U341 urface Integrals, tokes theorem, the divergence theorem To be turned in Wed., Dec. 1. 1. Let be the sphere of radius a, x 2 + y 2 + z 2 a 2. a. Use spherical coordinates (with ρ a) to parametrize.

Διαβάστε περισσότερα

Probability and Random Processes (Part II)

Probability and Random Processes (Part II) Probability and Random Processes (Part II) 1. If the variance σ x of d(n) = x(n) x(n 1) is one-tenth the variance σ x of a stationary zero-mean discrete-time signal x(n), then the normalized autocorrelation

Διαβάστε περισσότερα

Every set of first-order formulas is equivalent to an independent set

Every set of first-order formulas is equivalent to an independent set Every set of first-order formulas is equivalent to an independent set May 6, 2008 Abstract A set of first-order formulas, whatever the cardinality of the set of symbols, is equivalent to an independent

Διαβάστε περισσότερα

The Probabilistic Method - Probabilistic Techniques. Lecture 7: The Janson Inequality

The Probabilistic Method - Probabilistic Techniques. Lecture 7: The Janson Inequality The Probabilistic Method - Probabilistic Techniques Lecture 7: The Janson Inequality Sotiris Nikoletseas Associate Professor Computer Engineering and Informatics Department 2014-2015 Sotiris Nikoletseas,

Διαβάστε περισσότερα

CRASH COURSE IN PRECALCULUS

CRASH COURSE IN PRECALCULUS CRASH COURSE IN PRECALCULUS Shiah-Sen Wang The graphs are prepared by Chien-Lun Lai Based on : Precalculus: Mathematics for Calculus by J. Stuwart, L. Redin & S. Watson, 6th edition, 01, Brooks/Cole Chapter

Διαβάστε περισσότερα