Você está na página 1de 7
Table of Common Distributions Discrete Distributions Bernoulli) pmg P(X = 2p) = (1-9) 8 mean and iy Tonince, EX =P. VarX=y(1-p) maf Mx(t) = (1 —p) + pet Binomial(n, p) emp P(X =2In,p)= CU ~ pA F=012,....m5 OS PST mean and py _ = Tanunee, EX=np, VarX =np(l~p) maf Mx(t) = [pet + (= notes Related to Binomial Theorem (Theorem 3.2.2), The multinomial distri- bution (Definition 4.6.2) is a multivariate version of the binomial distri- bution Discrete uniform —LL———— maf Mx)= Dive Geometric(p) 7 pomp PX =ap)= mt z= L253 OSPST mean ond py _ variance =o VarX Le on maf notes Hypergeometric preg P(X = 2|N,M,K) = B= 041,200) K5 M-(N-K)<20 mean and py = KY, Var x = KEENE notes ‘i K 0, 2>0 mean and py _ ot variance sa maf Mx(t) = 1+, (Ito ati) & notes ‘The constant in the beta pdf can be defined in terms of gamma functions, B(a,8) = WEE. Equation (3.2.18) gives a general expression for the moments Cauchy(0,0) pdf Mele) = degaplaap ~ee0 eens do not exist variance maf does not exist notes Special case of Student’ t, when dogrees of freedom = 1. Also, if X and ¥ are independent n(0, 1), X/Y is Cauchy. Chi squared(p) pdf Lele) = ght 1-2, 0 F(z\m0) EX =y, VarX =20? Mx(t) = rf ith < Also known as the Laplace distribution. ext ‘TABLE OF COMMON DISTRIBUTIONS Exponential(?) af S(2l8) = fe*!?, 0<2 0 mean and 4) SarRAS EX =8, VarX = 8? mf — Mx(t)=y, teh notes Special case of the gamma distribution. Has the’ memoryless property. las many special cess: ¥ = X'/" is Weill Y = /2¥3 ts Rayleigh ax—Viog(X/8) is Gumbel F — (332) 7)? geen af fel) = satay (8) EE O? VarX =2(st25) RASB, wy >4 moments en oat ia not esa) °X*= SRE) (p)", ng notes _Related to chi squared (Fiyya = (3) / (8). where the 3% exe in- dependent) and t (Fi, = #2). Gamma(a, 3) pdf H(ela,3) = pyre? 129, 0<2<00, 48 >0 mean and px a0, VarX=aF maf Mx(t)=(3x)"s <5 notes Some special cases are exponential (a = 1) and chi squared (a= p/2, 8 = 2). a= 3, ¥ = /X/B is Maxwell. Y = 1/X has the inverted gamma distribution. Can also be related to the Poisson (Example 3.2.1). Logistie(u, 8) pag Iele,8) = bpm, -oo< 2 <0, -oo0 moon end px ay, Vark = 2 ‘TABLE OF COMMON DISTRIBUTIONS: o2, of Mx(t) = eP(1- BET +.Bt), [t\<} notes ‘The cdf is given by F(z|u,8) = a=d-ave. Lognormal( 1,02) pdf S(aluso*) = zee O<2<00, -00<"0 mean and py gui(o*/2}, Var X = elivto?) — etuto® variance moments na grentonle (maf does not exist) EX" = notes _ Example 2.3.5 gives another distribution with the same moments. Normal(:,0?) pap Salo) = Ghee EWA), oo << 00, -00< p< om, o>0 mean ond By oy Ver X =o? variance ie maf Me(t) = eutvors2 notes Sometimes called the Gaussian distribution. Pareto(a, 8) pdf flzla,8) = By, a0, B>0 ‘mean andl tenance, EX=P% O>1, VarX= fle, 8>2 maf does not exist t vif Ape ee mean and ie mean ond py 9, y>1, VarX vse nei exr = 8 ae v™/? ifn 0, B>0 mean and ver (ved a a= ee, EX= VT (142), Varx =6¥7[P(1+2)—-r7(1+2)] moments EX" = pvr (142) notes The mgf exists only for 7 > 1. Its form is not very useful. A special case is exponential (+) = 1) ‘TABLE OF COMMON DISTRIBUTIONS or = EE. - mix Yfke] avast fiewtionty roe 2, [Riprscomanie beats Pas [evee Binal], p= MIN nm oP EO Nm = Feat] 22m-p aL ast) Uniform >. 108 x min X, a XK y/o Weibal Dost Gn exponeatil Relationships among common distributions. Solid lines represent transformations and special cases, dashed lines represent limits. Adapted from Leemis (1986).

Você também pode gostar