4. Suppose Yi, Yn are iid randonn variables with E(X) = μ, Var(y)-σ2 < oo. For...
4. Suppose Yi Y, are id randonn variables with E(Y )-μ, Var(Y)= σ2 < o For large n, find the approximaate distribution of YBeure to name any theorems you used.
4 and 5 samples, the other in small samples. Which is which? Explain. (d) Suppose we know that the 5 values are from a symmetric distribution. Then the sample median is also unbiased and consistent for the population mean. The sample mean has lower variance. Would you prefer to use the sample 4. Suppose Yi, Y, are iid r ables with E(n)-μ, Var(K)-σ2 < oo. For large n, find the approximate 5. Suppose we observe Yi...Yn from a normal distribution...
5.13. Suppose X1, X2, , xn are iid N(μ, σ2), where-oo < μ < 00 and σ2 > 0. (a) Consider the statistic cS2, where c is a constant and S2 is the usual sample variance (denominator -n-1). Find the value of c that minimizes 2112 var(cS2 (b) Consider the normal subfamily where σ2-112, where μ > 0. Let S denote the sample standard deviation. Find a linear combination cl O2 , whose expectation is equal to μ. Find the...
3. Let X be a continuous random variable with E(X)-μ and Var(X)-σ2 < oo. Suppose we try to estimate μ using these two estimators from a random sample X, , X,: For what a and b are both estimators unbiased and the relative efficiency of μι to is 45n?
5) Let X be a random variable with mean E(X) = μ < oo and variance Var(X) = σ2メ0. For any c> 0, This is a famous result known as Chebyshev's inequality. Suppose that Y,%, x, ar: i.id, iandool wousblsxs writia expliiniacy" iacai 's(%) fh o() airl íinic vaikuitx: Var(X) = σ2メ0. With Υ = n Ση1 Y. show that for any c > 0 Tsisis the celebraed Weak Law of Large Numben
4. The moment generating function of the normal distribution with parameters μ and σ2 is (t) exp ( μ1+ σ2t2 ) for -oo < t oo. Show that E X)-ψ(0)-μ and Var(X)-ψ"(0)-[ty(0)12-σ2. 5. Suppose that X1, X2, and X3 are independent random variables such that E[X]0 and ElX 1 for i-12,3. Find the value of E[LX? (2X1 X3)2] 6. Suppose that X and Y are random variables such that Var(X)-Var(Y)-2 and Cov(X, Y)- 1. Find the value of Var(3X -...
Suppose that X1,X2, ,Xn are iid N(μ, σ2), where both parameters are unknown. Derive the likelihood ratio test (LRT) of Ho : σ2 < σ1 versus Ho : σ2 > σ.. (a) Argue that a LRT will reject Ho when w(x)S2 2 0 is large and find the critical value to confer a size α test. (b) Derive the power function of the LRT
5.26 Suppose that y is N, (μ, 2), where μ LJ and -σ2ρ for all Thus E(yi-μ for all i, var(yi) 0" for all i, and cov(yoy ij; that is, the y's are equicorrelated. (a) Show that Σ can be written in the form Σ-σ2(I-P)1+a (b) Show that Σ-i(vi-y?/(r2(1-p] is X2(n-1) 5.26 Suppose that y is N, (μ, 2), where μ LJ and -σ2ρ for all Thus E(yi-μ for all i, var(yi) 0" for all i, and cov(yoy ij; that...
CPoisson can not be determined. distribution P(np) ) Suppose X~N(0,1) and YN(24), they are independent, then (is incorrect. DX+Y-N(2, 5) BP(Y <2)>0.5 -Y-N (-2,5) D Var(X) < Var(Y) 5) Suppose X,Xy..,X, (n>1) is a random sample from N(μ,02) , let-ly, is| then Var(x)- ( Instruction: The followins ass
problems binomial random, veriable has the moment generating function, y(t)=E eux 1. A nd+ 1-p)n. Show that EIX|-np and Var(X) np(1-p) using that EIX)-v(0) nd E.X2 =ψ (0). 2. Lex X be uniformly distributed over (a b). Show that ElXI 쌓 and Var(X) = (b and second moments of this random variable where the pdf of X is (x)N of a continuous randonn variable is defined as E[X"-广.nf(z)dz. )a using the first Note that the nth moment 3. Show that...