[ARCHIMEDES] Suppose that Xo = 2/3, yo = 3, xn = 2xn-1 Yn-1 xn-1 + Yn-1 and Yn = 1xn Yn-1 for ne N. a) Prove that xnx and Yn 1 y, as n = , for some x, y E R. b) Prove that x = y and 3.14155 < x < 3.14161. (The actual value of x is a.)
Consider a sequence of random variables X1, ..., Xn, ..., where for each n, Xn~ tn. We will use Slutsky's Theorem to show that as the degrees of freedom go to infinity, the distribution converges to a standard normal. (a) Let V1, ..., Vn, ... be such that Vn ~ X2. Find the value b such that Vn/n þy b. (b) Letting U~ N(0,1), show that In = ☺ ~tn and that Tn "> N(0,1). VVn/n
Let Xi, X2, , xn be independent Normal(μ, σ*) random variables. Let Yn = n Ση1Xi denote a sequence of random variables (a) Find E(%) and Var(%) for all n in terms of μ and σ2. (b) Find the PDF for Yn for all n c) Find the MGF for Y for all n
& Let Yn = ao Xn ta, x n- do xn + a, Xn-1 ; n =1,2,... where Xi are iid RVs u ; n = 1, 2, with equal moon o and va siance 2.1 95 { yn in 21% SSS? Is {Yn: n 21 } WSS?
Exercise 7. Let Xi, X2, . . . be independent, identically distributed rundorn variables uithEX and Var(X) 9, and let Yǐ = Xi/2. We also define Tn and An to be the sum and the sample mean, respectively, of the random variablesy, ,Y,- 1) Evaluate the mean and variance of Yn, T,, and A (2) Does Yn converge in probability? If so, to what value? 3) Does Tn converge in probability? If so, to what value? (4) Does An converge...
Let Xo and Xı be independent exponentially distributed random variables with re- spective parameters Ao and ^i, so that, P(Xi t)eAit, for t2 0, i = 0,1 Let 0 if Xo X1, N = 1 if X1X0, min{Xo, X1}, M = 1 - N, V = x{X0, X1}, and W = V -U = |X0 - X1]. and U max Verify that U XN and V XM, then find the following: (a) P(N 0, U > t), for t 2...
Suppose that the data (X1, Y), ... (Xn, Yn is generated by the following ("true") model: a+ bX; + сX; +ei, where a, b, c are some parameters and ei are independent errors with zero mean and variance a2. Suppose that we fit the simple linear regression model to the data (i.e. we ignore the quadratic term cX2) using the OLS method. Find the expectation of the residual from the fit. Suppose that the data (X1, Y), ... (Xn, Yn...
We have a dataset with n = 10 pairs of observations (xi; yi), and Xn i=1 xi = 683; Xn i=1 yi = 813; Xn i=1 x2i = 47; 405; Xn i=1 xiyi = 56; 089; Xn i=1 y2 i = 66; 731: What is an approximate 95% confidence interval for the mean response at x0 = 90? We have a dataset with n = 10 pairs of observations (li, Yi), and n n Σ Xi = 683, Yi =...
6. Suppose we have i.id. Xi, , Xn ~ N(μ, σ2). In the class, we learned that Σί i m(Xi-X) X2-1. Use this fact and answer the following questions. (a) Consider an estimator σ-c Σηι (Xi-X)2. Find its mean and variance.
Let Xi....,Xn,..., ~iid Exp(1) and let Yn) be the sample maximum of the first n observations. Show that the limiting distribution of Zn-(Y(n)-log n) has CDF F(z) exp{-e-*), z є R.