ECOM40006/ECOM90013 Econometrics 3 Department of Economics University of Melbourne Assignment 1 Solutions Semester 1, 2021 1. In this question we will assume that x ∼ N(µ,Σ) is a p-vector, as is µ, and that the p× p matrix Σ > 0. (a) If v is any fixed p-vector, show that g = v′(x− µ)√ v′Σv ∼ N(0, 1). (1 mark) (b) If v is now a random vector independent of x for which P (v′Σv = 0) = 0, show that g ∼ N(0, 1) and is independent of v. Why have we assumed P (v′Σv = 0) = 0? Can you think of an equivalent statement of this assumption? (4 marks) (c) Hence show that if y = [y1, y2, y3] ′ ∼ N(0, I3) then h = y1e y3 + y2 log |y3| [e2y3 + (log |y3|)2]1/2 ∼ N(0, 1). (2 marks) 2. Suppose that x ∼ N(µ,Σ), where the p × p matrix Σ > 0, and that v is a fixed p-vector. If ri, the ith element of the vector r, is the correlation between xi and v′x, show that r = (cD)−1/2Σv, where c = v′Σv and D = diag(Σ). (3 marks) Bonus question: When does r = Σv? (1 mark) Your answers to the Assignment should be submitted via the LMS no later than 4:30pm, Thursday 1 April. No late assignments will be accepted but an incomplete exercise is better than nothing. 1
欢迎咨询51作业君