Page 253 - Probability and Statistical Inference
P. 253

230    4. Functions of Random Variables and Sampling Distribution

                                 U will be zero when u ≤ 0 or u ≥ 2, but it will be positive when 0 < u < 2.
                                 Thus, using the convolution result, for 0 < u < 1, we can write the df of U as
                                                                                   . Hence, for 0 < u
                                 < 1 we have                 .  On the other hand, for 1 ≤ u < 2, we can

                                 write the df of  U as
                                                                      so that
                                    4.2.10 Suppose that X  and X  are independent random variables, distrib-
                                                             2
                                                      1
                                 uted uniformly on the intervals (0, 1) and (0, 2) with the respective pdf’s
                                 f (x ) = I(0 < x  < 1) and f (x ) = 1/2I(0 < x  < 2). Use the convolution result
                                                       2
                                                                     2
                                  1
                                                         2
                                             1
                                    1
                                 to derive the form of the pdf g(u) of U = X  + 1/2X  with 0 < u < 2.
                                                                             2
                                                                      1
                                    4.2.11 (Example 4.2.10 Continued) Let U, V be iid N(µ, σ ). Find the pdf
                                                                                     2
                                 of W = U + V by the convolution approach. Repeat the exercise for the
                                 random variable T = U – V.
                                    4.2.12 (Example 4.2.11 Continued) Provide all the intermediate steps in the
                                 Example 4.2.11.
                                    4.2.13 Prove a version of the Theorem 4.2.1 for the product, V = X X , of
                                                                                            1 2
                                 two independent random variables X  and X  with their respective pdf’s given
                                                                      2
                                                                1
                                 by  f (x ) and  f (x ). Show that the pdf of  V is given by  h(v) =
                                        1
                                     1
                                                  2
                                                2
                                                          for v ∈ ℜ. Show that h(v) can be equivalently
                                 written as                      . {Caution: Assume that V can not take
                                 the value zero.}
                                    4.2.14 Suppose that X , X , X  are iid uniform random variables on the
                                                       1
                                                             3
                                                          2
                                 interval (0, 1).
                                    (i)   Find the joint pdf of X , X , X ;
                                                             3:1  3:2  3:3
                                    (ii)  Derive the pdf of the median, X ;
                                                                     3:2
                                    (iii)  Derive the pdf of the range, X  – X .
                                                                         3:1
                                                                   3:3
                                 {Hint: Use the Exercise 4.2.7}
                                    4.2.15 Suppose that X , ..., X  are iid N(0, 1). Let us denote Y  = 4Φ(X )
                                                                                                 i
                                                             n
                                                                                         i
                                                       1
                                 where                                            .
                                    (i) Find the pdf of the random variable
                                    (ii) Evaluate E[U] and V[U];
                                    (iii) Find the marginal pdf’s of Y , Y  and Y  – Y .
                                                                n:1  n:n    n:n  n:1
                                    4.2.16 Suppose that X  is uniform on the interval (0, 2), X  has its pdf 1/
                                                      1
                                                                                     2
                                                                 2
                                 2xI(0 < x < 2), and X  has its pdf 3/8x I(0 < x < 2). Suppose also that X , X ,
                                                   3
                                                                                                2
                                                                                             1
                                 X  are independent. Derive the marginal pdf’s of X  and X . {Hint: Follow
                                                                            3:1
                                                                                   3:3
                                  3
                                 along the Example 4.2.8.}
   248   249   250   251   252   253   254   255   256   257   258