The Poisson process has independent increments, meaning that the random variables corresponding to the number of events in disjoint time intervals are independent.
Step 1: Analyzing the increments.
The increments \( X = N(6) - N(1) \), \( Y = N(5) - N(3) \), \( W = N(6) - N(5) \), and \( Z = N(3) - N(1) \) all correspond to the number of events in specific time intervals. \( X \) counts the number of events in the interval \( [1, 6] \), with length 5.
\( Y \) counts the number of events in the interval \( [3, 5] \), with length 2.
\( W \) counts the number of events in the interval \( [5, 6] \), with length 1.
\( Z \) counts the number of events in the interval \( [1, 3] \), with length 2. Each of these variables follows a Poisson distribution with parameter \( \lambda \times {length of the interval} \), so:
\( X \sim {Poisson}(10) \)
\( Y \sim {Poisson}(4) \)
\( W \sim {Poisson}(2) \)
\( Z \sim {Poisson}(4) \)
Step 2: Covariance of \( X \) and \( Y \). The covariance of \( X \) and \( Y \) is calculated by considering the overlap between the time intervals of \( X \) and \( Y \). Both \( X \) and \( Y \) share the interval \( [3, 5] \). The covariance of two Poisson random variables with overlapping intervals is equal to the length of the overlapping interval times the rate \( \lambda \). The length of the overlapping interval is 2, and the rate \( \lambda = 2 \), so: \[ {Cov}(X, Y) = \lambda \times {overlap length} = 2 \times 2 = 4 \] Thus, the correct answer is \( \boxed{(D)} \).
Step 3: Verifying other options.
Option (A) is incorrect because \( {Cov}(W, Z) = 0 \), as \( W \) and \( Z \) correspond to independent intervals.
Option (B) is incorrect because \( Y + Z \sim {Poisson}(8) \), not \( {Poisson}(10) \).
Option (C) is incorrect because \( Y \) and \( Z \) are independent, so \( \Pr(Y = Z) \neq 1 \).
Let \( X \) and \( Y \) be discrete random variables with joint probability mass function \[ p_{X, Y}(m, n) = \frac{\lambda^n e^{-\lambda} 2^n m! (n - m)!}{n!}, \quad m = 0, \dots, n, \quad n = 0, 1, 2, \dots, \] where \( \lambda \) is a fixed positive real number. Then which one of the following options is correct?
Let \( (X, Y)^T \) follow a bivariate normal distribution with \[ E(X) = 2, \, E(Y) = 3, \, {Var}(X) = 16, \, {Var}(Y) = 25, \, {Cov}(X, Y) = 14. \] Then \[ 2\pi \left( \Pr(X>2, Y>3) - \frac{1}{4} \right) \] equals _________ (rounded off to two decimal places).
Let \( X_1, X_2 \) be a random sample from a population having probability density function
\[ f_{\theta}(x) = \begin{cases} e^{(x-\theta)} & \text{if } -\infty < x \leq \theta, \\ 0 & \text{otherwise}, \end{cases} \] where \( \theta \in \mathbb{R} \) is an unknown parameter. Consider testing \( H_0: \theta \geq 0 \) against \( H_1: \theta < 0 \) at level \( \alpha = 0.09 \). Let \( \beta(\theta) \) denote the power function of a uniformly most powerful test. Then \( \beta(\log_e 0.36) \) equals ________ (rounded off to two decimal places).
Let \( X_1, X_2, \dots, X_7 \) be a random sample from a population having the probability density function \[ f(x) = \frac{1}{2} \lambda^3 x^2 e^{-\lambda x}, \quad x>0, \] where \( \lambda>0 \) is an unknown parameter. Let \( \hat{\lambda} \) be the maximum likelihood estimator of \( \lambda \), and \( E(\hat{\lambda} - \lambda) = \alpha \lambda \) be the corresponding bias, where \( \alpha \) is a real constant. Then the value of \( \frac{1}{\alpha} \) equals __________ (answer in integer).