91Ó°ÊÓ

Independent random variables are a key concept in understanding how different probabilistic outcomes do not influence each other. When we have two random variables, say \(N_1\) and \(N_2\), they are independent if the outcome of one does not affect the outcome of the other.

For instance, in a Poisson distribution, if \(N_1\) represents the number of events occurring in one interval and \(N_2\) in another, these counts are independent if events in one interval do not influence the number in the other.

• Formally, independence is expressed as \(P(N_1 = k, N_2 = j) = P(N_1 = k) \cdot P(N_2 = j)\) for all \(k\) and \(j\).
• This multiplication property reflects that knowing the occurrence of \(N_1\) does not change the probability distribution of \(N_2\).

Understanding this property is crucial for analyzing and solving problems involving the summation of independent variables, such as determining the combined event count (\(N = N_1 + N_2\)).

The probability mass function (PMF) is a fundamental tool in understanding discrete random variables, such as those following a Poisson distribution. The PMF gives the probability that a discrete random variable is exactly equal to some value.

In the context of Poisson distribution, the PMF for a random variable \(N\) with parameter \(\lambda\) is given by:

• \(P(N = k) = \frac{e^{-\lambda} \lambda^k}{k!}\)

This formula tells us the probability of exactly \(k\) events occurring in a fixed interval of time or space. Here, \(\lambda\) represents the average number of events per interval, \(e\) is the base of the natural logarithm, and \(k!\) is the factorial of \(k\).

When dealing with the sum of two independent Poisson variables, \(N_1\) and \(N_2\), the resulting random variable \(N = N_1 + N_2\) also follows a Poisson distribution with parameter \(\lambda_1 + \lambda_2\). The PMF remains a crucial aspect to determine how often different event counts occur for \(N\).

Generating functions offer a powerful way to study random variables and their distributions, providing insights into their properties and behavior. For Poisson random variables, the probability generating function (PGF) is a particularly useful tool.

The PGF of a Poisson random variable \(N\) with parameter \(\lambda\) is expressed as:

• \(G_N(s) = e^{-\lambda(1-s)}\)

This generating function allows us to derive important properties of random variables, like their means and variances. When dealing with the sum of two independent Poisson random variables \(N_1\) and \(N_2\), their combined PGF is simply the product of their individual PGFs:

• \(G(s) = G_{N_1}(s) \cdot G_{N_2}(s) = e^{-\lambda_1(1-s)} \cdot e^{-\lambda_2(1-s)}\)
This simplifies to \(e^{-((\lambda_1 + \lambda_2)(1-s))}\), indicating that \(N = N_1 + N_2\) also follows a Poisson distribution, now with the parameter \(\lambda_1 + \lambda_2\). Generating functions, therefore, not only verify the resulting distribution but also provide an elegant way to handle sums of random variables.