11.3.2. Properties of MGFs

1. Existence: If the MGF exists, it uniquely determines the distribution.

This property states that if a moment generating function (MGF) can be calculated for a random variable, it contains all the information needed to identify the corresponding probability distribution. Thus, knowing the MGF allows statisticians to understand the characteristics of the random variable it represents. MGFs are valuable because they enable us to analyze the random variable without needing to evaluate the complete probability distribution directly.

Think of the MGF as a unique recipe for a dish. If you know the recipe (the MGF), you can recreate that dish (the probability distribution) exactly as it is. If someone has the same recipe, they will end up cooking the same dish, highlighting the uniqueness of the MGF for the specific distribution.

2. Derivatives: $$\frac{d^{r} M_{X}(t)}{dt^{r}} \bigg|_{t=0} = E[X^{r}]$$ Hence, the r-th moment of 𝑋 is the r-th derivative of the MGF evaluated at $t = 0$.

This property explains how we can derive the moments of the random variable using its MGF. The r-th moment can be found by calculating the r-th derivative of the MGF and evaluating it at t = 0. This means that if we want to calculate, say, the third moment of the variable, we would differentiate the MGF three times and then substitute t = 0 into the resulting expression. This offers a straightforward computational method to find moments.

Imagine you’re observing the growth of a plant. Each time you measure its height (first moment), its growth rate (second moment), and its growth acceleration (third moment), you are looking at different aspects of its growth process. The MGF is like a magical tool that gives you all this information just by adjusting a knob (taking derivatives) and checking at the base level (t = 0).

3. Additivity: For independent random variables 𝑋 and 𝑌: $$M_{X+Y}(t) = M_{X}(t) \cdot M_{Y}(t)$$

The additivity property of MGFs states that if you have two independent random variables X and Y, the MGF of their sum (X + Y) can be obtained by multiplying their individual MGFs. This property simplifies the process of finding the MGF for the sum of random variables, which is particularly useful in many applications, such as the central limit theorem. It shows how the combined effect of two independent variables can be represented together.

Think of X and Y as two different sources of income, say a job and a rental property. If you want to find out your total monthly income from both sources, you can simply add them together. The MGF facilitates this addition process mathematically by providing a way to combine their individual distributions into one.

--