11.3.2.2. Derivatives

A moment generating function 𝑀 (𝑡) of a random variable 𝑋 is defined as:

𝑀 (𝑡)= 𝐸[𝑒𝑡𝑋]

provided the expectation exists for 𝑡 in some neighborhood of 0.

The moment generating function (MGF) is a mathematical tool used in probability and statistics. It is a function that helps in calculating the moments (like mean, variance) of a random variable by taking the expected value of an exponential function. Specifically, for a random variable X, we define MGF as M(t) = E[e^(tX)], where E represents the expected value. This means we multiply e^(tX) by the probabilities of the outcomes of X and sum them up. The function is defined around t = 0.

Think of the MGF like a recipe for baking a cake. Just as the recipe specifies the ingredients and their quantities needed to create a cake, the MGF combines different probabilities and outcomes in a specific way (using the exponential function) to help us understand the characteristics of a random variable. By adjusting 't', we can extract different 'moments' similar to understanding different features of the cake like its sweetness (mean) or texture (variance) based on how we mix our ingredients.

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

𝑑𝑟𝑀 (𝑡)

𝑀(𝑟) (0)= 𝑋 | = 𝐸[𝑋𝑟] 𝑋 𝑑𝑡𝑟 𝑡=0

Hence, the r-th moment of 𝑋 is the r-th derivative of the MGF evaluated at 𝑡 = 0.

3. Additivity: For independent random variables 𝑋 and 𝑌:

𝑀 (𝑡) = 𝑀 (𝑡)⋅𝑀 (𝑡) 𝑋+𝑌 𝑋 𝑌

The properties of moment generating functions are crucial in understanding their utility. The first property emphasizes that if an MGF exists for a random variable, it provides a unique identification of that random variable's probability distribution. The second property involves derivatives: the r-th derivative of the MGF evaluated at t=0 will give you the r-th moment of the random variable X. This is powerful because it simplifies the calculation of moments. Lastly, the additivity property indicates that the MGF of the sum of two independent random variables (X and Y) is the product of their individual MGFs. This property is beneficial for calculations involving multiple random variables.

Imagine MGFs as tools in a toolbox. The 'existence' property tells us that having the right tool (MGF) will allow us to repair or understand a specific appliance (distribution) uniquely. The 'derivatives' property is like using a very sharp tool to cut cleanly; it helps us obtain precise measurements (moments) of our appliance. Finally, the 'additivity' property is akin to combining tools: if you know how each tool works independently, you can assemble them to tackle bigger jobs, just like calculating the distribution of combined random variables.

Let’s calculate the first and second moments using the MGF.

• First Moment (Mean): 𝐸[𝑋] = 𝑀 (0) 𝑋′

• Second Moment: 𝐸[𝑋2] = 𝑀 (0) 𝑋″

• Variance: Var(𝑋) = 𝐸[𝑋2]−(𝐸[𝑋])2 = 𝑀 (0)−(𝑀 (0))2 𝑋″ 𝑋′

To calculate the moments of a random variable using its MGF, we can evaluate the MGF at t = 0 for the first moment (mean) and use the first and second derivatives for the calculations of the mean and variance. For the first moment, we get the expected value E[X] as the first derivative of the MGF evaluated at t=0. For the second moment E[X^2], we take the second derivative of the MGF at t=0. The variance is then computed by using the second moment and the first moment to find how much the values of X deviate around the mean.

Imagine you're using a camera to capture sounds at a party. The 'mean' (first moment) would be like taking the average sound level in the room, while the 'second moment' relates to measuring how much louder some sounds are compared to this average. Finally, the 'variance' is akin to calculating how much the noise levels fluctuate around the average sound level as music plays; it shows how chaotic or uniform the party sounds in terms of noises!

--