No history yet

Exponential PDF Structure

The Exponential PDF

For a continuous random variable, we can't talk about the probability of a single, exact outcome. The chance of an event happening at exactly 3.14159... seconds is zero. Instead, we use a Probability Density Function (PDF) to describe the relative likelihood of outcomes within a range. For the exponential distribution, this function tells us the likelihood of waiting a certain amount of time, x, for an event to occur.

f(x;λ)={λe−λxif x≥00if x<0f(x; \lambda) = \begin{cases} \lambda e^{-\lambda x} & \text{if } x \ge 0 \\ 0 & \text{if } x < 0 \end{cases}

Let's break down the two key players here: xx and λ\lambda.

The variable x represents the waiting time until the event occurs. It’s the value we’re interested in. Since time can't be negative, the support of this distribution is all non-negative real numbers, or x≥0x \ge 0. For any x<0x < 0, the probability density is zero.

The parameter λ\lambda (lambda) is the of the distribution. It represents the average number of events that occur per unit of time. For example, if a call center receives an average of 3 calls per minute, then λ=3\lambda = 3. A higher λ\lambda means events happen more frequently, so the average waiting time for the next event will be shorter. A lower λ\lambda means events are rarer, and you'll likely wait longer.

Calculating the Expected Value

The PDF is our blueprint. To find the expected value, or the average waiting time E[X]E[X], we need to calculate the weighted average of all possible values of xx. For a continuous variable, this means using an integral. The general formula for the expected value of a continuous random variable is:

E[X]=∫−∞∞x⋅f(x) dxE[X] = \int_{-\infty}^{\infty} x \cdot f(x) \,dx

Now, we can plug our exponential PDF into this formula. Since our PDF is zero for any x<0x < 0, our integral's lower bound changes from −∞-\infty to 0. This simplifies things considerably and gives us the specific setup for finding the average waiting time.

E[X]=∫0∞x⋅(λe−λx) dxE[X] = \int_{0}^{\infty} x \cdot (\lambda e^{-\lambda x}) \,dx

Solving this integral requires a technique called integration by parts. Before we dive into that, let's review what we've established.

Ready to check your understanding?

Quiz Questions 1/4

For a continuous random variable, what is the probability of a single, exact outcome occurring (e.g., waiting exactly 5.000... seconds)?

Quiz Questions 2/4

In the context of the exponential distribution, what does the rate parameter, λ (lambda), represent?

Now that we have the integral set up, the next step is to solve it to find a simple expression for the expected value in terms of λ\lambda.