Exponential Distribution: PDF and CDF
What you'll learn: How to write and use the probability density and cumulative distribution functions for exponential random variables.
The Core Idea
The exponential distribution describes continuous waiting times between events in a Poisson process. You've seen it models "time until the next event" — now let's formalize its mathematical functions.
The distribution has one parameter: λ (lambda), called the rate parameter. It represents the average number of events per time unit. A higher λ means shorter typical waiting times.
The PDF: Probability Density Function
The PDF describes the relative likelihood of different waiting times:
f(x; λ) = λe^(-λx) for x ≥ 0
- x is the waiting time
- λ is the rate
- e is Euler's number (~2.718)
The curve starts at height λ when x=0 and decays exponentially toward zero. This reflects that short waits are more likely than long ones.
The CDF: Cumulative Distribution Function
The CDF gives the probability that the wait is at most x time units:
F(x; λ) = 1 - e^(-λx) for x ≥ 0
This accumulates all probability from 0 up to x. As x increases, F(x) approaches 1 (certainty).
Quick Example
If customers arrive at rate λ = 2 per hour:
- PDF at x=0.5 hours: f(0.5; 2) = 2e^(-1) ≈ 0.736
- CDF at x=0.5 hours: F(0.5; 2) = 1 - e^(-1) ≈ 0.632 (63.2% chance wait is ≤30 min)
Key Takeaway: The exponential distribution is fully determined by rate λ, with PDF f(x) = λe^(-λx) measuring density and CDF F(x) = 1 - e^(-λx) measuring cumulative probability up to time x.