The Gamma Distribution: Definition and Parameters
You'll learn: How to define the gamma distribution using its shape and rate parameters, and what these parameters control.
What Is the Gamma Distribution?
The gamma distribution is a flexible continuous distribution that generalizes the exponential distribution to model waiting times for multiple events. While the exponential distribution describes the time until the first event, the gamma distribution describes the time until the α-th event in a Poisson process.
Definition and PDF
The gamma distribution is characterized by two parameters:
- α (alpha): the shape parameter (α > 0)
- β (beta): the rate parameter (β > 0)
For a random variable X following a gamma distribution, the probability density function is:
f(x; α, β) = (β^α / Γ(α)) · x^(α-1) · e^(-βx) for x > 0
where Γ(α) is the gamma function you just learned about.
Interpreting the Parameters
-
Shape (α): Controls the "shape" of the distribution. When α = 1, you get the exponential distribution. Larger α values shift the distribution right and make it more bell-shaped. You can think of α as "how many events you're waiting for."
-
Rate (β): Controls how quickly events occur. Larger β compresses the distribution leftward (events happen faster); smaller β stretches it rightward (events happen slower). This is the same rate parameter as in the exponential distribution.
Analogy: If you're waiting for α = 3 buses that arrive at rate β = 2 per hour, the gamma distribution describes your total waiting time.
Key Takeaway: The gamma distribution with shape α and rate β models the sum of α independent exponential(β) random variables, with PDF involving the gamma function as a normalizing constant.