Convergence in Distribution
What You'll Learn
You'll learn what it means for a sequence of random variables to converge in distribution to another random variable—particularly to the normal distribution via the Central Limit Theorem.
The Core Idea
Imagine you have a sequence of random variables: X₁, X₂, X₃, ... Each has its own distribution. Convergence in distribution (also called convergence in law) means that as n grows, the cumulative distribution function (CDF) of Xₙ gets closer and closer to the CDF of some limiting random variable X.
Formally, we say Xₙ converges in distribution to X if:
lim F_Xₙ(x) = F_X(x)
n→∞
at every point x where F_X is continuous.
Why It Matters for the CLT
When you standardize the sample mean of n independent, identically distributed variables (as you learned in lesson 2978-2979), the Central Limit Theorem says this standardized quantity converges in distribution to the standard normal distribution Z ~ N(0,1).
This doesn't mean the random variables themselves become normal—it means their probability distribution behaves more and more like a normal distribution as n increases. Think of it like a sequence of histograms gradually morphing into the bell curve.
Compared to Other Convergence Types
Convergence in distribution is weaker than convergence in probability (lesson 2971). A sequence can converge in distribution without the actual values getting close. What converges are the probabilities, not necessarily the outcomes themselves.
Key Takeaway: Convergence in distribution means the CDF of a sequence of random variables approaches the CDF of a limiting distribution—this is how the CLT guarantees that standardized averages become approximately normal.