Course contentsShow
← Data Science
Lesson 156 of 2,1455. Continuous Probability DistributionsFree lesson

Probability Density Functions (PDFs)

Understand how PDFs represent probabilities for continuous variables and why P(X=x) always equals zero.

Probability Density Functions (PDFs)

What You'll Learn

You'll discover how continuous random variables use PDFs to describe probabilities, and why the probability of any single exact value is always zero.

The Challenge with Continuous Variables

Remember discrete random variables? They had specific, countable outcomes—like rolling a die (1, 2, 3, 4, 5, or 6). With continuous variables like height, weight, or time, there are infinitely many possible values in any range. You can't list them all or assign individual probabilities to each one.

What Is a PDF?

A Probability Density Function (PDF) is a curve that describes the relative likelihood of different values for a continuous random variable. Think of it like a smooth landscape of probabilities.

The Key Insight: Area = Probability

Instead of asking "What's the probability of exactly X?", we ask: "What's the probability X falls in a range?"

The PDF gives us densities (heights on the curve), and we find probabilities by calculating the area under the curve between two points.

Analogy: Imagine a PDF as a hill. The height at any point shows density, but to find the probability of landing in a valley, you measure the area of that section—not just the height at one spot.

Why P(X = x) Always Equals Zero

For any single, exact value (like X = 5.00000...), there's no width to create area under the curve. A single point is infinitely thin, so:

P(X = exactly 5) = 0

This doesn't mean it's impossible—it means we must think in ranges: P(4.9 ≤ X ≤ 5.1) has a real, non-zero probability.

Key Properties

  • PDF values are always ≥ 0 (no negative densities)
  • Total area under the PDF = 1 (represents all possible outcomes)
  • Probabilities come from areas, not individual points

Key Takeaway: PDFs describe continuous random variables through density curves where probabilities equal areas under the curve, and any single exact value has zero probability because points have no width.