Galton board – Plinko probability

MathematicsProbabilityAges 13–14

Use with my class

Drop balls through a triangular board of pegs: each time a ball hits a peg it bounces right with probability p, and after n rows of pegs it falls into a bin at the bottom. The Intro screen drops 1, 10 or 100 balls through a fixed 12-row board with p = 0.5. The Lab screen lets you change the number of peg rows (1–26) and the probability p with sliders, drop balls continuously, and compare the experimental mean/standard deviation with the theoretical binomial formula C(n,k)pᵏ(1−p)ⁿ⁻ᵏ. Based on the "Plinko Probability" simulation by PhET Interactive Simulations, University of Colorado Boulder (CC BY 4.0); rewritten. The Binomial screen sets n and p and shows the bars P(X = k) = C(n, k)pᵏ(1 − p)ⁿ⁻ᵏ or P(X ≤ k), the mean E(X) = np and variance V(X) = np(1 − p), the probability of an interval a ≤ X ≤ b, the counts of a Galton board beside them, and the normal curve N(np, np(1 − p)) with continuity correction when np and n(1 − p) are both at least 5.

Lesson: Experimental and theoretical probability

What it shows

On a Galton board each ball bounces right with probability p or left with probability 1 − p at every peg, independently of earlier bounces. After n rows the bin number k counts the right bounces, so k follows the binomial distribution P(X = k) = C(n, k)pᵏ(1 − p)ⁿ⁻ᵏ with mean np and variance np(1 − p). When np and n(1 − p) are both at least 5, the normal curve N(np, np(1 − p)) fits the bars well, and interval probabilities are approximated with the continuity correction a − 0.5 to b + 0.5.

How to use

On Intro, press Drop 1 ball, Drop 10 balls and Drop 100 balls and compare the bars with the theoretical curve. On Lab, change Peg rows n and Right-bounce probability p and tick Drop continuously. On Binomial, set Number of trials n, Probability of success p, From k = a and To k = b, switch Show between P(X = k) and P(X ≤ k), tick Normal curve, drop balls, then try the Task.

Parameters you can change

  • Screen Intro, Lab, Binomial
  • Number of peg rows (Intro, p = 0.5) 4–16 rows
  • Starting number of peg rows (Lab) 1–26 rows
  • Starting right-bounce probability p (Lab) 0–1
  • Bin labels Count, Percent
  • Show theoretical curve
  • Lab: start dropping continuously
  • Binomial: number of trials n 1–50
  • Binomial: probability of success p 0–1
  • Binomial: interval from k = a 0–50
  • Binomial: interval to k = b 0–50
  • Binomial: show P(X = k), P(X ≤ k)
  • Binomial: normal curve

Questions to explore

  1. Why do the relative frequencies get closer to P(X = k) as more balls are dropped?
  2. How do the mean np and the spread of the bars change when p moves away from 0.5?
  3. For which values of n and p does the normal curve fit the binomial bars well, and why?

Teaching ideas

All guides