Skip to content
AP Statistics · Probability, Random Variables, and Probability Distributions

Law of Large Numbers

Law of Large Numbers appears in 20 reviewed AP Statistics questions and sits in Probability, Random Variables, and Probability Distributions. Below are worked examples showing exactly how the exam tests it, with the answer marked and every distractor explained.

How Law of Large Numbers is tested

Example 1Easier
A simulation is used to estimate probabilities. A student simulates 500 draws from a bag of colored marbles and finds red marbles in 175 of the draws. What is the estimated probability of drawing a red marble?
  1. A175
  2. B500
  3. C0.65
  4. D0.35Correct

Why D is right

The estimated (empirical) probability is the relative frequency of the event: P(red) ≈ 175/500 = 0.35. By the Law of Large Numbers, this simulation-based estimate should be close to the true probability with a large enough number of trials.
Why the other 3 choices miss
A
175 is the count of red draws, not the probability. Probabilities are expressed as proportions between 0 and 1.
B
500 is the total number of draws (the sample size), not the probability of drawing red.
C
0.65 = 1 - 0.35 is the estimated probability of NOT drawing red (the complement), not the probability of drawing red.
Example 2Harder
A teacher tells students: 'If you flip a coin 1,000 times, you'll get almost exactly 500 heads.' A statistician disagrees. Which of the following BEST captures the correct statistical understanding?
  1. ABoth are wrong — probability is unpredictable and heads count could be anywhere from 0 to 1,000.
  2. BThe teacher is right — with 1,000 flips, you always get exactly 500 heads.
  3. CThe teacher is right only if the coin is perfectly fair to 10 decimal places.
  4. DThe statistician is right — the Law of Large Numbers says the PROPORTION of heads converges to 0.5, but the actual NUMBER of heads will likely deviate from 500 by some amount (typically by about 16 heads in either direction).Correct

Why D is right

The Law of Large Numbers says the PROPORTION of heads converges to 0.5, not that the count is exactly 500. The expected count of heads is 500, but the standard deviation is sqrt(n*p*(1-p)) = sqrt(250) ≈ 15.8. So the count will typically deviate from 500 by about 16 in either direction. The PROPORTION (count/1000) converges to 0.5, but the absolute count has variability.
Why the other 3 choices miss
A
Incorrect because probability does not make all outcomes equally likely in this context. By the CLT and LLN, heads count concentrates around 500 with decreasing relative variability as n grows. Outcomes far from 500 are extremely rare.
B
Incorrect because even a perfectly fair coin will produce a count that varies around 500. Getting exactly 500 heads in 1,000 flips has probability C(1000,500)*(0.5)^1000 ≈ 0.025 — less than 3% chance.
C
Incorrect because the LLN and CLT apply to any fair coin (probability exactly 0.5), and the convergence is probabilistic, not dependent on measurement precision of the fairness.
Example 3Medium
A fair coin is flipped 10,000 times. Let p-hat be the proportion of heads. Which of the following best describes the behavior of p-hat according to the law of large numbers?
  1. Ap-hat will be very close to 0.50 but is unlikely to be exactly 0.50Correct
  2. Bp-hat could be any value between 0 and 1 with equal probability
  3. Cp-hat will compensate for early runs of heads by producing more tails later
  4. Dp-hat will equal exactly 0.50 because the coin is fair

Why A is right

The law of large numbers guarantees that p-hat converges to p = 0.50 as the number of trials increases. With 10,000 flips, p-hat will be very close to 0.50, but random variability means it is extremely unlikely to be exactly 0.50000. The law of large numbers is about convergence in probability, not exact equality.
Why the other 3 choices miss
B
Incorrect. The sampling distribution of p-hat is concentrated near p = 0.50 for large n. It is not uniformly distributed between 0 and 1; extreme values are astronomically unlikely.
C
Incorrect. This describes the 'gambler's fallacy' — the mistaken belief that random processes self-correct. Each flip is independent; the coin has no memory of past results.
D
Incorrect. The law of large numbers does not guarantee exact equality. It guarantees that p-hat gets closer and closer to 0.50 as n increases, but any finite sample will have some deviation.

Studied alongside

Other concepts from Probability, Random Variables, and Probability Distributions.