THE VR SCHOOL
  • Schools & Districts
    • License the academy
    • Free program for your students
    • Request a demo
  • Catalog
    • AI & Data
    • Cybersecurity & Web
    • Programming
    • Health Science
    • All Guilds
    • All courses
  • Families
  • Accreditation
  • Log In
  • Request a demo
  • Home
  • Courses

RLP Statistics A — Exploring Data, Study Design and Probability

Curriculum

  • 4 Sections
  • 20 Lessons
  • 10 Weeks
Expand all sectionsCollapse all sections
  • Unit 1: Exploring One-Variable Data
    5
    • 1.1
      Distributions and the Statistical Process
      50 mins
    • 1.2
      Measuring Center and Spread
      50 mins
    • 1.3
      Comparing Distributions Across Missouri
      50 mins
    • 1.4
      Standardizing, Transforming and Reporting
      50 mins
    • 1.5
      Performance Task — Climate Station Profile
      150 mins
  • Unit 2: Two-Variable Data and Regression
    5
    • 2.1
      Scatterplots and Correlation
      50 mins
    • 2.2
      Least-Squares Regression
      50 mins
    • 2.3
      Residuals, Influence and Causation
      50 mins
    • 2.4
      Exponential Models and the Limits of Extrapolation
      50 mins
    • 2.5
      Performance Task — Bivariate Investigation Report
      150 mins
  • Unit 3: Designing Studies: Samples and Experiments
    5
    • 3.1
      Populations, Samples and Bias
      50 mins
    • 3.2
      Simulating Sampling Variability and the Margin of Error
      50 mins
    • 3.3
      Experiments, Observational Studies and Confounding
      50 mins
    • 3.4
      Comparing Treatments with a Randomization Test
      50 mins
    • 3.5
      Performance Task — Design, Run and Report a Study
      150 mins
  • Unit 4: Probability, Random Variables and the Binomial Model
    5
    • 4.1
      Probability Rules and Two-Way Tables
      50 mins
    • 4.2
      The Multiplication Rule, Trees and Counting
      50 mins
    • 4.3
      Random Variables, Expected Value and Variance
      50 mins
    • 4.4
      The Binomial Model
      50 mins
    • 4.5
      Performance Task — Expected-Value Decision Analysis
      150 mins

The Binomial Model

Unit 4  ·  Modeling & Reporting Workshop  ·  Lesson 19 of 20

The Binomial Model

PS.7RLP-STATSA
Hands arrange fourteen two-sided tokens into repeated binary outcome sequences, highlighting rows with few successes.
By the end of this lesson I can…

recognize binomial settings, compute binomial probabilities, means and standard deviations, and test whether a binomial model fits real data.

Instruction

The binomial setting. A random variable X has a binomial distribution when four conditions hold:

  1. Binary: each trial is a success or a failure.
  2. Independent: trials do not affect one another.
  3. Number fixed: there are n trials, decided in advance.
  4. Same probability: each trial has the same success probability p.

X counts the successes in the n trials.

Deriving the formula. One particular sequence with k successes and n − k failures (say SSF…) has probability pk(1 − p)n−k by the multiplication rule for independent events. There are C(n, k) different sequences with exactly k successes, one for each choice of which trials succeed. So

P(X = k) = C(n, k)·pk(1 − p)n−k,   k = 0, 1, …, n

The PS.3 example. What is the probability of five or fewer heads in 14 tosses of a fair coin? Here n = 14, p = 0.5, and every sequence has probability 0.514 = 1/16,384. Count the sequences: C(14, 0) + C(14, 1) + … + C(14, 5) = 1 + 14 + 91 + 364 + 1,001 + 2,002 = 3,473. So P(X ≤ 5) = 3,473/16,384 ≈ 0.212. In a spreadsheet: =BINOM.DIST(5, 14, 0.5, TRUE).

Mean and standard deviation (PS.5, PS.6). A binomial count is a sum of n independent trials, each with mean p and variance p(1 − p), so

μ = np     σ = √(np(1 − p))

An application (illustrative). A basketball player makes 70% of free throws; assume independent shots. This rate is illustrative. In 10 attempts, X ~ Binomial(10, 0.7): μ = 7, σ = √2.1 ≈ 1.45. P(X = 7) = C(10, 7)(0.7)7(0.3)3 ≈ 0.267, and P(X ≥ 8) ≈ 0.383. Even for a 70% shooter, making 8 or more of 10 happens less than half the time.

Testing the model on real data (A2.DS.A.2). Is the number of rainy days in a St. Louis January week binomial? Treat each day as a trial with p = the observed fraction of rainy days, January 1-28 of 2000-2024: p = 199/700 ≈ 0.284. With n = 7, the binomial model predicts, for 100 weeks:

rainy days01234567
binomial expects9.626.731.921.18.42.00.30.0
observed1722281713030

The means agree (np = 7 × 0.284 ≈ 1.99), and the middle of the distribution is close. The spread is not. The binomial variance is np(1 − p) ≈ 1.42, while the observed variance is 2.07, about 1.45 times as large. The model expects about 10 completely dry weeks, and 17 happened. It expects about 11 weeks with four or more rainy days, and 16 happened, three of them with six rainy days. The failed condition is independence: as Lesson 4.1 showed, rain today makes rain tomorrow more likely, so rainy days cluster into wet weeks and dry spells. A model is consistent with data only if its assumptions match the process. Here, checking the model taught us something true about Missouri winter weather. The reading repeats the check on Kansas City July heat, where the failure is clearer: 90°F days cluster in hot spells and the observed variance is about 2.5 times the binomial’s.

Tools. Spreadsheet: BINOM.DIST(k, n, p, FALSE) for P(X = k) and TRUE for P(X ≤ k). GeoGebra’s Probability app shows the distribution and shades areas.

📖 Read for this lesson

The reading opens over the lesson; close it to come back to exactly where you were. The checks below draw on it.

  • Binomial Tables for the Lesson’s Three Settings, and a Second Real Model CheckBinomial probability tables for (7, 0.284), (10, 0.7) and (14, 0.5), computed for this course; Kansas City International (USW00003947) July daily maximum temperatures 2000-2024 from NOAA GHCN-Daily; retrieved November 10, 2026 · about 4 min

    Full binomial tables for the lesson’s three settings and a second real model check, on Kansas City heat weeks, where independence fails even harder than for rain.

Vocabulary in context

  • binomial distribution — The distribution of the number of successes in n independent trials, each with success probability p.
  • binomial coefficient — C(n, k), the number of ways to choose which k of the n trials are successes.
  • trial — One repetition of the chance process, ending in success or failure.
  • model check — Comparing a model’s predictions with observed data to see whether its assumptions hold.

Formative check

Work through these before moving on. They are not graded — they tell you whether the standard below has landed yet.

+50 XP

What is P(5 or fewer heads in 14 tosses of a fair coin)?

Add C(14, k) for k = 0 to 5 (3,473 sequences) and divide by 2¹⁴ = 16,384. C(14, 5) alone gives only P(X = 5).

Simulation & tools

Plinko: where does the binomial come from?

Open the Lab screen. Set 14 rows and binary probability 0.5. Each ball makes 14 left/right bounces, so the bin it lands in is a Binomial(14, 0.5) count.

  1. Drop 1,000 balls (use the continuous button). Record the fraction landing in bins 0-5. Compare with 3,473/16,384 ≈ 0.212.
  2. Record the sim’s mean and SD and compare with np = 7 and √(np(1 − p)) ≈ 1.87.
  3. Change the probability to 0.3 and predict the new mean and SD before dropping balls, then check.

Question: which binomial condition would a real ball violate if bouncing right made the next bounce more likely to go right? No sim: toss 14 coins (or use =RANDBETWEEN(0,1) in 14 spreadsheet cells) 50 times and record the counts.

Open in a new tab ↗  ·  PhET Interactive Simulations, University of Colorado Boulder · CC BY 4.0

Myth or Fact?

The binomial model reproduces the spread of rainy days in a St. Louis January week, because its mean (1.99) matches the observed mean.

The means match, but the model’s variance (1.42) is well below the observed 2.07, and it expects about 10 dry weeks where 17 occurred. The independence condition fails.

A 70% free-throw shooter takes 10 shots. Compute P(X = 10), P(X ≥ 8), the mean and the SD, with the formula for one of them and BINOM.DIST for the rest. Then name a real reason a player’s shots might not be independent, and explain how that would change the distribution’s spread. Check your values against the table in the reading.

0 words
Quick self-check

How confident are you that you can compute binomial probabilities, means and SDs, and check whether a binomial model fits real data?

Not yetVery confident

Practice

Work these on paper or in your notebook, then open Check your answer. Aim for all of Fluency and Application; try at least one Challenge.

Printable version: this unit’s practice workbook (PDF)

Fluency

Build speed and accuracy with the core skill.

  1. X ~ Binomial(n = 7, p = 0.25). Find P(X = 6), P(X ≤ 6), and the mean and standard deviation of X.
    Check your answer
    Answer: P(X = 6) ≈ 0.0013; P(X ≤ 6) ≈ 0.9999; mean 1.75; SD ≈ 1.146
    P(X = k) = C(7, k) pk(1 − p)n−k.
  2. X ~ Binomial(n = 7, p = 0.2). Find P(X = 3), P(X ≤ 3), and the mean and standard deviation of X.
    Check your answer
    Answer: P(X = 3) ≈ 0.1147; P(X ≤ 3) ≈ 0.9667; mean 1.40; SD ≈ 1.058
    P(X = k) = C(7, k) pk(1 − p)n−k.
  3. X ~ Binomial(n = 8, p = 0.5). Find P(X = 6), P(X ≤ 6), and the mean and standard deviation of X.
    Check your answer
    Answer: P(X = 6) ≈ 0.1094; P(X ≤ 6) ≈ 0.9648; mean 4.00; SD ≈ 1.414
    P(X = k) = C(8, k) pk(1 − p)n−k.
  4. X ~ Binomial(n = 17, p = 0.75). Find P(X = 8), P(X ≤ 8), and the mean and standard deviation of X.
    Check your answer
    Answer: P(X = 8) ≈ 0.0093; P(X ≤ 8) ≈ 0.0124; mean 12.75; SD ≈ 1.785
    P(X = k) = C(17, k) pk(1 − p)n−k.
  5. X ~ Binomial(n = 10, p = 0.25). Find P(X = 6), P(X ≤ 6), and the mean and standard deviation of X.
    Check your answer
    Answer: P(X = 6) ≈ 0.0162; P(X ≤ 6) ≈ 0.9965; mean 2.50; SD ≈ 1.369
    P(X = k) = C(10, k) pk(1 − p)n−k.
  6. X ~ Binomial(n = 13, p = 0.2). Find P(X = 10), P(X ≤ 10), and the mean and standard deviation of X.
    Check your answer
    Answer: P(X = 10) ≈ 0.0000; P(X ≤ 10) ≈ 1.0000; mean 2.60; SD ≈ 1.442
    P(X = k) = C(13, k) pk(1 − p)n−k.
  7. Which condition of the binomial setting fails? Counting how many of the next 7 days are rainy in St. Louis in January.
    Check your answer
    Answer: Independence: rainy days cluster.
  8. Which condition fails? Drawing 5 cards without replacement from a deck and counting hearts.
    Check your answer
    Answer: Same probability / independence: each draw changes the deck (the draws are not independent).

Application

Use the skill in context. Show your reasoning.

  1. (Illustrative) A 70% free-throw shooter takes 10 independent shots. Find P(X = 10), P(X ≥ 8), the mean and the SD.
    Check your answer
    Answer: P(X = 10) ≈ 0.0282; P(X ≥ 8) ≈ 0.3828; mean 7; SD ≈ 1.449.
  2. For Kansas City July weeks, the fraction of July 1-28 days at or above 95°F is p = 125/700 ≈ 0.179. A Binomial(7, 0.179) model predicts, for 100 weeks: 25.2, 38.4, 25.0, 9.1, 2.0, 0.3, 0.0, 0.0 weeks with 0,…,7 hot days. The observed counts were 53, 14, 15, 6, 4, 3, 3, 2. Does the binomial model fit? Explain.
    Check your answer
    Answer: No. It predicts about 25 weeks with no hot days where 53 occurred, and fewer than one week (about 0.3) with six or seven hot days where 5 occurred; the observed variance (3.17) is about 3.1 times the binomial’s (1.03). Hot days cluster in heat waves, so independence fails.
    The means agree (7p = the observed mean); the spread does not.
  3. A quiz has 12 multiple-choice questions with 4 options each. A student guesses on every question. Find the probability of 6 or more correct.
    Check your answer
    Answer: P(X ≥ 6) ≈ 0.0544.
    X ~ Binomial(12, 0.25).

Challenge

Stretch problems. Expect to think before you write.

  1. Show directly that a Binomial(2, p) random variable has mean 2p and variance 2p(1 − p).
    Check your answer
    Answer: P(0) = (1 − p)², P(1) = 2p(1 − p), P(2) = p². E(X) = 2p(1 − p) + 2p² = 2p. E(X²) = 2p(1 − p) + 4p² = 2p + 2p². Var = 2p + 2p² − 4p² = 2p − 2p² = 2p(1 − p).

Review

Keep earlier skills sharp.

  1. (Lesson 4.3) A game pays $10 with probability 0.2 and −$2 otherwise. Find the expected value.
    Check your answer
    Answer: $0.40.
  2. (Unit 2) A line predicts y = 20 + 1.5x. For the point (10, 38), find the residual.
    Check your answer
    Answer: Predicted 35; residual 3.
    Residual = actual − predicted.

Missouri Learning Standards — Mathematics (data and probability) addressed: A2.DS.B.8, G.CP.A.2, A2.DS.A.2, MP.4

Extends beyond Missouri Statistics (enrichment): content Missouri places after Statistics

Instructional focus: Derivation, application and empirical testing of the binomial distribution

Reading

Binomial Tables for the Lesson’s Three Settings, and a Second Real Model Check

Binomial probability tables for (7, 0.284), (10, 0.7) and (14, 0.5), computed for this course; Kansas City International (USW00003947) July daily maximum temperatures 2000-2024 from NOAA GHCN-Daily; retrieved November 10, 2026 · SLS original (computed tables), with public-domain NOAA data

Why this reading. The lesson computes binomial probabilities for three settings and checks the model against the January rainfall weeks. Here are the full tables for all three, so any probability the lesson or your tool reports can be looked up, and a second real model check on the Kansas City heat weeks from the Lesson 4.3 reading, where the binomial model fails more clearly, for the same reason.

Table 1. Binomial(7, 0.284): rainy days in a St. Louis January week if days were independent

p = 199/700 = 0.2843, the fraction of rainy days across the 100 weeks. Mean np = 1.99; SD √(np(1 − p)) = 1.193; variance 1.42.

k01234567
P(X = k)0.09620.26750.31870.21100.08380.02000.00260.0002
P(X ≤ k)0.09620.36370.68240.89340.97720.99720.99981.0000
Expected weeks of 1009.626.731.921.18.42.00.30.0
Observed weeks1722281713030

The expected row is the lesson’s (9.6, 26.7, 31.9, 21.1, …). The means agree (as they must: p was estimated from these same days), and the middle of the distribution is close. The spread is not: the observed variance, 2.07, is 1.45 times the binomial variance of 1.42. The model expects 9.6 completely dry weeks and 17 occurred; it expects 10.7 weeks with four or more rainy days and 16 occurred, including three with six rainy days, which the model would produce about once in 380 weeks.

Table 2. Binomial(10, 0.7): the free-throw shooter (illustrative rate)

Mean 7, SD √2.1 = 1.449.

k012345678910
P(X = k)0.00000.00010.00140.00900.03680.10290.20010.26680.23350.12110.0282
P(X ≤ k)0.00000.00010.00160.01060.04730.15030.35040.61720.85070.97181.0000

P(X = 7) = 0.2668; P(X ≥ 8) = 1 − P(X ≤ 7) = 1 − 0.6172 = 0.3828; P(X = 10) = 0.710 = 0.0282. Check one by formula: C(10, 8)(0.7)8(0.3)2 = 45 × 0.05765 × 0.09 = 0.2335.

Table 3. Binomial(14, 0.5): heads in 14 tosses

Every sequence has probability 1/16,384, so P(X = k) = C(14, k)/16,384. Mean 7, SD √3.5 = 1.871.

k01234567891011121314
C(14, k)114913641,0012,0023,0033,4323,0032,0021,00136491141
P(X = k)0.00010.00090.00560.02220.06110.12220.18330.20950.18330.12220.06110.02220.00560.00090.0001
P(X ≤ k)0.00010.00090.00650.02870.08980.21200.39530.60470.78800.91020.97130.99350.99910.99991.0000

P(X ≤ 5) = 3,473/16,384 = 0.2120, the lesson’s answer, and the table shows where each of its six terms comes from.

A second model check: 90°F days in Kansas City July weeks

From Table B of the Lesson 4.3 reading, 310 of 700 July days at Kansas City International reached 90°F, p = 0.4429. If days were independent, W ~ Binomial(7, 0.443), with mean 3.10 and variance 1.73.

k01234567
P(W = k)0.01670.09270.22110.29290.23280.11100.02940.0033
Expected weeks of 1001.79.322.129.323.311.12.90.3
Observed weeks12131817121387

The means agree (3.10 against the observed 3.10), as they must, since p was estimated from the same days. Everything else disagrees. The binomial model expects fewer than two weeks with no 90-degree day (1.7); 12 happened. It expects 0.3 of a week of seven straight; 7 happened. The observed variance is 4.25 against a binomial 1.73, 2.46 times larger. Hot spells last for days, and so do cool ones: a July day at 90°F is more likely to be followed by another than an independent-trials model allows. The independence condition fails harder for heat (variance ratio 2.46) than for rain (1.45), and the observed distributions show why: the weeks with the most days are far more common than independence would give.

What to do

  1. Use Table 2 to answer the lesson’s free-throw questions, and compute one of the probabilities by formula.
  2. Write the model check for Kansas City as a paragraph: the model, its assumptions, the comparison of expected and observed, and which assumption failed. Quote the two variances.
  3. Name a real process, other than weather, where you would expect the independence condition to fail, and say in which direction the variance would move. Check your answer against this rule: positive dependence makes the count’s variance larger than np(1 − p); or ask a parent or guardian whether your example makes sense.

Sources: NOAA National Centers for Environmental Information, GHCN-Daily (Daily Summaries), station USW00013994 (the query used here) (ncei.noaa.gov); NOAA National Centers for Environmental Information, GHCN-Daily (Daily Summaries), station USW00003947 (the query used here) (ncei.noaa.gov)

Up NextComplete & Continue →

Leave a Reply Cancel reply

Random Variables, Expected Value and Variance
Prev
Performance Task — Expected-Value Decision Analysis
Next

© 2026 The VR School | Career content by Wiley | Powered by Sejal Learning Systems.

Join free · Accreditation · Privacy Policy · Terms of Service

Modal title

Main Content