ACT Math: Statistics & Probability

Imagine you're dealt a royal flush in poker. The odds? One in 649,740. How do mathematicians calculate such precise probabilities? Counting techniques. The ACT tests these in 2–3 questions per test, and they boil down to one decision: does order matter? If yes, use permutations. If no, use combinations. That single question—"does order matter?"—is worth more on the ACT than any formula you could memorize. Master that distinction and you'll handle every counting problem the ACT throws at you.

Counting, Permutations & Combinations

Imagine you're dealt a royal flush in poker. The odds? One in 649,740. How do mathematicians calculate such precise probabilities? Counting techniques. The ACT tests these in 2–3 questions per test, and they boil down to one decision: does order matter? If yes, use permutations. If no, use combinations. That single question—"does order matter?"—is worth more on the ACT than any formula you could memorize. Master that distinction and you'll handle every counting problem the ACT throws at you.

What You'll Learn The fundamental counting principle (multiply choices at each stage). Factorials: n! = n × (n-1) × ·s × 1. Permutations: arrangements where order matters (nPr). Combinations: selections where order doesn't matter (nCr). The one question that decides which formula to use. Probability with counting: favorable ÷ total.

The Fundamental Counting Principle

If you have m ways to do the first thing and n ways to do the second thing, there are m × n total ways to do both. This extends to any number of steps—just multiply.

This principle is the foundation of ALL counting. Permutations and combinations are just special applications of it. Whenever you're making sequential choices, multiply the number of options at each step.

Example 1: Counting Principle in Action
A restaurant offers 4 appetizers, 6 entrees, and 3 desserts. How many different 3-course meals are possible?

Step 1: Identify the stages: appetizer choice, entree choice, dessert choice.

Step 2: Count options at each stage: 4, 6, 3.

Step 3: Multiply: 4 × 6 × 3 = 72 different meals.

Another example: How many 4-digit PINs using digits 0–9 with repetition allowed?

Each digit has 10 choices: 10 × 10 × 10 × 10 = 10⁴ = 10{,}000 PINs.
Practice Question 1 (easy)
A restaurant offers 4 appetizers, 6 entrees, and 3 desserts. How many different 3-course meals are possible?

Permutations: When Order Matters

A permutation counts the number of ways to arrange items when the order matters. First place versus second place is different—winning gold versus silver is not the same achievement.

The formula: nPr = (n!)/((n-r)!)

Here n = total items and r = how many you're choosing.

Factorial reminder: n! = n × (n-1) × (n-2) × ·s × 1. For example, 5! = 120 and 0! = 1 by definition.

Permutation vs. Combination: choosing 3 letters from {A, B, C}
PERMUTATIONS(order matters)ABCACBBACBCACABCBA6 arrangementsCOMBINATIONS(order doesn't matter){A, B, C}1 groupAll 6 permutations collapseinto 1 combination because3! = 6 rearrangements exist.

Data Collection and Sampling Bias

Imagine walking into the ACT math section and instantly recognizing that 5 to 7 questions — nearly 12 percent of your math score — follow predictable patterns you can master in the next few minutes. Statistics and probability questions are not about complex calculations. They are about recognizing situations and applying simple rules. You will encounter questions about averages, data bias, and probability that test the same core concepts repeatedly. Most students overthink these problems, but you will learn to spot the patterns quickly. From calculating means to identifying biased samples, these questions offer some of the most reliable points on the test. Let's unlock those patterns and turn statistics into your scoring advantage.

What You'll Learn How 5–7 questions per test (8–12% of the Math section) cover statistics and probability. The four sampling methods the ACT loves to test. How to identify selection bias, response bias, nonresponse bias, and undercoverage. Basic probability rules — single events, 'or' events, and 'and' events. Combinations and expected value essentials.

Mean, Median, Mode, and Range

The four statistical measures form the foundation of ACT statistics questions. Mean equals the sum divided by the count — the arithmetic average you use daily. Median is the middle value when numbers are ordered; with even counts, average the two middle values. Mode is simply the most frequent value, which could be none, one, or multiple values. Range equals maximum minus minimum, measuring spread.

Working Backwards from the Mean
If the mean of 5 numbers is 20, their sum must be 5 × 20 = 100. This reverse calculation appears frequently on the ACT. Whenever you know the mean and the count, multiply to find the total sum, then subtract any known values to find the missing one.

Basic Probability Rules

Every probability question starts from one golden formula:

$P(event) = frac{Number of favorable outcomes}{Total number of possible outcomes}$

For single events, apply the formula directly. When a problem says "or," add probabilities (and subtract any overlap). When it says "and," multiply probabilities. The critical check is replacement — with replacement, probabilities stay the same for each draw; without replacement, the denominator shrinks by one each time.

Practice Question 2 (medium)
A teacher recorded test scores for 15 students:\n\n72, 85, 78, 92, 78, 88, 79, 82, 78, 95, 90, 79, 83, 87, 76\n\nWhat is the difference between the mean and the median of these scores?

Lines of Best Fit and Regression

Imagine predicting your ACT score based on hours studied. That is regression in action! Every ACT features five to seven statistics questions, roughly ten percent of the math section, with regression and lines of best fit appearing consistently. These problems test whether you can find patterns in data and use them to make predictions. The ACT loves real-world scenarios — temperature affecting ice cream sales, study hours improving test scores, or price influencing demand. Unlike classroom statistics that might involve complex formulas, ACT regression focuses on practical application. You will need to interpret regression equations, understand slopes in context, and make predictions using the line. Master these skills, and you will turn scattered data points into guaranteed ACT points!

What You'll Learn How regression problems appear on every ACT test (5–7 statistics questions total). The regression equation y = mx + b and what each part means. How to interpret slope and y-intercept in real-world contexts. How to make forward and reverse predictions. Correlation strength, R², and why extrapolation is risky.

Understanding Lines of Best Fit

A line of best fit is like finding the average path through a cloud of points. It minimizes the total distance between the line and all data points, passes through or near the center of the data, and has roughly equal points above and below. When data points rise together — like hours studied and test scores — you have positive correlation with an upward-sloping line. When one increases while the other decreases — like price and demand — that is negative correlation with a downward slope.

A scatter plot with a line of best fit showing a strong positive trend.
01234567890246810xyy = 0.95x + 1.5

The Regression Equation

The regression equation y = mx + b is your prediction machine. Here, m is the slope telling you how much y changes when x increases by one, and b is the y-intercept showing where the line crosses the y-axis. On the ACT, you rarely need to derive this equation from scratch — your calculator does it instantly with the LinReg function. The test wants you to use the equation, not create it.

Interpreting Slope and Y-Intercept in Context
Equation: y = 5x - 230 (ice cream sales vs. temperature in degrees F)

Slope = 5 means for every 1-degree increase in temperature, 5 more ice creams are sold.

Y-intercept = -230 would mean negative 230 sales at 0 degrees F — clearly not realistic, which shows why context matters. Some y-intercepts are meaningless outside the data range.
Practice Question 3 (medium)
An ice cream shop owner collected data on daily temperature (degrees F) and ice cream sales (number sold). The regression equation for this data is y = 5x - 230, where x is temperature and y is sales. What is the predicted number of ice cream sales when the temperature is 83 degrees F?

Measures of Center: Mean, Median, and Mode

Every ACT has that moment when a student sees a statistics question and either panics or grins. Which one will you be? Statistics questions appear one to two times per test, representing easy points if you know the tricks. Here is the reality — these are not the complex statistics problems from your math class. The ACT keeps it simple with mean, median, and mode. Master these three measures of center, and you will turn potential stumbling blocks into guaranteed points. Most students overthink these problems or make careless errors. Not you. You are about to learn the streamlined approach that makes statistics questions some of the fastest to solve on test day.

What You'll Learn 1–2 questions per ACT Math section focus on measures of center. Mean, median, and mode calculations and when to use each. The 'working backwards' method for finding missing values. How outliers affect each measure differently. Box plots and the five-number summary.

The Mean: More Than Just Average

The mean is the arithmetic average — add all values and divide by the count.

$Mean = frac{Sum of all values}{Number of values}$

The mean is the most commonly tested measure on the ACT. It is affected by every value in the dataset and is sensitive to outliers. The ACT's favorite twist: they give you the mean and ask you to work backwards. If the mean of 5 tests is 85, the total sum must be 5 × 85 = 425. Subtract known scores to find the missing one.

An outlier (85) pulls the mean far from the cluster, but the median stays near the center.

The Median: Finding the Middle Ground

The median is the middle value when data is arranged in order.

For an odd number of values, the median is the exact middle. For an even number, average the two middle values.

Example (odd): 3, 7, 9, 12, 15 — Median = 9 Example (even): 4, 7, 11, 15, 20, 23 — Median = (11 + 15)/(2) = 13

The median is not affected by outliers, making it the better choice for skewed distributions. Always reorder your data first — the most common median error is forgetting to sort.

How One Outlier Changes Everything
Original Data: 20, 22, 23, 25, 26

Mean: 23.2

Median: 23

Mode: None

With Outlier Added: 20, 22, 23, 25, 26, 85

Mean: 33.5 (jumped by 10.3!)

Median: 24 (barely moved)

Mode: Still none

The mean is extremely sensitive to outliers — it gets 'pulled' toward extreme values. The median resists outliers, barely changing. When you see words like 'unusual values,' 'extreme scores,' or 'one very different result,' think MEDIAN.
Practice Question 4 (medium)
A basketball player's points scored in 10 games are:\n\n72, 85, 90, 78, 88, 92, 80, 95, 88, 76\n\nWhat is the difference between the mean and median scores?

Measures of Spread: Range and IQR

Two data sets can have identical averages but tell completely different stories. One ACT question separates students who truly understand data from those who just memorize formulas. Measures of spread reveal the hidden patterns in numbers that averages alone cannot show. You will face 2 to 3 questions on the ACT about range, interquartile range, and box plots. These are not just calculations — they are tools for understanding real-world variation. From test score distributions to weather patterns, spread measures help us quantify uncertainty and make better predictions. Master these concepts and you will unlock a deeper understanding of statistics that extends far beyond the exam.

What You'll Learn 2–3 questions per ACT test cover measures of spread. Range shows total variation in data but is sensitive to outliers. IQR reveals the middle 50% spread and resists outliers. Box plots visualize the five-number summary at a glance. When to use range vs. IQR depends on context and outliers. How to read and compare box plots like a pro.

Range: The Simplest Spread Measure

Range = Maximum value - Minimum value

For example, if test scores run from 65 to 92, the range is 92 - 65 = 27 points. Range is the quickest way to gauge total variation, but it has a serious limitation — one extreme value can drastically change it. A single outlier can double or triple the range while the rest of the data stays tightly clustered.

Think of throwing darts at a target. The range tells you the distance between your worst and best throws — nothing more. It ignores everything in between.

Interquartile Range (IQR)

IQR = Q3 - Q1 (Third Quartile minus First Quartile)

The IQR focuses on the middle 50% of data, ignoring extremes. To find it:

1. Order data from least to greatest. 2. Find the median (Q2) — the middle value. 3. Q1 = median of the lower half (values below Q2). 4. Q3 = median of the upper half (values above Q2). 5. Subtract: IQR = Q3 - Q1.

With an even number of data points, split the data into two equal halves. With an odd number, exclude the median itself from both halves before finding Q1 and Q3.

Practice Question 5 (medium)
The daily rainfall (in inches) for a week in Seattle was recorded as: 2.1, 2.3, 2.8, 3.2, 3.5, 3.9, 4.2. What is the interquartile range of this data?

Probability Rules and Expected Value

A student reaches into their pocket and pulls out three quarters, two dimes, and a nickel. What are the odds they will have enough for a 1.25-dollar vending machine snack? This everyday scenario captures the essence of probability on the ACT. You will face five to seven probability and statistics questions, making up eight to twelve percent of the math section. These are not just abstract concepts — they are tools for understanding real-world uncertainty. From basic probability ratios to expected value calculations, you will learn to quantify chance and predict long-term outcomes. The ACT tests three main areas: basic probability, combined events, and expected value. Each follows logical patterns that, once recognized, transform seemingly complex problems into straightforward calculations.

What You'll Learn 5–7 probability questions per test (8–12% of the math section). Three main types: basic probability, combined events, and expected value. The fundamental formula: P = frac{favorable}{total}. AND means multiply, OR means add, 'at least one' means use the complement. Expected value: multiply each outcome by its probability and sum.

Understanding Basic Probability

Basic probability answers a simple question: how likely is something to happen?

$P(Event) = frac{Number of favorable outcomes}{Total number of possible outcomes}$

Probabilities always range from 0 (impossible) to 1 (certain). The complement — the probability something does NOT happen — equals 1 - P(event). If there is a 30% chance of rain, there is a 70% chance it stays dry.

Expected value: a fair die has E(X) = 3.5, the average over many rolls.
0123456700.050.10.150000000000000020.20.25outcomeprobability

Multiple Events and Combined Probability

When the ACT combines events, two rules apply.

AND Rule (both happen): Multiply probabilities. Roll a 6 AND flip heads: (1)/(6) × (1)/(2) = (1)/(12)

OR Rule (at least one happens): Add probabilities. For mutually exclusive events: P(A or B) = P(A) + P(B) For overlapping events: P(A or B) = P(A) + P(B) - P(A and B)

The ACT favorite? 'At least one' problems. Use the complement: P(at least one) = 1 - P(none). This shortcut transforms complex multi-scenario problems into simple calculations.

Practice Question 6 (medium)
A jar contains 15 red marbles, 10 blue marbles, 8 green marbles, and 7 yellow marbles. If a marble is randomly selected from the jar, what is the probability that it is NOT yellow?

Scatter Plots and Correlation

Two dots on a graph saved a company millions of dollars. How? By revealing a hidden pattern nobody else saw. That is the power of scatter plots on the ACT! You will face 2 to 3 scatter plot questions worth crucial points on test day. These are not just random dots — they are visual stories about relationships between variables. From predicting test scores based on study hours to spotting outliers that change everything, scatter plots unlock patterns invisible in raw data. Master correlation types, line of best fit, and prediction techniques, and you will turn those scattered points into perfect ACT scores!

What You'll Learn 2–3 questions per ACT test cover scatter plots and correlation. How to identify positive, negative, and no correlation. How correlation strength is measured by the coefficient r (from -1 to +1). Using the line of best fit (y = mx + b) for predictions. Interpolation (within data) vs. extrapolation (beyond data). Why outliers matter and why correlation does not prove causation.

What Are Scatter Plots?

A scatter plot displays data as points on a coordinate plane, showing the relationship between two variables. The x-axis represents the independent variable (what you control or measure first), and the y-axis represents the dependent variable (what responds).

When you look at a scatter plot, ask four questions: 1. Direction — Are points generally rising (positive) or falling (negative)? 2. Strength — How tightly do points cluster around an invisible line? 3. Form — Is the pattern linear (straight) or curved? 4. Outliers — Are any points far from the main pattern?

Points clustering in an upward diagonal show positive correlation. Points trailing downward show negative correlation. Scattered randomly like confetti? No correlation.

Types of Correlation

The correlation coefficient r ranges from -1 to +1 and tells you both direction and strength:

Strong Positive (r > 0.7): Points rise tightly from left to right. As x increases, y increases consistently. Examples: study time vs. test scores, practice hours vs. skill level.

Moderate (0.3 < |r| < 0.7): A trend is visible but with significant scatter. The relationship exists but is not overwhelming.

Weak (|r| < 0.3): Barely any pattern. The points look almost random.

Strong Negative (r < -0.7): Points fall tightly from left to right. As x increases, y decreases. Examples: distance from downtown vs. home prices, altitude vs. air pressure.

No Correlation (r approx 0): Points scattered randomly with no visible pattern. Examples: shoe size vs. GPA, phone number vs. height.

Two-Way Tables and Conditional Probability

Sixty percent of ACT test takers miss conditional probability questions not because they cannot do the math, but because they misread the table. That is right — six out of ten students who understand the concept still get these questions wrong. Two-way tables and conditional probability directly appear in 1–2 questions per ACT, but the table-reading and probability skills they build support the broader statistics category (4–5 questions total). The formula is simple: probability of A given B equals the number of outcomes where both A and B occur divided by the total number of B outcomes. But success requires careful reading and systematic thinking. Let's build bulletproof table-reading skills so you never leave these points on the table (pun intended).

What You'll Learn 1–2 questions per test directly test two-way tables and conditional probability. How to read two-way tables: rows, columns, cells, and margins. The difference between joint and marginal frequencies. The conditional probability formula: P(A|B) = frac{count of A and B}{count of B}. How to test for independence between events. Why P(A|B) ≠ P(B|A) — order matters!

Understanding Two-Way Tables

Two-way tables organize data about two categorical variables. Rows represent one variable, columns represent another, and each cell shows how many items meet both conditions. The margins (edges) give row and column totals, and the grand total sits in the bottom-right corner.

Here is an example. A study tracked 110 students based on whether they studied for an exam and whether they passed:

| | Studied | Didn't Study | Total | |—|—|—|—| | Passed | 72 | 18 | 90 | | Failed | 8 | 12 | 20 | | Total | 80 | 30 | 110 |

Always verify that rows sum correctly and columns sum correctly — this 30-second check catches errors that cost points. For instance: 72 + 18 = 90 (first row checks out), 72 + 8 = 80 (first column checks out), and 90 + 20 = 110 (grand total checks out).

Joint and Marginal Frequencies

Joint frequency lives inside the table cells — it means BOTH conditions are true (e.g., students who studied AND passed = 72). Marginal frequency sits at the edges — it means only ONE condition (e.g., total students who passed = 90, regardless of whether they studied).

Joint probability: P(A and B) = frac{joint frequency}{grand total} Example: P(Studied and Passed) = (72)/(110) approx 0.655

Marginal probability: P(A) = frac{marginal frequency}{grand total} Example: P(Passed) = (90)/(110) approx 0.818