Statistics

Probability Distribution Table Calculator

Enter the values of X with probabilities, fractions, frequencies or k — get the full discrete distribution table with E(X), Var(X), SD(X), the cumulative column, a graph, P(X ≥ a) and step-by-step working.

Expected Value E(X) Variance Var(X) Solve for k Frequency Tables
Share this tool

Enter your discrete random variable

Separate with commas, spaces or new lines. Negatives and fractions are fine.

Decimals, fractions (1/6) or percentages (25%). Use k (e.g. 2k, k/4, k^2) to solve for an unknown.

Quick Load:
Calculating distribution…

Enter values and probabilities (or tap a quick-load example) to build the full distribution table.

What is a probability distribution table?

A probability distribution table is a structured way to describe all possible outcomes of a discrete random variable X and their associated probabilities. Every row lists one value the random variable can take — written as P(X = x) — alongside how likely that outcome is.

This discrete probability distribution calculator builds the table for you: enter the values of X and their probabilities as decimals, fractions (1/6), percentages or expressions in k, or paste raw frequencies. It returns E(X), Var(X), SD(X), the cumulative column, a graph, the median and mode, any P(X ≥ a) or P(a ≤ X ≤ b) you ask for, and E(aX + b) — with every step shown.

Discrete distributions appear everywhere: the number of goals scored in a football match, the outcome of rolling a die, the number of defective items in a batch of 20, or the number of customers who arrive at a checkout in a minute. Whenever the outcomes are countable and finite, a probability distribution table gives you the full picture in one place.

From that table you can derive three key statistics: the expected value E(X) (the long-run average), the variance Var(X) (how spread out the values are), and the standard deviation SD(X) (variance in the same units as X). You also get the cumulative distribution function P(X ≤ x), which tells you the probability that X takes a value no greater than any threshold you choose.

How a Probability Distribution Table Works

Random variable X12345
P(X = x)0.10.20.40.20.1

✓ Rule 1 satisfied

Each P(X=x) ∈ [0, 1]

✓ Rule 2 satisfied

ΣP = 0.1+0.2+0.4+0.2+0.1 = 1.0

E(X) = 1(0.1) + 2(0.2) + 3(0.4) + 4(0.2) + 5(0.1) = 3.0

E(X²) = 1(0.1) + 4(0.2) + 9(0.4) + 16(0.2) + 25(0.1) = 10.2

Var(X) = E(X²) − [E(X)]² = 10.2 − 9.0 = 1.2

SD(X) = √1.2 ≈ 1.095

How to Construct a Probability Distribution Table

Building a valid discrete probability distribution takes three steps:

  1. List every possible outcome of the random variable in a row of values x₁, x₂, …, xₙ. These do not need to be integers or ordered, but ordering them makes the CDF column meaningful.
  2. Assign a probability to each outcome. Each probability must be between 0 and 1 (inclusive). A probability of 0 means the outcome can never happen; 1 means it always happens.
  3. Verify ΣP = 1. All probabilities must sum to exactly 1. If your total is 0.99 due to rounding, that is acceptable. If it is 0.9 or 1.1, your model is wrong.

Common sources of discrete distributions include: counting experiments (Binomial), waiting-time experiments (Geometric), rare-event counts (Poisson), and custom empirical data from observations.

How to Calculate E(X) — Expected Value

The expected value E(X) is the long-run average of X over many repetitions. It answers the question: if you repeated this random experiment infinitely many times and averaged all the outcomes, what number would you approach?

E(X) = Σ xᵢ · P(X = xᵢ)

Practical examples: If X is the payout on a lottery ticket where you win £10 with probability 0.05 and nothing with probability 0.95, then E(X) = 10(0.05) + 0(0.95) = £0.50. That is the fair ticket price — anything higher means the lottery profits; anything lower means the player has an edge.

Note that E(X) does not have to be a value X can actually take. The expected number of heads in three fair coin flips is 1.5 — an outcome that never occurs. E(X) is a summary statistic of the distribution, not a prediction of any individual outcome.

How to Calculate Var(X) — Variance and Standard Deviation

Variance Var(X) measures how spread out the values of X are around E(X). A high variance means outcomes vary widely; a low variance means most results cluster near the mean.

The two-step shortcut formula avoids computing squared deviations one by one:

E(X²) = Σ xᵢ² · P(X = xᵢ)

Var(X) = E(X²) − [E(X)]²

SD(X) = √Var(X)

Why the shortcut works: Expanding the definition Var(X) = E[(X − μ)²] algebraically gives Var(X) = E(X²) − [E(X)]². This is equivalent but much faster because you only need two sums over the table.

Standard deviation SD(X) is simply √Var(X). Because variance is in units of X², SD(X) brings the spread measure back to the same units as X itself, making it interpretable as "typical distance from the mean."

Quality control engineers use SD(X) to set tolerance bands. Finance analysts use Var(X) to compare investment risks. Teachers use SD(X) to understand how spread exam scores are around the class average.

Understanding the Cumulative Distribution Function (CDF)

The cumulative distribution function P(X ≤ x) gives the probability that the random variable takes a value no greater than x. It is computed by adding each probability from the first row down:

P(X ≤ xₙ) = P(X = x₁) + P(X = x₂) + … + P(X = xₙ)

The CDF always starts at P(X ≤ x₁) = P(X = x₁) and ends at P(X ≤ xₙ) = 1. It is non-decreasing — each step adds a non-negative probability.

You can use the CDF column to answer questions like: "What is the probability that X is at most 3?" or "What is the probability that X is between 2 and 4?" (answer: CDF(4) − CDF(1)). These are the most common types of question in A-Level statistics exams.

Rules Every Probability Distribution Must Satisfy

Non-negativity

Every probability P(X = x) must be ≥ 0. Negative probabilities are not meaningful — an event cannot be "less than impossible."

Boundedness

Every P(X = x) must be ≤ 1. A probability greater than 1 is undefined — certainty is the maximum, represented by exactly 1.

Normalisation

The sum of all probabilities must equal 1. Together, all possible outcomes account for the entire probability space.

Mutual exclusivity

Each outcome x must be distinct — the same value cannot appear twice. Listing x = 3 twice would double-count its probability.

How to find k in a probability distribution table

Exam questions often give the probabilities in terms of an unknown constant k and ask you to find it. The key fact is that the probabilities of a discrete random variable always add up to 1, so you add them, set the total equal to 1 and solve.

x1234
P(X = x)k2k3k4k

k + 2k + 3k + 4k = 1 → 10k = 1 → k = 0.1

So the probabilities are 0.1, 0.2, 0.3 and 0.4, and E(X) = 1(0.1) + 2(0.2) + 3(0.3) + 4(0.4) = 3. When the table mixes k and k² — for example 2k² and k — the total gives a quadratic (2k² + k − 1 = 0, so k = 0.5 or k = −1). Reject any root that makes a probability negative or bigger than 1; here only k = 0.5 works.

In the calculator, type the probabilities exactly as written in the question — k, 2k, 3k, 4k, k/4, 0.1 + k or 3k^2 — and it solves for k, shows the working, and then builds the full table.

Probability distribution from a frequency table

When you have survey or experiment counts instead of probabilities, divide each frequency by the total. This gives the relative frequency, which you use as the probability of each value. Fifty families were asked how many children they have:

Children x01234
Frequency f8141783
P(X = x) = f/500.160.280.340.160.06

The mean number of children is E(X) = 0(0.16) + 1(0.28) + 2(0.34) + 3(0.16) + 4(0.06) = 1.68. Choose Frequencies above the input boxes and paste the counts to get this table, plus the variance and standard deviation, without dividing by hand.

E(aX + b) and Var(aX + b): linear transformations

If every value of X is multiplied by a and then has b added — converting units, or turning a score into a payout — the new mean and spread follow simple rules:

E(aX + b) = a·E(X) + b

Var(aX + b) = a²·Var(X)

SD(aX + b) = |a|·SD(X)

The constant b moves the whole distribution but does not change how spread out it is, which is why it disappears from the variance. With E(X) = 3 and Var(X) = 1.2, Y = 2X + 3 has E(Y) = 9 and Var(Y) = 4 × 1.2 = 4.8. Open "Optional: find a probability or E(aX + b)" in the calculator to get these with working.

Probability Distribution Table FAQ

How do you make a probability distribution table?

List every value the discrete random variable X can take in one row, write P(X = x) for each value underneath, and check that every probability is between 0 and 1 and that they add up to 1. Then add x·P(X = x) and x²·P(X = x) columns to get E(X) and Var(X), and a running total for the cumulative probability P(X ≤ x).

How do you find k in a probability distribution?

Use the fact that all probabilities add up to 1. Write the sum of the probabilities in terms of k, set it equal to 1 and solve. For P(X = x) = kx with x = 1, 2, 3, 4: k + 2k + 3k + 4k = 10k = 1, so k = 0.1. If the probabilities contain k², solve the quadratic and reject any value of k that gives a negative probability or one above 1. Type k, 2k, k/4 or 3k^2 into this calculator and it solves for k automatically.

How do you find the expected value of a probability distribution?

Multiply each value by its probability and add the results: E(X) = Σ x·P(X = x). For a fair die, E(X) = (1 + 2 + 3 + 4 + 5 + 6) × 1/6 = 3.5. The expected value is the long-run average over many trials, so it does not have to be a value X can actually take.

How do you find the variance of a discrete random variable?

Use Var(X) = E(X²) − [E(X)]². First find E(X²) = Σ x²·P(X = x), then subtract the square of the mean. For a fair die, E(X²) = 91/6 and E(X) = 7/2, so Var(X) = 91/6 − 49/4 = 35/12 ≈ 2.9167. The standard deviation is the square root of the variance.

How do you turn a frequency table into a probability distribution?

Divide each frequency by the total frequency. If 50 families have 0, 1, 2, 3 or 4 children with frequencies 8, 14, 17, 8 and 3, then P(X = 2) = 17/50 = 0.34. Switch this calculator to Frequencies mode and paste the counts — it does the division and builds the table.

What is E(aX + b) and Var(aX + b)?

Adding a constant shifts the mean but not the spread, and multiplying scales both: E(aX + b) = a·E(X) + b, Var(aX + b) = a²·Var(X) and SD(aX + b) = |a|·SD(X). For example, if E(X) = 3 and Var(X) = 1.2, then E(2X + 3) = 9 and Var(2X + 3) = 4.8.

How do you find P(X ≥ a) or P(a ≤ X ≤ b) from a table?

Add the probabilities of every value that meets the condition. P(X ≥ 3) is P(X = 3) + P(X = 4) + … ; it also equals 1 − P(X ≤ 2). For a range on whole numbers, P(2 ≤ X ≤ 4) = F(4) − F(1), where F is the cumulative column. Watch the difference between < and ≤: P(X < 3) does not include x = 3.

Can the expected value be a number X never takes?

Yes. The expected score on a die is 3.5 and the expected number of heads in three coin flips is 1.5, yet neither result can happen on a single trial. E(X) is the balance point of the distribution — the average you would approach over many repeats.

What makes a probability distribution valid?

Two rules: every probability must be between 0 and 1, and the probabilities must add up to exactly 1. Each value of X must also appear only once. This calculator checks all three and allows a total within 0.001 of 1 for rounded decimals; use fractions such as 1/3 for exact answers.