On this concept: Formula

Not sure which lesson to do first? Find your level and get a plan →

Math · Statistics & Probability · Grade 9-12

Expected Value

The expected value is the probability-weighted average of all possible outcomes — multiply each value by its chance and add.

E(X)=∑[x×P(x)]

Quick Answer

The expected value is the probability-weighted average of all possible outcomes — multiply each value by its chance and add. Use it to judge a bet, a game, an insurance policy or any choice with uncertain payoffs: it gives the average result per play if the situation were repeated many times. A game with a negative expected value loses money in the long run, however often it pays out in the short run. The expected value need not be a possible single result; for one die it is 3.5.

Why This Matters

Expected value puts risky choices on one scale. A $2 raffle ticket with a 1-in-500 chance at $500 has expected winnings of $1, so each ticket loses $1 on average. Casinos, insurers and game designers set prices with this calculation; looking only at the size of the prize, and not its probability, is how people overpay for long shots.

Intuitive Explanation

A fair die pays you, in dollars, whatever number it shows. Roll it 600 times and each face comes up about 100 times, so you collect about 100×(1+2+3+4+5+6)=2100 dollars, or 2100600=3.5 dollars per roll. That 3.5 is the expected value. You can skip the 600 rolls: E=1⋅16+2⋅16+⋯+6⋅16=3.5, each value weighted by how often it happens.

The weighting matters when outcomes are not equally likely. A prize wheel pays $1 with probability 0.7, $10 with probability 0.2 and $50 with probability 0.1. A plain average of the prizes, 1+10+503≈20.33, treats the rare $50 as if it came up a third of the time. The weighted sum, 1(0.7)+10(0.2)+50(0.1)=0.70+2+5=7.70, is the true long-run average per spin.

The expected value is neither the most likely outcome nor what happens on one play. On that wheel the most likely result is $1, which comes up 70% of the time, and no spin ever pays exactly $7.70. If a spin costs $8, you lose 30 cents per spin on average, so over 1,000 spins expect to be down about $300, even though some spins pay $50.

Think of it like this. The expected value is the fair price of a bet: the ticket price at which neither the player nor the house comes out ahead over many plays. Pay more than the expected value and you lose in the long run; pay less and you win. The picture says nothing about one play, which never pays exactly its average.

Core idea. Expected value is each outcome's value weighted by its probability, summed — the average you'd settle on over many, many trials.


When to Use

Use expected value when outcomes come with probabilities and payoffs and the question asks about the long run, the average per play, whether a game is fair, or which option pays more on average. Lay out a table of outcomes, values and probabilities, then multiply and add. If the question asks which single outcome is most likely, give the outcome with the largest probability. If you have observed data values with no probabilities attached, take their ordinary mean.

Tip. Ask: Am I weighting each outcome by its probability and summing to get a long-run average?

How to Recognize It

Before computing an expected value, check that every possible outcome has both an amount and a probability, and that the question is about what happens over many repeats.

  1. Can you write an amount next to each outcome, such as +10 dollars for a win and −2 for a loss?

    If yes, multiply each amount by its probability and add. If the outcomes are only labels, like win or lose with nothing at stake, you can only ask how likely each one is, which is a plain probability.

  2. Have you listed every outcome, including the ordinary losing one?

    Check that the probabilities add to 1. If they fall short, an outcome is missing, most often the plain loss worth 0 or minus the price of a ticket, and the expected value will come out too high.

  3. Would the answer still make sense if no single play could produce it, like 3.5 on a die?

    If yes, the question wants an expected value, a long-run average. If it needs an actual result, such as the prize you are most likely to walk away with, give the outcome with the highest probability instead.

  4. Are the values data already collected, like last week's daily sales?

    If yes, every value has an equal weight and you want the ordinary mean of the data. Expected value is for outcomes that have not happened yet, each weighted by its chance.

Expected Value compared with Mean (of data), Mode / most likely outcome, and Probability

Expected value, the mean of data, the most likely outcome and probability can all be read from one table of outcomes. Ask whether you want a long-run average of amounts (expected value), an average of past results (mean), the result with the top chance (mode), or a chance (probability).

Expected Value

Meaning
Use this when outcomes have known probabilities and you want the long-run average value of a random situation.
Key test
Am I weighting each outcome by its probability and summing to get a long-run average?
Formula
E(X)=∑[x×P(x)]
Example
A spinner lands on $5 with probability 0.5, $0 with 0.3, and $20 with 0.2. What is the expected payoff?

Mean (of data)

Meaning
Averages observed values, all weighted equally, from a data set.
Key test
Use when you have actual data, not probabilities for future outcomes.
Formula
∑xn
Example
Average of five recorded test scores

Mode / most likely outcome

Meaning
The single outcome with the highest probability, not the weighted average.
Key test
Use when asked which result is most probable, not the average value.
Example
Most common dice sum is 7

Probability

Meaning
The chance of one event, a number 0 to 1, not a weighted value.
Key test
Use when you want how likely an event is, not its average payoff.
Formula
favorabletotal
Example
Chance of rolling a 6

Formula & Notation

E(X)=∑[x×P(x)]
E(X)=∑ixi P(X=xi) (discrete); E(X)=∫−∞∞x f(x) dx (continuous)

How to read it: E(X) or μX denotes the expected value of random variable X

Worked Examples

Example 1 — A spinner game

Easy

A spinner lands on $5 with probability 0.5, $0 with 0.3, and $20 with 0.2. What is the expected payoff?
Show the steps and the answer
  1. Check the probabilities: 0.5+0.3+0.2=1.

    A complete list of outcomes must have probabilities summing to 1; otherwise an outcome is missing.

  2. Multiply each payoff by its probability: 5(0.5)=2.50, 0(0.3)=0, 20(0.2)=4.00.

    Each product is that outcome's share of the long-run average.

  3. Add: 2.50+0+4.00=6.50.

    The total is the average payoff per spin over many spins.

  4. Interpret: over 100 spins you would collect about 100×$6.50=$650.

    No single spin pays $6.50; it is a per-spin average.

Answer: $6.50

Takeaway: Weight each payoff by its probability and add, after checking that the probabilities total 1.

Example 2 — Most likely vs average

Standard

On the same spinner, someone asks 'what payoff should I most expect to land on?'
Show the steps and the answer
  1. Read the question: 'most expect to land on' asks for the single most likely outcome.

    That is about one spin's most probable result, not an average over many spins.

  2. Compare the probabilities: 0.5 for $5, 0.3 for $0, 0.2 for $20.

    The largest probability, 0.5, belongs to $5.

  3. Note that $6.50 is not a section of the spinner at all.

    The rare $20 prize pulls the weighted average above $5, but no spin can land on $6.50.

Answer: $5 (prob 0.5), even though E=$6.50

Takeaway: The most likely outcome has the largest probability; the expected value is the weighted average and may not be a possible outcome.

Example 3 — Find the mistake: an unweighted average

Application

A carnival game costs $3 to play. You win $10 with probability 0.1, $2 with probability 0.3, and nothing with probability 0.6. Jay writes: "The prizes average 10+2+03=$4, which is more than $3, so the game is worth playing." Find the mistake and correct it.
Show the steps and the answer
  1. Spot the error: Jay gives each prize the same weight, 13.

    The prizes are not equally likely; winning nothing happens 60% of the time.

  2. Weight by probability: 10(0.1)+2(0.3)+0(0.6)=1.00+0.60+0=1.60.

    Each prize counts in proportion to how often it is won, and 0.1+0.3+0.6=1 confirms the list is complete.

  3. Subtract the cost: 1.60−3.00=−1.40.

    The $3 is paid on every play, so the net expected value is expected winnings minus cost.

Answer: Expected net result =−$1.40 per play, so the game loses money on average.

Takeaway: Weight each prize by its probability before averaging, then subtract the cost to judge the game.

Where You'll See It

  • Is the extended warranty worth it?

    A store sells a $40 two-year warranty on a $300 tablet. If about 5% of tablets need a $200 repair in that time, the expected repair cost is 0.05×$200=$10. Paying $40 to cover an expected $10 is why stores push warranties: they keep about $30 per sale on average.

  • Going for it on fourth down

    Near the goal line, a football coach compares a field goal worth 3 points that succeeds about 95% of the time, E≈3(0.95)=2.85, with a touchdown try worth 7 points that succeeds about 45% of the time, E≈7(0.45)=3.15. The higher expected points favor going for it.

Common Mistakes

  1. The slip: Averaging the outcome values without weighting by probability

    Instead: multiply each value by its chance first.

  2. The slip: Letting the probabilities not sum to 1

    Instead: a complete set of outcomes must have probabilities adding to 1.

  3. The slip: Treating E(X) as the result of one trial

    Instead: it is the long-run average, which need not be an achievable single outcome.


Mini Practice

Try these on your own. Tap Reveal when you want to check.

  1. You roll a fair die and win the number shown in dollars. What are your expected winnings per roll?

    Hint: Each face has probability 16. Multiply each prize by it and add.

  2. The number of goals X a team scores has P(0)=0.3, P(1)=0.4, P(2)=0.2, P(3)=0.1. Find E(X).

    Hint: Multiply each number of goals by its probability, then add the products.

  3. A game costs $2 to play. You roll a die and win $10 on a 6, nothing otherwise. What is your expected net gain per game?

    Hint: Find the expected prize first, then subtract the cost of playing.

  4. A $1 raffle ticket has a 1 in 500 chance of winning $200 and a 1 in 100 chance of winning $20, otherwise nothing. What is the expected value of buying one ticket?

    Hint: Weight each prize by its chance, add them, then subtract the ticket price.

  5. A raffle ticket wins nothing 90% of the time and $50 the other 10%. Question 1: what result will you get most often? Question 2: what is the average per ticket over many tickets? Which one does expected value answer?

    Hint: One question asks for the most likely single result, the other for a long-run average.

  6. A spinner pays $1 with probability 0.7 and $10 with probability 0.3. Ivy writes: "E=1+102=5.50 dollars." Correct her work.

    Hint: Are the two payouts equally likely?

Want the full set?

50 practice questions for this concept — free to try, every one with a complete worked solution showing the why, not just the answer.

Frequently Asked Questions

How do casinos make money if most bets are close to fair?

Each bet is only slightly unfair, but the casino takes millions of them. In American roulette, a $1 bet on red wins $1 with probability 1838\frac{18}{38} and loses $1 with probability 2038\frac{20}{38}, since the two green pockets count as losses. The expected value is −238-\frac{2}{38}, a loss of about 5.3 cents per dollar. One player can win on a given night, but over all the bets the casino keeps very close to 5.3 cents of every dollar wagered.

How many plays does it take before my average gets close to the expected value?

There is no fixed number; it depends on how widely the results swing. For a fair die, whose expected value is 3.5, the average of 10 rolls often lands anywhere from about 2.5 to 4.5. After 1,000 rolls it is usually within about 0.1 of 3.5 and very rarely more than 0.2 away. A lottery is the extreme case: the payoffs swing so wildly that a lifetime of tickets can still be far from the expected value.

On average, how many rolls does it take to get a 6?

Six. When an event has probability pp on each independent try, the expected number of tries until it first happens is 1p\frac{1}{p}, so a 6 takes 6 rolls on average and heads takes 2 tosses. That does not mean a 6 is due after five misses. The die has no memory, so someone who has already missed five times still expects to need 6 more rolls, not 1.

Learning Path

← Before

ProbabilityMean
Expected Value

You are here

Next →

Variance
You need Probability, to give each outcome its chance, and Mean, since the expected value is a mean in which each value is weighted by its probability. Expected value adds a way to price games, bets and decisions under uncertainty. Next, Variance measures how far results typically scatter around the expected value, which separates a safe choice from a risky one with the same average.

See Also