AP Statistics probability rules cheat sheet

By Jude Wallis · Published

The core AP Statistics probability rules are the complement rule, the general addition rule for "or", the conditional probability formula for "given", the general multiplication rule for "and", and the shortcut P(A and B) = P(A)P(B) that holds only for independent events.

AP Statistics: Unit 2 (topics 2.4 Introduction to Probability, 2.5 Mutually Exclusive Events, 2.6 Conditional Probability, 2.7 Independent Events and Unions of Events). These rules are Unit 2, topics 2.4 through 2.7, of the Fall 2026 AP Statistics course. Two-way tables are introduced in topic 2.1.

The rules in one table

RuleFormulaUse it for
Probability scale0≤P(A)≤10 \leq P(A) \leq 1, and the whole sample space has probability 1Checking any answer
Equally likely outcomesP(A)=number of outcomes in Anumber of outcomes in the sample spaceP(A) = \frac{\text{number of outcomes in } A}{\text{number of outcomes in the sample space}}Outcomes that all have the same chance
ComplementP(AC)=1−P(A)P(A^C) = 1 - P(A)"Not A"
General additionP(A∪B)=P(A)+P(B)−P(A∩B)P(A \cup B) = P(A) + P(B) - P(A \cap B)"A or B" for any two events
Addition, mutually exclusive eventsP(A∪B)=P(A)+P(B)P(A \cup B) = P(A) + P(B)"A or B" when P(A∩B)=0P(A \cap B) = 0
Conditional probabilityP(A∣B)=P(A∩B)P(B)P(A \mid B) = \frac{P(A \cap B)}{P(B)}"A given B"
General multiplicationP(A∩B)=P(A)⋅P(B∣A)P(A \cap B) = P(A) \cdot P(B \mid A)"A and B" for any two events
Multiplication, independent eventsP(A∩B)=P(A)⋅P(B)P(A \cap B) = P(A) \cdot P(B)"A and B" when the events are independent

Read A∪BA \cup B as "A or B" (the union, which includes both happening), A∩BA \cap B as "A and B" (the intersection, also called the joint probability), ACA^C as "not A", and P(A∣B)P(A \mid B) as "the probability of A given B".

Mutually exclusive versus independent

FeatureMutually exclusive (disjoint)Independent
MeaningThe events cannot happen togetherKnowing one happened does not change the probability of the other
Joint probabilityP(A∩B)=0P(A \cap B) = 0P(A∩B)=P(A)⋅P(B)P(A \cap B) = P(A) \cdot P(B)
Conditional probabilityP(A∣B)=0P(A \mid B) = 0P(A∣B)=P(A)P(A \mid B) = P(A)
"Or"P(A∪B)=P(A)+P(B)P(A \cup B) = P(A) + P(B)P(A∪B)=P(A)+P(B)−P(A)⋅P(B)P(A \cup B) = P(A) + P(B) - P(A) \cdot P(B)

Two events that each have positive probability cannot be both mutually exclusive and independent. If they are mutually exclusive, knowing that one happened makes the other impossible, which changes its probability. More in disjoint vs independent events.

Three ways to check independence

Events AA and BB are independent when any one of these holds. With real numbers in hand, pick whichever is fastest.

CheckIndependent when
Condition on BBP(A∣B)=P(A)P(A \mid B) = P(A)
Condition on AAP(B∣A)=P(B)P(B \mid A) = P(B)
Compare the joint probability with the productP(A∩B)=P(A)⋅P(B)P(A \cap B) = P(A) \cdot P(B)

Show both numbers and state whether they are equal. If they are not equal, the events are not independent. Worked cases are in how to check if events are independent.

Reading probabilities from a two-way table

A two-way table gives every kind of probability directly. This table classifies 200 students by grade and by whether they have a part-time job.

GradeJobNo jobTotal
Junior3575110
Senior454590
Total80120200
ProbabilityWhere it comes fromExample for one randomly chosen student
MarginalA row or column total over the table totalP(job)=80200=0.40P(\text{job}) = \frac{80}{200} = 0.40
JointOne inside cell over the table totalP(senior∩job)=45200=0.225P(\text{senior} \cap \text{job}) = \frac{45}{200} = 0.225
ConditionalOne inside cell over its row or column totalP(job∣senior)=4590=0.50P(\text{job} \mid \text{senior}) = \frac{45}{90} = 0.50

The condition sets the denominator. "Given senior" restricts attention to the 90 seniors. The first worked example below applies every rule to this table. For more on reading tables, see how to read a two-way table.

Complement shortcuts and at least one

"At least one" is the complement of "none":

P(at least one)=1−P(none)P(\text{at least one}) = 1 - P(\text{none})

For nn independent trials that each succeed with probability pp, P(none)=(1−p)nP(\text{none}) = (1-p)^n, so P(at least one)=1−(1−p)nP(\text{at least one}) = 1 - (1-p)^n. With p=0.2p = 0.2 and n=5n = 5: 1−0.85=1−0.32768=0.67231 - 0.8^5 = 1 - 0.32768 = 0.6723.

When the trials are not independent, such as drawing without replacement, find P(none)P(\text{none}) with the general multiplication rule and subtract from 1. The second worked example does this. More cases are in probability of at least one.

Words that signal each rule

Wording in the problemProbabilityRule
"and", "both"P(A∩B)P(A \cap B)Multiplication rule, or a table cell over the table total
"or", "either"P(A∪B)P(A \cup B)Addition rule, subtracting the overlap
"given", "among", "of those who"P(A∣B)P(A \mid B)Conditional probability formula
"not", "none", "neither"P(AC)P(A^C)Complement rule
"at least one"1−P(none)1 - P(\text{none})Complement rule, then multiplication for "none"

Order matters in a conditional probability. P(A∣B)P(A \mid B) and P(B∣A)P(B \mid A) have different denominators and are usually different numbers. See conditional probability: order matters.

Every rule on one two-way table

Use the table of 200 students above (110 juniors: 35 with a job, 75 without; 90 seniors: 45 with a job, 45 without). One student is chosen at random. Find the probability the student (a) has no job, (b) is a senior or has a job, (c) is a senior given that the student has a job. (d) Decide whether "senior" and "job" are independent.

  1. Marginal probabilities: P(job)=80200=0.40P(\text{job}) = \frac{80}{200} = 0.40 and P(senior)=90200=0.45P(\text{senior}) = \frac{90}{200} = 0.45.

  2. (a) Complement: P(no job)=1−0.40=0.60P(\text{no job}) = 1 - 0.40 = 0.60, which matches 120200\frac{120}{200}.

  3. Joint probability: P(senior∩job)=45200=0.225P(\text{senior} \cap \text{job}) = \frac{45}{200} = 0.225.

  4. (b) General addition: P(senior∪job)=0.45+0.40−0.225=0.625P(\text{senior} \cup \text{job}) = 0.45 + 0.40 - 0.225 = 0.625. Check by counting: 90+80−45=12590 + 80 - 45 = 125 students, and 125200=0.625\frac{125}{200} = 0.625.

  5. (c) Conditional: P(senior∣job)=0.2250.40=0.5625P(\text{senior} \mid \text{job}) = \frac{0.225}{0.40} = 0.5625, the same as 4580\frac{45}{80}.

  6. (d) Independence: P(job∣senior)=4590=0.50P(\text{job} \mid \text{senior}) = \frac{45}{90} = 0.50, and P(job)=0.40P(\text{job}) = 0.40. These are not equal. The product check agrees: 0.45×0.40=0.180.45 \times 0.40 = 0.18, which is not 0.225.

(a) 0.60. (b) 0.625. (c) 0.5625. (d) Not independent, because P(job∣senior)=0.50P(\text{job} \mid \text{senior}) = 0.50 differs from P(job)=0.40P(\text{job}) = 0.40.

General multiplication without replacement

A box holds 10 bulbs, 3 of which are defective. Two bulbs are drawn at random without replacement. Find the probability that (a) both are defective and (b) at least one is defective.

  1. (a) General multiplication: P(both defective)=P(first defective)⋅P(second defective∣first defective)=310⋅29=690=0.0667P(\text{both defective}) = P(\text{first defective}) \cdot P(\text{second defective} \mid \text{first defective}) = \frac{3}{10} \cdot \frac{2}{9} = \frac{6}{90} = 0.0667.

  2. (b) Find "none" first: P(neither defective)=710⋅69=4290=0.4667P(\text{neither defective}) = \frac{7}{10} \cdot \frac{6}{9} = \frac{42}{90} = 0.4667.

  3. Complement: P(at least one defective)=1−4290=4890=0.5333P(\text{at least one defective}) = 1 - \frac{42}{90} = \frac{48}{90} = 0.5333.

(a) 690≈0.067\frac{6}{90} \approx 0.067. (b) 4890≈0.533\frac{48}{90} \approx 0.533.

Frequently asked questions

When can I multiply two probabilities?

You can always use the general rule P(A∩B)=P(A)⋅P(B∣A)P(A \cap B) = P(A) \cdot P(B \mid A). The shorter product P(A)⋅P(B)P(A) \cdot P(B) is correct only when the events are independent. See when to multiply probabilities.

Why does the addition rule subtract the joint probability?

Outcomes in both AA and BB are counted once in P(A)P(A) and again in P(B)P(B). Subtracting P(A∩B)P(A \cap B) removes the double count. For mutually exclusive events the joint probability is 0, so nothing is subtracted.

Is P(A given B) the same as P(B given A)?

Usually not. P(A∣B)P(A \mid B) divides the joint probability by P(B)P(B), and P(B∣A)P(B \mid A) divides it by P(A)P(A). In the table above, P(job∣senior)=0.50P(\text{job} \mid \text{senior}) = 0.50 and P(senior∣job)=0.5625P(\text{senior} \mid \text{job}) = 0.5625.