Summary
For a discrete random variable X with values x₁, x₂, …, xₙ, the probability mass function (p.m.f.) gives P(X = xᵢ) = pᵢ for every value. The p.m.f. is usually written as a table: the values of X in the first row and their probabilities in the second.
To find P(a ≤ X ≤ b) or P(X > a), add the probabilities of the values that satisfy the condition. For 'X > 2' you may also use 1 − P(X ≤ 2) when that has fewer terms. For a quadratic in the constant, such as 6k² + 5k − 1 = 0, reject the root that makes any probability negative.
Key formulas
- p.m.f. conditions
- pᵢ ≥ 0, Σ pᵢ = 1
- c.d.f.
- F(x) = P(X ≤ x); P(X = xᵢ) = F(xᵢ) − F(xᵢ₋₁)
- Tail probability
- P(X > a) = 1 − F(a)
- Mean
- E(X) = μ = Σ xᵢ pᵢ
- Mean of a function
- E[g(X)] = Σ g(xᵢ) pᵢ; E(aX + b) = aE(X) + b
- Variance
- Var(X) = E(X²) − [E(X)]² = Σ xᵢ² pᵢ − μ²
- Standard deviation
- σ = √Var(X); Var(aX + b) = a² Var(X)
- X = 1, 2, …, n equally likely
- E(X) = (n + 1)/2, Var(X) = (n² − 1)/12
What this note covers
- Probability mass function
- Cumulative distribution function
- Expected value
- Variance and standard deviation
Solved past-paper question (MHT-CET 2024)
A random variable has the following probability distribution: X: 0,1,2,3,4,5,6,7; P(x): 0, 2p, 2p, 3p, p², 2p², 7p², 2p. Then the value of p is
- (A) (1/10)
- (B) (1/30)
- (C) (1/100)
- (D) (3/20)
Solution
The probabilities of a p.m.f. add up to 1.
0 + 2p + 2p + 3p + p² + 2p² + 7p² + 2p = 1
Collect the like terms.
10p² + 9p − 1 = 0
Factorise.
(10p − 1)(p + 1) = 0
p = −1 would give negative probabilities, so reject it.
p = 1/10
Check: all probabilities (such as 2p = 1/5 and p² = 1/100) are positive, so p = 1/10 is valid.
Answer: (A) (1/10)
Common mistake: Keeping both roots of the quadratic. A probability cannot be negative, so p = −1 is rejected.
The full note has 9 solved questions, 9 practice questions, figures and a topic test. Reading it on PrepKi is free after you log in.
PDF download is included in PrepKi plans. See plans.