Probability Distributions Study Guide
(Discrete + Continuous)
PROBABILITY DISTRIBUTIONS STUDY GUIDE (DISCRETE + CONTINUOUS)
This guide summarizes the most important discrete and continuous probability
distributions with:
- What they model
- Real-life use cases
- Parameters
- Formulas (PMF or PDF, Mean, Variance)
- Clear examples
DISCRETE DISTRIBUTIONS
1. BERNOULLI
- Use: One success/failure trial
- Parameters: p (success probability)
- PMF: P(X = x) = p^x * (1 - p)^(1 - x), x = 0 or 1
- Mean = p, Variance = p(1 - p)
- Example: Flip a coin → P(Heads) = 0.5
2. BINOMIAL
- Use: Count successes in n trials
- Parameters: n (trials), p (success)
- PMF: P(X = k) = C(n, k) * p^k * (1 - p)^(n - k)
- Mean = np, Variance = np(1 - p)
- Example: P(6 heads in 10 coin flips) ≈ 0.205
3. GEOMETRIC
- Use: Trials until first success
- Parameter: p
- PMF: P(X = k) = (1 - p)^(k - 1) * p
- Mean = 1/p, Variance = (1 - p)/p^2
- Example: P(success on 3rd die roll) = (5/6)^2 * (1/6) ≈ 0.116
4. NEGATIVE BINOMIAL
- Use: Trials until r successes
- Parameters: r (successes), p
- PMF: P(X = k) = C(k - 1, r - 1) * p^r * (1 - p)^(k - r)
- Mean = r/p, Variance = r(1 - p)/p^2
- Example: P(3rd success on 8th call, p = 0.1) ≈ 0.0124
5. POISSON
- Use: Count of events in fixed interval
- Parameter: λ (average rate)
- PMF: P(X = k) = (λ^k * e^(-λ)) / k!
- Mean = λ, Variance = λ
- Example: P(5 calls/hour, λ = 4) ≈ 15.6%
6. HYPERGEOMETRIC
- Use: Sampling without replacement
- Parameters: N (population), K (successes), n (sample size)
- PMF: P(X = k) = [C(K, k) * C(N - K, n - k)] / C(N, n)
- Mean = n(K/N), Variance = n(K/N)(1 - K/N)(N - n)/(N - 1)
- Example: P(2 defective out of 4 from 5/20) ≈ 0.2167
7. DISCRETE UNIFORM
- Use: Equal chance for n outcomes
- Parameters: a, b (min and max integers)
- PMF: P(X = x) = 1 / (b - a + 1)
- Mean = (a + b)/2, Variance = [(b - a + 1)^2 - 1]/12
- Example: P(rolling a 4 on a die) = 1/6
CONTINUOUS DISTRIBUTIONS
1. NORMAL
- Use: Natural variation, bell curve
- Parameters: μ (mean), σ (std dev)
- PDF: f(x) = (1 / (σ√2π)) * e^(-(x - μ)^2 / 2σ^2)
- Mean = μ, Variance = σ^2
- Example: P(IQ < 130 if μ = 100, σ = 15) ≈ 97.7%
2. STUDENT'S t
- Use: Small sample inference, unknown σ
- Parameter: df = n - 1
- PDF: Similar to normal but heavier tails
- Mean = 0, Variance = df/(df - 2)
- Example: t = (105 - 100)/(8/√10) ≈ 1.98
3. FISHER'S F
- Use: Ratio of two variances (ANOVA)
- Parameters: df1, df2
- PDF: Depends on df1 and df2
- Mean = df2 / (df2 - 2) for df2 > 2
- Example: F = s1^2 / s2^2 = 20 / 10 = 2
4. EXPONENTIAL
- Use: Time until next event
- Parameter: λ (rate)
- PDF: f(x) = λ * e^(-λx), x ≥ 0
- Mean = 1/λ, Variance = 1/λ^2
- Example: λ = 0.1 → P(X < 5) ≈ 39.3%
5. GAMMA
- Use: Time until r-th event
- Parameters: k (shape), λ (rate)
- PDF: f(x) = λ^k * x^(k - 1) * e^(-λx) / Γ(k)
- Mean = k/λ, Variance = k/λ^2
- Example: P(3rd failure < 40 hrs, λ = 0.1) ≈ 85.7%
6. WEIBULL
- Use: Failure times, reliability
- Parameters: k (shape), λ (scale)
- PDF: f(x) = (k/λ)(x/λ)^(k-1) * e^(-(x/λ)^k)
- Mean = λΓ(1 + 1/k)
- Example: k = 1.8, λ = 1200 → P(X < 1000) ≈ 48.8%
7. BETA
- Use: Probabilities/proportions between 0 and 1
- Parameters: α, β
- PDF: f(x) = x^(α-1) * (1-x)^(β-1) / B(α, β)
- Mean = α / (α + β), Variance = αβ / [(α + β)^2(α + β + 1)]
- Example: Posterior after 12/40 → Beta(13,29) → mean ≈ 0.31
8. CHI-SQUARE
- Use: Variance testing, independence
- Parameter: df
- PDF: Special case of Gamma(k = df/2, λ = 0.5)
- Mean = df, Variance = 2df
- Example: Used in χ² test of independence
9. CONTINUOUS UNIFORM
- Use: Equal likelihood over an interval
- Parameters: a, b
- PDF: f(x) = 1 / (b - a), a ≤ x ≤ b
- Mean = (a + b)/2, Variance = (b - a)^2 / 12
- Example: U(0,10) → P(3 ≤ X ≤ 7) = 4/10 = 40%
Use this guide to recognize distribution types, model data, and solve real problems in
statistics, AI, quality control, and operations.