Valid Probability Distribution: A discrete probability distribution must satisfy two conditions: (1) Each probability is between 0 and 1, inclusive, and (2) The sum of all probabilities equals 1.
- Check that each probability is non-negative
- Check that each probability is ≤ 1
- Verify that the sum of all probabilities equals 1
- Calculate the required probability
All probabilities: 0.2, 0.3, 0.25, 0.15, 0.1 are between 0 and 1 ✓
0.2 + 0.3 + 0.25 + 0.15 + 0.1 = 1.0 ✓
P(X ≥ 3) = P(X = 3) + P(X = 4) + P(X = 5) = 0.25 + 0.15 + 0.1 = 0.5
This is a valid probability distribution. P(X ≥ 3) = 0.5.
• Probability axioms: 0 ≤ P(X = x) ≤ 1 for all x
• Total probability: ΣP(X = x) = 1
• Cumulative probability: P(X ≥ a) = ΣP(X = x) for x ≥ a
Expected Value: E[X] = Σx·P(X = x), the weighted average of all possible values. Variance: Var(X) = E[X²] - (E[X])², measures the spread of the distribution.
E[X] = (1)(0.2) + (2)(0.3) + (3)(0.25) + (4)(0.15) + (5)(0.1) = 0.2 + 0.6 + 0.75 + 0.6 + 0.5 = 2.65
E[X²] = (1²)(0.2) + (2²)(0.3) + (3²)(0.25) + (4²)(0.15) + (5²)(0.1) = (1)(0.2) + (4)(0.3) + (9)(0.25) + (16)(0.15) + (25)(0.1) = 0.2 + 1.2 + 2.25 + 2.4 + 2.5 = 8.55
Var(X) = E[X²] - (E[X])² = 8.55 - (2.65)² = 8.55 - 7.0225 = 1.5275
E[X] = 2.65 and Var(X) = 1.5275.
• Expected value: E[X] = Σx·P(X = x)
• Variance formula: Var(X) = E[X²] - (E[X])²
• Computational efficiency: Using the alternative variance formula
Binomial Distribution: X ~ B(n,p) where n is the number of trials and p is the probability of success on each trial. P(X=k) = C(n,k)p^k(1-p)^(n-k).
Each question is an independent trial with probability p = 1/4 of success (guessing correctly). X ~ B(10, 1/4).
P(X = 3) = C(10,3)(1/4)³(3/4)⁷ = 120 × (1/64) × (2187/16384) ≈ 0.2503
For binomial distribution: E[X] = np = 10 × (1/4) = 2.5
P(X = 3) ≈ 0.2503 and E[X] = 2.5.
• Binomial probability: P(X = k) = C(n,k)p^k(1-p)^(n-k)
• Binomial expectation: E[X] = np
• Independence assumption: Each trial is independent
Discrete Random Variable: A variable that can take on a finite or countably infinite number of distinct values.
Probability Mass Function (PMF): The function P(X = x) that gives the probability that the discrete random variable X takes on the value x.
Expected Value: The theoretical average value of the random variable, calculated as E[X] = Σx·P(X = x).
Variance: A measure of the spread of the distribution, calculated as Var(X) = E[(X - E[X])²] = E[X²] - (E[X])².
Standard Deviation: The square root of the variance, σ = √Var(X).
- Identify the distribution: Determine if uniform, binomial, geometric, etc.
- Verify probability distribution: Check that probabilities are valid
- Calculate required measures: Expected value, variance, specific probabilities
- Apply appropriate formulas: Use distribution-specific formulas when possible
- Interpret results: Understand practical meaning
- Verify calculations: Double-check arithmetic
• Expected value: E[X] = Σx·P(X = x)
• Variance: Var(X) = E[X²] - (E[X])²
• Standard deviation: σ = √Var(X)
• Valid distribution: P(X = x) ≥ 0 and ΣP(X = x) = 1
• Binomial: X ~ B(n,p), E[X] = np, Var(X) = np(1-p)
• Geometric: X ~ Geo(p), E[X] = 1/p, Var(X) = (1-p)/p²
Geometric Distribution: Models the number of trials needed to get the first success in a sequence of independent Bernoulli trials. P(X=k) = (1-p)^(k-1)p for k=1,2,3,...
Flipping until first head is a geometric distribution with success probability p = 1/2.
Need 3 tails followed by 1 head: P(X = 4) = (1/2)³ × (1/2) = (1/8) × (1/2) = 1/16.
For geometric distribution: E[X] = 1/p = 1/(1/2) = 2.
P(X = 4) = 1/16 and E[X] = 2.
• Geometric probability: P(X = k) = (1-p)^(k-1)p
• Geometric expectation: E[X] = 1/p
• Independent trials: Each flip is independent of previous flips
Hypergeometric Distribution: Models the number of successes in a sample drawn without replacement from a finite population. P(X=k) = [C(K,k)×C(N-K,n-k)]/C(N,n).
N = 15 (total balls), K = 10 (red balls), n = 4 (balls drawn), k = 2 (desired red balls).
P(X = 2) = [C(10,2) × C(5,2)] / C(15,4) = [45 × 10] / 1365 = 450/1365 ≈ 0.3297
Ways to choose 2 red from 10: C(10,2) = 45. Ways to choose 2 blue from 5: C(5,2) = 10. Total favorable outcomes: 45×10 = 450. Total possible outcomes: C(15,4) = 1365.
P(X = 2) ≈ 0.3297.
• Hypergeometric probability: P(X = k) = [C(K,k)×C(N-K,n-k)]/C(N,n)
• Without replacement: Sampling affects subsequent probabilities
• Finite population: Total population size is fixed
Discrete Random Variable: A variable that can take on a finite or countably infinite number of distinct values.
Probability Mass Function (PMF): The function P(X = x) that gives the probability that the discrete random variable X takes on the value x.
Expected Value: The theoretical average value of the random variable, calculated as E[X] = Σx·P(X = x).
Variance: A measure of the spread of the distribution, calculated as Var(X) = E[(X - E[X])²] = E[X²] - (E[X])².
Standard Deviation: The square root of the variance, σ = √Var(X).
Valid Distribution: Must satisfy: (1) 0 ≤ P(X = x) ≤ 1 for all x, and (2) ΣP(X = x) = 1.
- Distribution identification: Determine the appropriate discrete distribution
- Parameter specification: Identify all necessary parameters
- Verification: Check that probabilities form a valid distribution
- Measure calculation: Compute expected value, variance, and other required measures
- Application: Solve specific probability questions
- Interpretation: Understand the practical meaning of results
• Expected value: E[X] = Σx·P(X = x)
• Variance: Var(X) = E[X²] - (E[X])²
• Standard deviation: σ = √Var(X)
• Valid distribution: P(X = x) ≥ 0 and ΣP(X = x) = 1
• Binomial: X ~ B(n,p), E[X] = np, Var(X) = np(1-p)
• Geometric: X ~ Geo(p), E[X] = 1/p, Var(X) = (1-p)/p²
• Hypergeometric: E[X] = nK/N, where N=population, K=successes, n=sample
• Simple: Uniform distribution (fair die)
• Intermediate: Given probability distribution table
• Advanced: Binomial distribution applications
• Complex: Geometric and hypergeometric distributions
• Discrete variables have distinct, separate values
• Probabilities must sum to 1
• Expected value is the long-run average
• Variance measures spread around the mean
• Use distribution-specific formulas when available
Questions & Answers
Question: What's the difference between binomial and geometric distributions?
Answer: Key differences:
- Binomial: Fixed number of trials (n), counts number of successes
- Geometric: Variable number of trials, counts trials until first success
Example: Binomial - Number of heads in 10 coin flips. Geometric - Number of flips until first head appears.
Question: Why do we need both E[X²] and (E[X])² in the variance formula?
Answer: The variance formula Var(X) = E[X²] - (E[X])² captures different aspects:
- E[X²]: Average of squared values
- (E[X])²: Square of the average value
- The difference measures how much values deviate from the mean
This is equivalent to E[(X - E[X])²], which directly measures squared deviations from the mean.
Question: When should I use hypergeometric instead of binomial distribution?
Answer: Use hypergeometric when sampling WITHOUT replacement from a finite population:
- Binomial: Sampling with replacement OR very large population (so removal doesn't matter)
- Hypergeometric: Sampling without replacement from small/finite population
Example: Drawing cards from a deck (hypergeometric) vs. flipping coins (binomial). When population is large, both give similar results.