Probability Theory and Random Variables: Fundamentals andKey

Probability Theory and Random Variables

Fundamentals, Distributions, and Applications

---

Photo by Deng Xiang on Unsplash

• Definition: A branch of mathematics concerned with probability, providing a rigorous formalization of uncertainty.
• Probability Scale: Ranges from 0 (impossible event) to 1 (certain event).
• Fundamental Rule: The sum of probabilities for all possible outcomes in a sample space must equal 1.

• Weather forecasting (predicting precipitation likelihood).
• Insurance risk assessment (calculating premiums and claims).
• Networks and systems reliability (uptime and failure analysis).
• Poll management (statistical sampling and opinion prediction).

• Definition: A process with multiple possible outcomes where the specific outcome is unpredictable.
• Conditions: Must be repeatable under identical conditions.
• Examples: Flipping a coin, rolling a die, counting defective bolts in a batch, measuring bulb lifetime (0 < t < 4000).

• Sample Space (S): The set of all possible outcomes. Examples: Coin S={H,T}, Die S={1, 2, 3, 4, 5, 6}.
• Sample Point: A single element within the sample space.
• Event: A subset of the sample space. Example: Two coin tosses resulting in only one head, S={HT, TH}.

• Sure Event: The entire sample space S.
• Impossible Event: The empty set (e.g., rolling a 7 on a standard 6-sided die).
• Simple Event: An event with only one outcome (e.g., rolling exactly 3).
• Compound Event: An event with multiple outcomes (e.g., getting at least one head in three tosses).

Bayes Theorem

Advanced Conditional Probability

---

Photo by Shubham Dhage on Unsplash

• Definition: A mathematical mapping from outcomes of a random experiment to real numbers.
• Purpose: To quantify outcomes for numerical analysis. Representation: X, Y, Z.
• Example: Two coin toss outcomes (HH, HT, TH, TT) mapped to number of heads: HH->2, HT->1, TH->1, TT->0. Range = {0, 1, 2}.

• Formalism: A random variable X is a function X:S → R.
• Examples: Mapping die outcomes to faces, mapping two-coin outcomes to the number of heads.

• Number of heads in 3 coin tosses.
• Number of customer arrivals per hour.
• Lifespan of an electronic bulb.
• Number of defective items in a batch of 10.

• Definition: A variable that takes countable values (finite or countably infinite).
• Examples: Students in a class, telephone calls received, number of heads.
• Key Distributions: Binomial and Poisson.

• Definition: A variable that takes any value within an interval of real numbers.
• Examples: Height, weight, temperature, race completion time.
• Key Distributions: Uniform and Normal (Gaussian).

• The set of possible values a random variable can take.
• Two coin toss: Range = {0, 1, 2}.
• Sum of two dice: Range = {2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12}.

• Properties: Non-negative function, total area under the curve is 1.
• Probability as Area: P(a ≤ X ≤ b) = integral from a to b of f(x) dx.

• Definition: F(x) = P(X ≤ x).
• Properties: Ranges from 0 to 1, non-decreasing, limit as x approaches infinity is 1.
• Relation: F(x) is the integral of the PDF.

• Criteria: n independent trials, success probability p, failure probability q = 1-p.
• Formula: P(X=k) = C(n, k) p^k q^(n-k)

• Parameters: n = 4, p = 0.10.
• Find P(X=1): C(4, 1) (0.1)^1 (0.9)^3 = 4 0.1 0.729 = 0.2916.
• Conclusion: 29.16% probability of exactly one defect.

Poisson Distribution

Modeling rare events in fixed intervals

---

Photo by Deng Xiang (https://unsplash.com/@dengxiangs?utmsource=karaf&amp;utmmedium=referral) on Unsplash (https://unsplash.com/?utmsource=karaf&amp;utmmedium=referral)

• Definition: f(x) = 1/(b-a) for a ≤ x ≤ b.
• Probability: P(x1 ≤ X ≤ x2) = (x2-x1)/(b-a).
• Examples: Bus waiting time (0-10 min), selecting a random point on a 1m ruler.

• Mean (μ): (a+b)/2, representing the midpoint of the interval.
• Variance (σ²): (b-a)²/12, representing the spread based on interval length.

• Problem 1: Uniform(-2, 6) -> Mean=2, Variance=64/12. P(X<4)=6/8=0.75, P(X>0)=6/8=0.75.
• Problem 2: Uniform(8, 20) -> Mean=14, Variance=12. P(|X-6|≤15)=1, P(15≤X≤17)=1/6.

• Definition: pdf = (1/(σsqrt(2π))) e^(-(x-μ)² / (2σ²)).
• Shape: Bell-shaped and symmetric around the mean.
• Examples: Heights, IQ scores, measurement errors.

• Standardization: Z = (X-μ)/σ, Z ~ N(0,1).
• PDF: φ(z) = (1/sqrt(2π)) * e^(-z²/2).
• Purpose: Allows use of a single universal statistical table for any normal distribution.

• Properties: Total area = 1.
• Empirical Rule: P(μ-σ < X < μ+σ) ≈ 0.6826.

• Usage: Provides area from mean to Z.
• Examples: Z=1.00 corresponds to area 0.3413, Z=1.96 corresponds to area ≈ 0.4750.

• Comparison: Uniform(8,20) for P(15≤X≤17) = 1/6 ≈ 0.1667.
• Normal(μ=14, σ²=12) for the same range ≈ 0.1937.
• Conclusion: Different distribution shapes result in different probability values for the same interval.