Questions
~2 questions per paper
Difficulty
Medium
Importance
Medium yield for BHEL/ONGC/IOCL
Overview
Probability and Statistics are fundamental to engineering decision-making and data analysis in PSU exams. Understanding these distributions and descriptive statistics allows you to predict outcomes based on data trends, which is highly relevant for quality control and systems engineering roles.
Central Tendency and Variance
These measures describe the center and spread of a dataset, serving as the foundation for statistical analysis. Mastery here is essential for answering direct calculation questions quickly during time-constrained exams.
- Mean (Average): Sum of values divided by count
- Median: The middle value in a sorted dataset
- Mode: The most frequently occurring value
- Variance: E[(X - μ)²] or σ²
- Standard Deviation: Square root of variance (σ)
Discrete Probability Distributions
Discrete distributions handle countable outcomes, with Binomial and Poisson being the most frequently tested types in PSU papers. Identify which distribution to use based on whether you have a fixed number of trials or a rate of occurrence.
- Binomial: P(X=k) = nCk * p^k * q^(n-k)
- Binomial Mean: np, Variance: npq
- Poisson: P(X=k) = (e^-λ * λ^k) / k!
- Poisson Mean: λ, Variance: λ
- Poisson is used for rare events over a fixed interval
Normal Distribution
The Normal (Gaussian) distribution is a continuous probability distribution defined by its bell-shaped curve and symmetry. Most exam questions focus on the standard normal distribution and Z-score calculations.
- PDF: f(x) = (1 / σ√(2π)) * e^(-(x-μ)² / 2σ²)
- Z-score: Z = (X - μ) / σ
- Empirical Rule: 68-95-99.7% for 1, 2, and 3 sigma
- Mean = Median = Mode for symmetric normal curve
Regression Analysis
Regression quantifies the relationship between two variables, primarily focusing on linear regression in engineering aptitude sections. This allows you to model trends and predict dependent variable outcomes.
- Equation: Y = a + bX
- Least Squares Method minimizes sum of squared residuals
- Correlation coefficient (r) ranges from -1 to 1
- Slope b = r * (σy / σx)
Formula Sheet
P(X=k) = nCk * p^k * q^(n-k)
P(X=k) = (e^-λ * λ^k) / k!
Z = (X - μ) / σ
σ² = Σ(xi - μ)² / n
Y = a + bX
Exam Tip
Always verify if the distribution is discrete or continuous before applying formulas, as this single step eliminates 90% of incorrect formula choices.
Common Mistakes
- Confusing the Mean and Variance formulas for Binomial vs Poisson distributions.
- Forgetting to check if the probability p and q add up to 1 in Binomial distribution problems.
- Mixing up standard deviation and variance when solving Z-score problems.
More Revision Notes
Ready to test yourself?
Play topic-wise Probability & Statistics questions in Aspirant Arcade — gamified MCQ practice.
Download Free