Home/Notes/Probability & Statistics
Engineering Exam Notes

Probability & Statistics Notes

Questions

~2 questions per paper

Difficulty

Medium

Importance

High yield for HPCL/NTPC/ONGC

Overview

Probability and Statistics form the foundation of decision-making and data analysis in engineering. Mastery of this topic is essential for competitive PSU exams because it tests your ability to model uncertainty and interpret data-driven outcomes efficiently.

Probability Fundamentals & Distributions

Probability models measure the likelihood of outcomes in random experiments. Binomial, Poisson, and Normal distributions are the most frequently tested patterns for modeling discrete and continuous variables.

  • Binomial: P(X=k) = nCk * p^k * q^(n-k)
  • Poisson: P(X=k) = (e^-λ * λ^k) / k!
  • Normal: N(μ, σ^2) with Z-score = (X-μ)/σ
  • Total probability and Bayes' Theorem applications

Sampling and Hypothesis Testing

Sampling allows us to infer population parameters from a subset of data, while hypothesis testing validates assumptions about these populations. Focus on the null hypothesis and the significance levels used in decision criteria.

  • Central Limit Theorem: Distribution of sample mean approaches normal as n increases
  • Null Hypothesis (H0) vs. Alternative Hypothesis (H1)
  • Type I error: Rejecting H0 when true
  • Type II error: Failing to reject H0 when false

Correlation and Regression Analysis

These techniques quantify the strength and nature of relationships between two variables. Regression provides a predictive model, while correlation coefficients measure the consistency of the relationship.

  • Pearson correlation coefficient (r) range: -1 to +1
  • Coefficient of determination (r^2) indicates variance explained
  • Linear Regression model: y = mx + c
  • Method of Least Squares for line fitting

Formula Sheet

Binomial Mean: E(X) = np

Poisson Mean = Variance = λ

Z-score = (x - μ) / σ

Regression Line: y - y_bar = r * (σy/σx) * (x - x_bar)

Exam Tip

Always convert your Normal distribution variable into a Standard Normal Z-score before referencing the Z-table to avoid calculation errors.

Common Mistakes

  • Confusing the standard deviation (σ) with variance (σ^2) in normal distribution problems.
  • Forgetting to check if the conditions for Binomial (n is fixed) vs Poisson (λ is average rate) are met.
  • Mixing up Type I and Type II error definitions during hypothesis testing.

More Revision Notes

Ready to test yourself?

Play topic-wise Probability & Statistics questions in Aspirant Arcade — gamified MCQ practice.

Download Free