Descriptive Statistics and Probability Theory
CSIR NET Mathematical Sciences Unit 4: descriptive statistics, EDA, probability, Bayes, random variables, characteristic functions, inequalities, LLN, CLT.
- 5
- Topics
- 82
- Min read
- 01 Descriptive Statistics and Exploratory Data AnalysisStart here CSIR NET statistics: mean, median, quantiles, moments, skewness, kurtosis, correlation, regression lines, box plots and outlier rules, with practice.
- 02 Sample Space, Independence and Bayes' Theorem CSIR NET probability: sample spaces, sigma-fields, Kolmogorov axioms, inclusion-exclusion, conditional probability, independence and Bayes' theorem.
- 03 Random Variables, Distribution Functions and Moments CSIR NET probability: random variables, CDF properties, discrete, continuous and mixed laws, transformations, expectation, moments, MGF and PGF.
- 04 Joint, Marginal and Conditional Distributions; Characteristic Functions CSIR NET probability: joint, marginal and conditional laws, independence, conditional expectation, bivariate normal, Jacobians, characteristic functions.
- 05 Inequalities, Convergence and Limit Theorems CSIR NET probability: Markov, Chebyshev and Jensen inequalities, modes of convergence, Borel-Cantelli, weak and strong laws of large numbers, i.i.d. CLT.
- Probability Theory Formula Sheet and Short Notes Revise The whole chapter on one page.
Chapter Overview
This chapter opens Unit 4 of the CSIR NET Mathematical Sciences syllabus, the statistics unit. Everything else in that unit rests on it: Markov chains need conditional probability and limits, statistical inference needs distributions, moments and the central limit theorem, and linear models need covariance and conditional expectation.
The notes assume an MSc-level first course in probability (the measure-theoretic language of a probability space, random variables and expectation as an integral) and a first statistics course. They do not re-teach those courses. They collect exact statements, the hypotheses that matter, standard computations, and the counter-examples that decide Part C questions: Cauchy and lognormal variables, uncorrelated but dependent pairs, pairwise but not mutually independent events, sequences that converge in one mode and not another.
What You’ll Learn
By the end of this chapter you will be able to:
- Summarise data with location, dispersion, moments, \( \beta_1 \), \( \beta_2 \), correlation and regression lines, and screen it with box plots and Tukey’s fences
- Build probability models from axioms, use inclusion–exclusion, total probability and Bayes’ theorem, and test events for pairwise and mutual independence
- Read any distribution function, including mixed ones; transform random variables; compute expectations, moments, MGFs and PGFs, and know when they exist
- Work with joint, marginal and conditional distributions, conditional expectation, the bivariate normal, Jacobian transformations and characteristic functions
- Apply the Markov, Chebyshev and Jensen inequalities, decide modes of convergence with Borel–Cantelli, and use the laws of large numbers and the i.i.d. central limit theorem
Prerequisites
- Real Analysis: limits, series, improper and Lebesgue integrals, uniform convergence. Expectation is an integral and almost-sure convergence is pointwise convergence.
- Linear Algebra: inner products (Cauchy–Schwarz gives \( \lvert r \rvert \le 1 \)) and quadratic forms (covariance matrices).
- Counting: permutations, combinations and inclusion–exclusion.
Learning Path
graph TD
A[1. Descriptive Statistics and EDA] --> C[3. Random Variables, Distribution Functions and Moments]
B[2. Sample Space, Independence and Bayes] --> C
C --> D[4. Joint and Conditional Distributions, Characteristic Functions]
D --> E[5. Inequalities, Convergence and Limit Theorems]
C --> E
E --> F[Quick Revision]Pages 1 and 2 can be read in either order: one is about data, the other about models. They meet on page 3, where the data summaries reappear as properties of distributions.
Topics in This Chapter
| # | Topic | What it covers | Time |
|---|---|---|---|
| 1 | Descriptive Statistics and Exploratory Data Analysis | mean, median, quantiles, dispersion, coding and pooling, moments, skewness and kurtosis, correlation, regression lines, box plots, Tukey’s fences, resistance | 30 min |
| 2 | Sample Space, Independence and Bayes’ Theorem | \( \sigma \)-fields, axioms, inclusion–exclusion, matching problem, geometric probability, conditional probability, total probability, Bayes, Pólya’s urn, pairwise vs mutual independence | 30 min |
| 3 | Random Variables, Distribution Functions and Moments | CDF characterisation, discrete, continuous, singular and mixed laws, transformations, expectation and tail formulas, moments, PGF, MGF, memorylessness | 35 min |
| 4 | Joint, Marginal and Conditional Distributions; Characteristic Functions | joint CDFs, independence, covariance, conditional expectation, total variance, bivariate normal, Jacobians, convolutions, characteristic functions, inversion, Lévy continuity | 35 min |
| 5 | Inequalities, Convergence and Limit Theorems | Markov, Chebyshev, Cantelli, Jensen, Lyapunov, four modes of convergence, Borel–Cantelli, Slutsky, WLLN, SLLN, Lindeberg–Lévy CLT, normal approximation | 35 min |
| Quick Revision | every formula, table and counter-example on one page | 10 min |
Official syllabus lines and where they are covered
| Official topic line | Covered in |
|---|---|
| Descriptive statistics, exploratory data analysis | Descriptive Statistics and Exploratory Data Analysis |
| Sample space, independence, Bayes theorem | Sample Space, Independence and Bayes’ Theorem; independence of random variables in Joint, Marginal and Conditional Distributions |
| Random variables, distribution functions, expectation, moments | Random Variables, Distribution Functions and Moments |
| Marginal/conditional distributions, characteristic functions | Joint, Marginal and Conditional Distributions; Characteristic Functions |
| Chebyshev, Markov, Jensen inequalities | Inequalities, Convergence and Limit Theorems (Inequalities section) |
| Modes of convergence, laws of large numbers, CLT (i.i.d.) | Inequalities, Convergence and Limit Theorems (Modes, Laws and CLT sections) |
The detailed catalogue of standard distributions, sampling distributions and estimation belongs to the separate distributions and inference unit of the syllabus. This chapter uses the common distributions only as examples.
How CSIR NET Asks It
Per the NTA information bulletin for December 2026, the Mathematical Sciences paper (code 704) is marked as follows:
| Part B | Part C | |
|---|---|---|
| Questions given | 40 | 60 |
| Questions to attempt | 25 | 20 |
| Marks per correct answer | 3 | 4.75 |
| Marks per wrong answer | −0.75 | 0 |
| Maximum | 75 | 95 |
NTA publishes no topic-wise weightage, so we make no claim about how many questions come from this chapter. The format tells you how to prepare:
- Part B (single correct) rewards fast, exact computation: a Bayes posterior, a constant that makes a density integrate to 1, a variance from an MGF, \( E(Y \mid X = x) \) on a triangle, a Chebyshev bound, a limit from the SLLN, a normal approximation.
- Part C (one or more correct) rewards counter-examples and hypothesis-checking. Typical stems: “which of the following are characteristic functions”, “in which modes does \( X_n \) converge”, “which statements about this CDF are true”, “which pairs of these events are independent”. Every topic page ends with Level 3 practice in exactly this format, with every option justified.
For the marking scheme and the other units, see the Mathematical Sciences overview. The Part A chapter Graphical Analysis and Data Interpretation covers histograms, box plots and scatter plots at the aptitude level, and Numerical Ability covers elementary counting and probability; both are quick marks for a statistics candidate. Found an error? See About for how to report it.
Start Learning
Begin with the first topic: