Introduction to

the Course

1
Importance of Statistics
To study :

NSSO Data

Census Data

RBI reports

NFHS data

2
Importance of Statistics
To study –

◦ How much MSP helps small farmers

◦ Whether rural electrification improved school

outcomes

◦ If women’s reservation actually increased

female empowerment

3
Importance of Statistics
Don’t Assume — Analyze
How do we know if PMAY (Housing Scheme) improved
housing security?
How do we know if MGNREGA actually provides
employment in rural areas?
How do we know if Ayushman Bharat is helping poor
households with healthcare?
Has Beti Bachao Beti Padhao improved gender ratios or
education levels?
Has Swachh Bharat Mission improved sanitation
behavior?
4
Examples
•Swachh Bharat: Toilet Construction = End of Open Defecation
Govt. reports show 100% toilet coverage, can we assume the
end of open defecation?
•India’s GDP is Growing, So Everyone is Better Off
Poverty and inequality – GINI Index
•Digital India is Transforming Rural Lives
Increase in number of mobile connections or UPI users in rural
areas.
What about infrequent access? Low digital literacy? Fear of
fraud?

5
Importance of Statistics
Data doesn’t lie, but it also doesn’t speak for itself.
That’s why interpretation, context, and statistical reasoning
matter.
•We have to consider –

6
Importance of Statistics
•Measurement bias
•Misuse of indicators
•Role of Confounding variables
•Importance of survey design and field verification

If the data collection is wrong, it doesn’t matter how

brilliant your analysis is.

Garbage in, garbage out.

7
Importance of Statistics
•Measurement bias

Underreporting of women’s work in labour force surveys.

•Women working on family farms or businesses are not

“officially” counted unless they're paid or self-report it as
“primary work.”
•Survey questions often ask: “Have you worked for income in
the last week/month?”

8
Importance of Statistics
•Misuse of indicators
Claim: “Crime is falling – FIRs registered are lower than last
year“

What’s wrong –
FIRs ≠ Actual Crimes

9
Importance of Statistics
•Role of Confounding variables
Households That Own Motorbikes Have Better Child
Nutrition

Confounder – household income

10
Did you know that –
global ice cream sales and shark attacks both rise in
summer? Should we ban ice cream to save swimmers?
Ice cream sales and power cuts both increase in summers?
Years when Nicolas Cage starred in more movies also saw
more people drowning in swimming pools. Should we ban
Cage to save lives?

As Facebook users grew, so did Greece’s national debt.

Coincidence or Zuckerberg’s fault?

11
Did you know that –
Did you know that in years with more Reels posted per
capita, India’s GDP also rose?

Did you know that states with more road accidents also
report higher engineering admissions?
(Maybe IIT prep books should come with driving lessons!)

Did you know that cities with more educational institutions

also have an high number of momo stalls?

12
Did you know that –
India’s marriage rate rises when GDP rises. Is economic
growth making people more romantic?

Students who eat more pani puri near college gates perform
better in exams. Is chutney boosting brain cells?

States with more Instagram posts have higher tourism

revenue. Are influencers driving the economy?

13
Did you know that –
When onion prices rise, people honk more in traffic. Is
kitchen stress spilling onto the road?

States with more PhD holders have lower birth rates. Is

education scaring people off parenting?

14
Course: Statistics
Nature of the course: Core / Major
Credits: 4

15
Course: Statistics
This course provides a comprehensive introduction
to –
statistical methods,
probability distributions,
estimation,
hypothesis testing,
regression, and
operational research techniques

16
 Learning Outcomes
1 To understand concepts related to descriptive statistics, probability
distributions, estimation, and hypothesis testing.
2 To analyze statistical methods and their applications in decision-
making processes.
3 To apply statistical techniques such as regression analysis and
operational research methods to solve real-world problems.
4 To evaluate statistical inferences using parametric and nonparametric
methods.
5 To interpret and optimize solutions using operational research
techniques such as linear programming and transportation problems.

6 To utilize statistical software tools for data analysis and problem-

solving. 17
Course Content:
I Descriptive Statistics: Numerical Measures
II Introduction to Probability: Basic Relationships, Discrete &
Continuous Probability Distributions
III Estimation and Inference
IV Testing Hypotheses
V Regression Analysis
VI Introduction to Operational Research (OR)
VII Advanced Algorithms in OR

18
Module 1:
Descriptive Statistics: Numerical Measures
•Measures of Location and Variability; Weighted
Mean; Grouped Data.
•Measures of Distribution Shape;
•Exploratory Data Analysis;
•Measures of Association Between Two Variables:
Dependency among real variables, (Bivariate data),
scatter plot and other diagram

19
Understanding Statistics
•Panel data: like stalking the same people over time,
but for science.

20
Understanding Statistics
•Standard Deviation: The Drama Queen of Data
SD is like that person at a party who can’t stop
telling you how much everyone is different from the
average — even if no one asked.

21
Module 2:
Introduction to Probability
•Conditional Probability; Bayes’ Theorem;
•Discrete Probability Distributions: Binomial Probability
Distribution; Negative Binomial Distribution Poisson
Probability Distribution; Hypergeometric Probability
Distribution;
•Continuous Probability Distributions: Uniform Probability
Distribution; Normal Probability Distribution; Normal
Approximation of Binomial Probabilities; Exponential
Probability Distribution.
•Relationship among all these distributions with examples.

22
Understanding Statistics
Probability isn’t about predicting the future — it’s
about understanding how the world behaves in the
long run.

23
Understanding Statistics
“Rare Events” Happen All the Time — Given
Enough Chances

The chance of being struck by lightning in a year: 1

in 1.2 million

But in India, over 2,000 people die from lightning

every year

24
Module 3:
Estimation and Inference
•Estimating Parameters.
•Method of Maximum Likelihood (MLE), Method of
Moments (MoM)
•Sampling distribution of sample mean, sample proportion,
SE of point estimators, Central Limit Theorem
•Minimum-Variance Estimators; The Cramér-Rao Lower
Bound, Sufficient Estimators, Consistency, Bayesian
Estimation.
•Properties of Point Estimators; Other Sampling Methods.
• Interval estimators with level of confidence, etc.
25
Understanding Statistics
Estimation gets us close, and inference tells us
whether to believe what we found.

Estimation is guessing how many cups of chai

you’ve had this week.

Inference is blaming the chai for your insomnia —

with 95% confidence.

26
Understanding Statistics
Estimation: The Art of Being Precisely Wrong

The average Indian household earns ₹23,450.32

per month…

27
Understanding Statistics
Inference Is Magic — With Math

Before: You don’t know anything.

After: You run a t-test.
Now: You still don’t know anything — but with a p-
value!

28
Understanding Statistics
CLT –
We talked to 1,000 people and now we know how
the whole country feels?

29
Module 4:
Testing Hypotheses
•Null and Alternative Hypotheses, Simple versus composite
hypothesis; critical region, type I and type II errors, power of
a test; The Decision Rule, trinity of classical tests (Wald test,
Lagrange multiplier, likelihood ratio).
•Parametric Method: test of correlation; ANOVA;
Contingency tables; joint and conditional distributions; test
of independence
•Nonparametric Methods: Sign test, Wilcoxen test; Testing of
randomness;
•Comparing – Parametric and Nonparametric procedures

30
Understanding Statistics
Hypothesis testing is a method to decide whether
the pattern we observe in data is statistically
significant or just due to chance.

31
Understanding Statistics
Parametric Tests Love Rules
“Data must be normal. Variances must be equal.
Sample size must be large.”

Non-parametric tests be like:

“I’ll work with whatever you’ve got, boss.”

32
Module 5:
Regression
•Simple Linear Regression Model; Least Squares
Method; Coefficient of Determination; Model
Assumptions; Testing for Significance; Using the
Estimated Regression Equation for Estimation and
Prediction;
•Multiple Regression: Multiple Regression Model;
Least Squares Method; Multiple Coefficient of
Determination; Model Assumptions; Testing for
Significance

33
Understanding Statistics
Regression doesn't prove causation — but it tells
you where to look.

34
Understanding Statistics
Regression Doesn’t Predict the Future

It just projects the past forward

→ Like your uncle saying, “You topped in 10th

standard, so you’ll top forever.”
(Not necessarily!)

35
Understanding Statistics
Regression Is Like Indian Curry

Too many ingredients (variables), and you can’t

taste the dal.
Too few, and it’s bland.

Balance your model — or it’ll be confusing and

undercooked.

36
Module 6:
Introduction to Operation Research (OR)
•Linear Programming Problem(LPP) in any number
of variables using mixed constraints, Dual LPP and
its interpretation.
•LP Formulation and LP with solver and sensitivity
analysis.
• Transportation problems (TP): Initial solution by
NW method, LCEM and VAM; Optimise TP cost
•Assignment Problem (AP) and its optimization .
•Using solver analyse all types of LPP, TP and AP.

37
Module 7:
Advanced algorithms in OR
•Goal Programming;
•Queuing Theory;
•Networking Models
•Markov chains

38
Understanding Statistics
Operations Research is the application of
mathematical models, statistics, and
algorithms to aid decision-making and
optimize resources in complex systems.

39
Understanding Statistics
Operations Research is the application of
mathematical models, statistics, and algorithms to
aid decision-making and optimize resources in
complex systems.

OR

It helps maximize output, minimize cost, or

optimize efficiency in real-world problems.

40
Understanding Statistics
Operations Research is like the Google Maps of
decision-making.

It won’t drive for you, but it will give the fastest,

cheapest, or best route — based on inputs and
constraints.

41
Readings:
Richard Levin and Rubin. (2005): Statistical Methods for Management
Larsen, R. J., and Morris L. M. (2001): An Introduction to Mathematical
Statistics and its Applications. 3rd ed. Upper Saddle River, NJ: Prentice
Hall.
Lewis M. (2011): Applied Statistics for Economists, Routledge.
Newbold P. (2007): Statistics for Business and Economics (6th edition or
later), Prentice Hall.
Sweet, S. and Karen G.- M. (2008): Data Analysis with SPSS: A First
Course in Statistics, Allyn & Bacon, 3rd Edition.

42
Readings:
Field A. (2013): Discovering Statistics using IBM SPSS Statistics. Fourth
Edition, SAGE
Render and Stair. (2012): Quantitative Analysis for Managerial Decision
Making.
Hiller and Liberman. (2011): Operations Research.
Hamdy and Taha. (2013): Operations Research.

43
Readings:
•Gupta, S.C. & Kapoor, V.K. – Fundamentals of Mathematical
Statistics

•S.C. Gupta – Probability and Statistics

•Goon, Gupta & Dasgupta – Fundamentals of Statistics

•Kanti Swarup, Gupta & Man Mohan – Operations Research

44
45