INDIAN STATISTICAL INSTITUTE

Students’ Brochure
Post-Graduate Diploma in Applied Statistics (PGDAS)
05 August 2022

203 BARRACKPORE TRUNK ROAD

KOLKATA 700108
INDIA
 Table of Contents

General Information 4
Scope 4
Eligibility 4
Duration 4
Selection 4
Tuition Fee 5
Payment delays and enrollment 5
Cancellation and refund policy 5
Waiver of tuition fee 5
programme Structure 6
Deferment Policy 7
Course Enrollment Policy 7
Grading 8
Grading of individual courses 8
Back-paper examination 8
Timeline for quizzes, assignments and examinations 8
Assignment and examination deadline policy 8
Grade dispute 8
Conduct 9
Final Result 9
Award of Certificate 9
Change of Rules 10
Legal Disputes 10

Syllabi of Courses 11
First Semester: Compulsory Courses 11
F1: Basic Statistics 11
F2: Basic Probability 11
F3: Statistical Methods (Prerequisites: F1 and F2) 11
F4: Survey Sampling (Prerequisite: F1 and F2) 12
F5: Introduction to Official Statistical System 12
F6: Statistics and Economy 13
Second Semester: Specialisations 13
Official Statistics Specialisation (Prerequisites: F1-F6) 13
OS1: Management of Data 13
OS2: Advanced Survey Sampling 14
OS3: Population and Social Statistics 14
OS4: National Accounts Statistics and Price Indices 15
OS5: Sectoral Statistics 15

2
 OS6: Monetary, Financial System and Foreign Trade Statistics 16
Data Analytics Specialisation (Prerequisites: F1-F6) 16
DA1: Introduction to R and Python 16
DA2: Multiple Regression 17
DA3: Advanced Regression (Prerequisites: DA1 and DA2) 17
DA4: Time Series Analysis and Forecasting (Prerequisite: DA1) 17
DA5: Multivariate Statistics (Prerequisite: DA1) 18
DA6: Statistical Machine Learning (Prerequisite: DA1-DA3) 18

3
I. General Information
1. Scope
This postgraduate diploma programme, delivered online1, aims at providing the student the statistical
tools and concepts necessary to make data-driven decisions and advance their career in the fields of
applied statistics and quantitative analytics. The programme emphasises the use of real-world data,
including data from governments and international organisations that are available in the public domain.

2. Eligibility
The student should have an undergraduate degree from any recognised university in India or abroad, and
basic knowledge of high school-level mathematics.

3. Duration
The duration of this course is two semesters.

4. Selection
There are two channels of selection of candidates for this programme. Admission through the regular
channel includes a review of academic transcripts submitted by the applicants. Applicants who qualify for
the next stage are required to take a quiz for final selection. Admission through the tuition waived channel
consists of an annually conducted written test, a review of academic transcripts, and a personal interview.

Once every year, a limited number of students will be selected for complete tuition fee waiver (in other
words, no course fee) through the ISI admission test and interview. The number of seats and the selection
process are available on the ISI admission site:
https://www.isical.ac.in/~admission

Usually, the application window for the ISI admission test starts towards the end of February and remains
open till the end of March. Interested candidates are advised to visit the admission site towards the end of
February or beginning of March for details of the admission test and application process for the term
starting in August (Fall term). Note that the admission test and interviews, which are not online, are held
in India only.

The tuition fee waiver is open to everyone. Foreign nationals are treated as general category candidates
(no reservation) in the selection process. However, the ISI admission test is conducted in centres which
are located only in India. All candidates applying through this channel will have to appear in the
admission test in one of the designated centres in India and subsequently in an interview in ISI Kolkata
only. There is no provision of appearing online for the admission test and interview.

1
Further information on the programme and its delivery is available in the PGDAS webpage at Coursera.

4
5. Registration and tuition Fees2
The total fee for the course is USD 6,000 or INR 450,000. The payment must be made according to the
following schedule.

Item Amount Payment due

Registration Fee USD 500 or INR 38,000 Within 15 days of receiving the admission letter.

Semester 1 USD 2500 or INR 187,000 Five days before the beginning of the semester.
Tuition Fee

Semester 2 USD 3000 or INR 225,000 One week before the commencement of the
Tuition Fee second semester.

Total USD 6,000 or INR 450,000

Payment delays and enrollment

The deadlines for enrolling for a course and making the applicable payment are strict. If a student does
not complete the initial payment due in a semester (USD 500 / INR 38,000) by the stipulated date, he/she
will not be able to enrol in the corresponding semester.

If a student fails to make any instalment of the payment by the due date, his/her enrollment for the
semester will be cancelled. However, the partial payment already made in that semester can be carried
forward for enrollment in a subsequent semester.

Cancellation and refund policy

It is expected that, once enrolled, every student will complete the programme as planned initially. If a
student contemplates withdrawing from the programme, it is recommended that he/she discuss his/her
issues with the Student Success Advisor to figure out if the issues can be solved.

If a student still decides to withdraw from the programme before completion, he/she will have to inform
the PGDAS programme Coordinator, Indian Statistical Institute. After the formal withdrawal, the
student's access to the courses will be revoked.

All the fees are non-refundable.

Waiver of tuition fee

There is no partial waiver or financial aid on a case by case basis. One has to be admitted to the
programme through the tuition waived channel in order to be eligible for full tuition waiver.

2
A different set of fees and the payment schedule may be applicable for students joining the programme after
August 2022.

5
6. Programme Structure
The courses offered in this two-semester online programme are outlined in the following diagram.

6
The first semester consists of six compulsory courses. In the second semester, a student needs to choose
one of the specialisation tracks from Official Statistics and Data Analytics.

Each course runs for eight weeks, out of which six weeks are for lectures, quizzes, assignments and
interaction sessions. During these weeks, the student can expect a weekly workload of 8-10 hours per
week for each course. The last two weeks are for the final examination, back-paper examination (refer to
the section on course grading policy to understand the rules of the back-paper), grading and publication of
results. The results are expected to be declared in the eighth week.

At any point of time, two courses run in parallel. The sequence of courses within a semester may be
altered from the indicative sequence shown in the diagram, while maintaining the requisite order between
a course and its prerequisite.

7. Deferment Policy
This programme offers substantial flexibility in meeting the needs of students who wish to take more than
one year to complete it for some reason.

One can take up to three years (six semesters) starting from the semester which he/she initially applied for
to complete the programme. A student may also choose to take a break after the first semester and enrol
for the second semester courses in one of the subsequent semesters.

It is also possible to defer enrollment in the middle of a semester. Every semester consists of six courses,
with two running at any point of time. After completing a few of those courses, one may defer the
enrollment in the other courses to another semester.

Deferred enrollment will attract no extra fee. The payments to be made are always in advance, before the
beginning of a semester, and non-refundable. However the total amount one will have to pay is still the
same (USD 6,000 or INR 450,000).

8. Course Enrollment Policy

● Some courses can be taken only after successful completion of the respective prerequisite
courses, as mentioned in the syllabi.
● The student has to complete all six courses of the first semester before enrolling for any course
belonging to a specialisation / track.
● The student has to express an intent to choose one of the two tracks three weeks before the end of
the first semester.
● After the completion of the first semester, the student has to enrol for the next semester by paying
the appropriate fees in case he/she chooses to continue the programme in a specialisation.

The courses for which the student has enrolled will be added to his/her PGDAS Home Page on Coursera
approximately 1 day before the term begins.

7
9. Grading
a. Grading of individual courses
The grade for each individual course will be given as an absolute score, out of 100. The score will be a
weighted sum of the scores obtained in the graded assessments (assignments, quizzes and the final
examination).

The graded quizzes and assignments will have a total of 60% weightage and the final examination will
have 40% weightage.

For most courses, a major part of the final examination will be staff graded.

To pass a course, one must get a score of at least 50 out of 100.

b. Back-paper examination
If someone does not pass in a course, he/she will have to appear for another examination, henceforth
called the back-paper, which will be held immediately after the declaration of the results.

● The back-paper examination acts as a replacement for the final examination only.
● Irrespective of the performance in the back-paper examination, the maximum composite score
that a student can obtain in a course via the back-paper channel will be capped at 50%.

c. Timeline for quizzes, assignments and examinations

All quizzes, assignments and examinations will have a 24-48 hours window, within which the student can
start taking it. Once started, the student will have to finish within a stipulated time as specified in the quiz
/ assignment / examination.

d. Assignment and examination deadline policy

For all the assignments / quizzes except the final examination, a late submission will attract a penalty of
25% per day beyond the deadline. For the final or back-paper examination, a penalty of 50% per day will
be applicable. In other words, if one submits more than 24 hours after the deadline, there will be a 100%
penalty.

e. Grade dispute
In case of a grading dispute, the student may request a review of the respective module / assignment /
examination and the instructor will review the disputed issue.

8
10. Conduct
If at any point of time documents provided by a candidate for establishing his/her eligibility are found not
to be authentic, he/she will be disqualified. Any diploma provided to a disqualified student will stand
revoked.

Submitting an assignment that is not a student’s own may result in permanent failure in a course.

11. Final Result

The composite score of a student in the programme will be calculated as a simple average of his/her
scores in all the courses and this composite score will determine the final grade of the student as per the
following table.

Average Composite score range (%) Grade Grade point

90-100 A 10

80-89 B 9

70-79 C 8

60-69 D 7

50-59 P 6

Below 50 F 0

12. Award of Certificate

A student passing all the requisite courses for any specialisation is given the Post Graduate Diploma in
Applied Statistics along with a final mark sheet which includes the list of all courses taken along with the
respective composite scores and letter grades. The diploma mentions the specialisation and the overall
letter grade in the programme.

A student passing all the requisite courses for both the specialisations is given the Post Graduate Diploma
in Applied Statistics along with a final mark sheet which includes the list of all courses taken along with
the respective composite scores and letter grades. The diploma mentions both the specialisations and the
letter grade in the programme.

A student passing all courses in the first semester but not intending to complete the diploma programme is
given a Post Graduate Certificate in Basic Statistics along with a final mark sheet which includes the list
of all courses taken along with the respective composite scores and letter grades. The certificate mentions
the letter grade in the programme.

9
The diploma is awarded in the Annual Convocation of the Institute following the attainment of
qualification. If a student is unable to be present in the Convocation, he/she will receive the degree online.

13. Change of Rules

The Institute reserves the right to make changes in the above rules, programme structure and the
curriculum as and when needed. The modified rules will be applicable prospectively to students joining
the programme after the rules are modified.

14. Legal Disputes

Any legal dispute regarding grades or otherwise will be dealt under the jurisdiction of the Hon’ble High
Court at Calcutta only.

10
II. Syllabi of Courses
1. First Semester: Compulsory Courses
F1: Basic Statistics

● Different types of data and ways to load/save/export data using LibreOffice.

● Graphical presentation of data: theory and practice
● Textual representation of data, histogram, contingency tables: theory and practice.
● Measures of central tendency: mean, median, mode etc. Concept of robustness.
● Measures of dispersion: Range, mean absolute deviation, semi-interquartile range and boxplot
● Bivariate data and measures of association. Skewness and kurtosis.

(LibreOffice Calc for all computations)

References
1. Statistics (11th edition) by R S Witte and J S Witte
2. Statistics (4th edition) by D Freedman, R Pisani and R Purves
3. How to Lie with Statistics by D Huff.

F2: Basic Probability

● Randomness, basic definitions, elementary probability based on counting

● Conditional probability, statistical independence; Bayes rule
● Random variables, distributions, expected values, variance and standard deviation, correlation
● Normal approximations for different distributions
● Sampling distribution, sampling error

References

1. Applied Statistics and Probability for Engineers. Douglas C. Montgomery and George C. Runger;
Wiley (2016).
2. Introduction to Probability and Statistics for Engineers and Scientists. Sheldon M. Ross;
Academic (2014).
3. Probability and Simulation. Giray Otken; Springer (2020).
4. Simulation. Sheldon M. Ross; Springer (2013).

F3: Statistical Methods (Prerequisites: F1 and F2)

● Concept of population, sample, sampling distributions and estimation of mean, proportion and
dispersion.
● Concept of test of statistical hypotheses, one-sample, two-sample and paired t-tests.
● Analysis of variance: the concept and methodology.

11
 ● Chi-square tests for goodness of fit and independence.
● Regression and least squares.
● Introduction to time series

(LibreOffice Calc for all computations)

References

1. Mathematical Statistics with Applications by K M Ramachandran and C P Tsokos (2009).

F4: Survey Sampling (Prerequisite: F1 and F2)

● Terms and concepts in survey sampling

● Simple random sampling with and without replacement
● Systematic sampling
● Stratified random sampling
● Sampling with probability proportional to size
● Ratio and regression estimators

References

1. "A First Course in Survey Sampling" by T. Dalenius in Handbook of Statistics Vol. 6 (ed. P.R.
Krishnaiah and C.R. Rao), Chapter 2; Wiley (1988).
2. Practical Sampling Techniques. Ranjan K. Som; Marcel Dekker (1996).
3. Sampling Techniques. Wiliam G Cochran; Wiley (1977).

F5: Introduction to Official Statistical System

● An introduction to official statistics in general.

● Social statistics
● Economic statistics
● Price statistics
● Environment statistics
● Process of collection, compilation and dissemination of official statistics and their quality.

References
1. Handbook of Statistical Organization: The Operation and Organization of a Statistical Agency
(Third Edition). United Nations (2003).
https://unstats.un.org/unsd/publication/SeriesF/SeriesF_88E.pdf
2. Statistical System in India 2009. Government of India, Ministry of Statistics and Programme
Implementation.

F6: Statistics and Economy

● Basic framework of an economy and national income accounting

12
 ● Theories of growth, trade cycle and inflation
● Models of income determination
● Theories of money supply
● Determination of price in a competitive market
● Market equilibrium

References

1. Microeconomic Theory: Basic Principles And Extensions. Walter Nicholson and Christopher
Snyder; S. Chand & Co (2000).
2. Microeconomics. P Krugman and R Wells, Worth (2018).
3. Macroeconomics. Greg Mankiw; Cengage Learning India (2017).
4. Macroeconomics: Economic Growth, Fluctuations, and Policy. Robert E. Hall and David H.
Papell; Norton (2005).
5. National Accounts: A Practical Introduction. United Nations (2003).
https://unstats.un.org/unsd/publication/SeriesF/seriesF_85.pdf

2. Second Semester: Specialisations

a. Official Statistics Specialisation (Prerequisites: F1-F6)

OS1: Management of Data

● Introduction to databases, data abstraction, data integration, data validation, data indexing
● Introduction to database models, ER data model, ER diagram, normalisation, relational algebra
● Basics of SQL programming I: Database creation with SQL, database modification with SQL,
database manipulation with SQL
● Basics of SQL programming II: Dealing with nullity and duplicity in SQL, database view in SQL,
integrity control with SQL, efficient querying in SQL
● Spatial data and their uses: Introduction to spatial data, Representation of geographic features,
Survey Techniques, Storage and presentation.
● Spatial data analytics: Analysis of Remote Sensing data, Analysis of vector data, Advanced
analytical techniques for spatial data, Concepts of map making.

References

1. Database System Concepts, Sixth Edition. Avi Silberschatz, Henry F. Korth and S. Sudarshan;
McGraw-Hill (2013). http://www.db-book.com
2. Database Management Systems, Third Edition. Raghu Ramakrishnan and Johannes Gehrke;
McGraw-Hill (2014). http://pages.cs.wisc.edu/~dbbook/
3. Mining of Massive Datasets. Jure Leskovec, Anand Rajaraman and Jeff Ullman; Cambridge
University Press (2014). http://www.mmds.org
4. Geographic Information Science and Systems, Fourth Edition. Longley, Goodchild, Maguire,
Rhind, 2015, Wiley.

13
 5. Principles of Geographical Information Systems. Burrough, McDonnell, Lloyd, 2015, Oxford
University Press.
6. GIS Fundamentals: A First Text on Geographic Information Systems. Bolstad, 2016, XanEdu.
7. Introduction to Remote Sensing. Campbell and Wynne, 2011. Guilford Press.
8. GIS Technology Applications in Environmental and Earth Sciences. B. Tian, 2017, Routledge.
9. Intro to GIS and Spatial Analysis. Gimond, 2022, ebook. https://mgimond.github.io/Spatial/
10. Introductory Digital Image Processing: A Remote Sensing Perspective, Fourth Edition. Jensen,
2017, Pearson.
11. Remote Sensing and Image Interpretation, Seventh Edition. Lillesand, Kiefer and Chipman, 2015,
Wiley.

OS2: Advanced Survey Sampling

● Cluster sampling, multistage sampling

● Planning and designing of large scale sample surveys
● Small area estimation Methods and associated estimators
● Randomised response technique for surveys on sensitive issues
● Adaptive sampling and network sampling
● Some other sampling methods

References

1. Survey Methodology. Robert M. Groves, Floyd J. Fowler, Jr., Mick P. Couper, James M.
Lepkowski, Eleanor Singer and Roger Tourangeau; Wiley (2009).
2. Designing Household Survey Samples: Practical Guidelines. United Nations (2005).
https://unstats.un.org/unsd/demographic/sources/surveys/handbook23june05.pdf
3. Sampling. Steven K. Thompson , Wiley (2012)
4. Survey Sampling. Leslei Kish; Wiley (1995). [Some Part II chapters]
5. Sampling Techniques Third Edition. Wiliam G Cochran; Wiley (1977).
6. Survey Sampling: Theory and Methods, Second Edition. Arijit Chaudhuri and Horst Stenger;
CRC Press (2005).
7. Randomized Response Theory and Techniques. Arijit Chaudhuri and Rahul Mukerjee; Taylor and
Francis (1988).

OS3: Population and Social Statistics

● Population statistics
● Living standards statistics
● Labour statistics
● Health statistics
● Education statistics
● Other social statistics

References

14
 1. Sample Registration System Year Books, 1971 - 2007. Office of Registrar General of India,
Government of India.
2. Handbook on Population and Housing Census. United Nations (2009).
https://unstats.un.org/unsd/publication/SeriesF/seriesf_82rev1e.pdf
3. The Follow-up Method in Demographic Sample Surveys. United Nations Statistical Office (1992).
4. Surveys of Economically Active Population, Employment, Unemployment and Underemployment:
An ILO Manual on Concepts and Methods. RaIf Hussmanns, Farhad Mehran and Vijay Verma;
International Labour Office (1990).
https://www.ilo.org/public/english/bureau/stat/download/lfs.pdf

OS4: National Accounts Statistics and Price Indices

● National accounts atatistics

● Price indices
● Compilation of CPI
● Compilation of PPI
● SDG related indicators

References
1. Accounting for Production: Sources and Methods. Handbook of National Accounting. United
Nations (1986). https://unstats.un.org/unsd/publication/SeriesF/SeriesF_39E.pdf
2. Financial Production, Flows and Stocks in the System of National Accounts. Handbook on
National Accounting. United Nations (2015).
https://www.ecb.europa.eu/pub/pdf/other/handbookofnationalaccounting2 014en.pdf
3. Consumer Price Index Manual: Theory and Practice, ILO (2004).
https://www.ilo.org/public/english/bureau/stat/download/cpi/cpi_manual_e n.pdf
4. Producer Price Index Manual. IMF (2004).
https://www.imf.org/external/pubs/ft/ppi/2010/manual/ppi.pdf 5

OS5: Sectoral Statistics

● Agriculture and allied sector statistics

● Animal husbandry
● Fishery statistics
● Industrial statistics
● Services sector statistics
● Environment statistics

References
1. Food and Agricultural Organisation (FAO): Statistical Yearbooks. FAO, Rome.
http://www.fao.org/economic/ess/ess-publications/ess-yearbook/en/#.Xbg

15
 2. 2000 World Census of Agriculture. FAO Statistical Development, Series 12; FAO (2010).
http://www.fao.org/fileadmin/templates/ess/ess_test_folder/World_Census_Agriculture/Publicatio
ns/Census14_v16.pdf
3. Sampling Methods for Agricultural Surveys. FAO Statistical Development Series 3; FAO (1989)
http://www.fao.org/3/ca5865en/CA5865EN.pdf
4. Sample-based Fishery Surveys: A Technical Handbook. FAO (2002).
http://www.fao.org/3/y2790e/y2790e.pdf
5. International Recommendations for Industrial Statistics 2008. United Nations (2010).
https://unstats.un.org/unsd/statcom/doc08/BG-IndustrialStats.pdf
6. Framework for the Development of Environment Statistics (FDES2013).
https://unstats.un.org /unsd /environment /fdes

OS6: Monetary, Financial System and Foreign Trade Statistics

● Monetary and financial system statistics

● Government finance statistics
● Foreign trade statistics
● Balance of payments statistics
● Uses of financial data for analysis

References
1. Monetary and Financial Statistics Manual and Compilation Guide. Cartas Jose and Harutyunyan
Artak, International Monetary Fund; IMF (2017).
https://www.imf.org//media/Files/Data/Guides/mfsmcg-final.ashx
2. Government Finance Statistics Manual 2014. International Monetary Fund; IMF (2015).
https://www.imf.org/external/Pubs/FT/GFS/Manual/2014/gfsfinal.pdf
3. Government Finance Statistics Guide. European Central Bank (2019).
https://www.ecb.europa.eu/pub/pdf/other/ecb.governmentfinancestatistics guide1901.en.pdf
4. Balance of Payments Manual. International Monetary Fund; IMF (2005).
https://www.imf.org/external/pubs/ft/bopman/bopman.pdf
5. International Recommendations for Distributive Trade Statistics 2008. United Nations (2009).
https://unstats.un.org/unsd/trade/M89%20EnglishForWeb.pdf

b. Data Analytics Specialisation (Prerequisites: F1-F6)

DA1: Introduction to R and Python

● Introduction and basics of R

● Basic data analysis using R
● Working with R
● Introduction to Python
● Introduction to numpy
● Basic text analysis using Python

16
References

1. Introductory Statistics with R, Peter Dalgaard; Springer (2008).

2. Learning Statistics with R. Daniel Navarro (2015).
3. Programming in Python 3: A Complete Introduction to the Python Language (CODE). Mark
Summerfield; Pearson Addison-Wesley Professional (2010).

DA2: Multiple Regression

● Probabilistic basis of simple and multiple linear regression models

● Simple linear regression
● Multiple regression analysis
● Some tricks of the trade
● Prediction through regression modelling
● Multicollinearity and variable selection in regression

References

1. Introduction to Linear Regression Analysis. Douglas C. Montgomery, Elizabeth A. Peck and G.

Geoffrey Vining; Wiley (2021).
2. Practical Regression and Anova using R; J.J. Faraway (2002).
3. An R Companion to Applied Regression Analysis, John Fox and Sanford Weisberg; SAGE (2019).

DA3: Advanced Regression (Prerequisites: DA1 and DA2)

● Detect nonlinearity, heteroscedasticity, serial correlation and non-normality in multiple linear

regression through plots and tests
● Deal with above violations of assumptions of the multiple linear regression model
● Understand and make use of casewise diagnostics in regression
● Understand and deal with the issue of multicollinearity, Use penalised linear regression (ridge
regression, lasso and elastic net)
● Understand and use Generalised Linear Models including Logistic Regression
● Understand the importance of nonparametric regression. Splines and Kernel smoothing

References

1. Practical Regression and Anova using R. J.J. Faraway (2002).

2. Nonparametric Statistical Methods Using R. J. Kloke and J.W. McKean; Chapman and Hall/CRC
(2014).
3. Advanced Regression Models with SAS and R. Olga Korosteleva; Chapman and Hall/CRC (2020).

DA4: Time Series Analysis and Forecasting (Prerequisite: DA1)

● Descriptive plots, summary and decomposition

● ARMA modelling

17
 ● Fitting of stationary and non-stationary time series models
● Forecasting
● Model selection issues
● Advanced models

References

1. Time Series Analysis and Forecasting by Example. Soren Bisgaard and Murat Kulahci; Wiley
(2011).
2. Time Series Analysis and Its Applications: With R Examples. Robert H. Shumway and David S.
Stoffer; Springer (2017).
3. Introductory Time Series with R. Andrew V. Metcalfe and Paul S.P. Cowpertwait; Springer
(2009).
4. Basic Data Analysis for Time Series with R. DeWayne R. Derryberry; Wiley (2014).

DA5: Multivariate Statistics (Prerequisite: DA1)

● Visualisation of multivariate data: problems and solutions.

● Concept of dimension
● Principal Component Analysis
● Factor Analysis
● Multidimensional Scaling
● Correspondence analysis

References

1. Univariate, Bivariate, and Multivariate Statistics Using R: Quantitative Tools for Data Analysis
and Data Science. Daniel J. Denis; Wiley (2020).
2. Multivariate Statistics Made Simple: A Practical Approach. K.V.S. Sarma and R. Vishnu
Vardhan; Chapman and Hall/CRC (2019).
3. Applied Multivariate Statistics with R. Daniel Zelterman; Springer (2015).

DA6: Statistical Machine Learning (Prerequisite: DA1-DA3)

● Basic ideas of supervised and unsupervised classification, General recipes for classifier
construction.
● Classification based on Gaussian models: LDA and QDA. Logistic regression and GLMNET.
● Classification using kernel density estimates and kernel regression, nearest neighbour density
estimation, and nearest neighbour classification.
● Classification tree and random forest, Linear Support Vector Machines (SVMs): separable and
non-separable case, Nonlinear SVM using the kernel trick
● Neural network, single-layer and multi-layer perceptrons, backpropagation algorithm, brief ideas
of deep learning, Bagging, boosting, and other ensemble methods

18
 ● A brief introduction to clustering. Different types of similarity and dissimilarity measures,
Hierarchical methods for clustering, k-means clustering algorithm

References

1. Introduction to Machine Learning with Python: A Guide for Data Scientists. Andreas C. Müller
and Sarah Guido; O’Reilly (2016).
2. The Elements of Statistical Learning. Jerome H. Friedman, Robert Tibshirani and Trevor Hastie;
Springer (2017).
3. An Introduction to Statistical Learning: With Applications in R. Gareth James, Daniela Witten,
Trevor Hastie and Robert Tibshirani; Springer (2017).
4. Mathematical Statistics and Data Analysis. John A. Rice; Brooks/Cole (2006).
5. Data Analysis and Applications 1: Clustering and Regression, Modeling-estimating, Forecasting
and Data Mining. James R. Bozeman and Christos H. Skiadas (eds); Wiley (2019).

19