Data Analytics Stream

Learning Outcomes and Skills

  • Formulate and test statistical hypotheses
  • Work with very large datasets of all types (Big Data)
  • Run simulation exercises using computational techniques
  • Knowledge of specialized econometric techniques such as Time Series Econometrics and Bayesian Econometrics
  • Ability to program in R and Hadoop
  • Preparation for jobs in data analytics (FMCG, retail, consulting, e-commerce etc.)
  • How to estimate Bayesian models using R

The course descriptions of each elective are given below.

 

Statistical Computing & Machine Learning

Instructor: Sunil Saraswat, Assistant Professor, University of Mumbai

Statistical computing and machine learning are techniques of recognizing patterns from data in order to develop statistical models. This course will teach students:

  • How to carry out Monte-Carlo simulations using R
  • How to aggregate data in cluster analysis to uncover similarities in large data sets
  • Neural network methods
  • How to work with Decision trees and Boosted Regression trees to model statistical relationships

 

Time Series Econometrics

Instructors: Neeraj Hatekar (Director, Department of Economics, University of Mumbai) and Anuradha Patnaik (Assistant Professor, University of Mumbai)

Many of the insights from the Core Econometrics course, which studies mostly cross-sectional data, carry over to situations where data are collected over time (e.g. financial data). However, time-series data present important challenges of their own. In this course, students will learn:

  • The difference between stationary and non-stationary time series
  • How to estimate models with stationary time series data, and in particular, how to detect and address the problem of serial correlation in these models
  • How to estimate models with non-stationary time series data, and in particular, how to work with integrated processes
  • How to estimate VAR, VEC, ARCH and GARCH models
  • How to implement econometric estimation of time series models using the statistical software R

 

Bayesian Econometrics

Instructors: Instructors: Neeraj Hatekar (Director, Department of Economics, University of Mumbai) and Anuradha Patnaik (Assistant Professor, University of Mumbai)

Bayesian econometrics allows combining of prior (pre-sample) information with sample information to estimate relatively more precise estimators. In the course, students will learn:

  • How to make sense of pre-sample information through various types of prior distributions
  • How to combine prior information with sample information to derive efficient estimators
  • How to work with Markov chains and MCMC algorithms
  • How to test hypotheses using the Bayesian framework
  • How to estimate Bayesian models using R
Workshops/Econ Labs

The Workshops/Econ Labs in this stream will cover topics such as programming in R and Hadoop, two computing languages that are very commonly used in data analytics jobs.

Request a Callback
×

REQUEST A CALLBACK

REQUEST A CALLBACK
Contact a course advisor at
022-60126001