• header Image

Introduction to Data Analysis and Database

Home/ Introduction To Data Analysis and Database
Course Type Course Code No. Of Credits
Discipline Elective SPG2PP408 4

Semester and Year Offered: Semester 2 (Winter Semester)

Course Coordinator and Team: Partha Saha

Email of course coordinators: partha@aud.ac.in

Pre-requisites: None

Aim: This course is aimed to acquaint students with data sources focusing on definitions, usages and limitations and to equip students with various techniques of data analysis so that students can undertake independent empirical studies.

Course Outcomes:

  • Ability to analyse and demystify the empirics of policy documents published by different sources.
  • Undertake empirical research on topics related to Public Policy.
  • Meaningfully engage in policy debates with a view to provide insightful observations on trends and patterns of policy variables.

Brief description of modules/ Main modules:

This course consists of five modules.

Module 1: Basic Data Handling (with applications in Excel / Gretl) – Four weeks

This module will introduce students to the types of data that are more often used in Public Policy and discuss their usages and limitations. The two most widely used databases in India – Census and National Sample Surveys will be introduced and different sampling techniques will be discussed. Using various databases, this module will then explore tables, pivot tables and graphs which can be generated and provide meaningful interpretations of the same. Further, this module will discuss descriptive statistics which are often presented to summarize key aspects of a data set. This module will conclude with a discussion of association between variables – covariance & correlation.  

Module 2: A Brief Introduction to R – Two weeks

The biggest advantage of using R instead of any other software is that R is a free software (open source) environment for statistical computing and graphics. Since it is freely downloadable and quite user friendly, students will get a first-hand exposure to using software for statistical analysis without much trouble.

Module 3: Statistical Inference – Two weeks

This module will introduce students to inferential statistics branch where the overarching issue is how to make a meaningful estimate of population parameter by specifying interval of values on a number line along with a statement about how confident one can be that the interval contains the population parameter.

Module 4: Regression Analysis – Two weeks

Regression is a very important tool generally used in Economics, but now increasingly used in policy formulation exercises in order to understand relationship between two or more variables. In social science, it is extremely difficult to say with certainty what factors result in what kind of outcomes, and this is also true in public policy where in order to formulate a policy a host of factors need to be accounted for and the interaction between them are quite complex. This module will be the first entry point towards understanding this complexity. In this module the focus will be on the basic problem of causal inference and the conditions under which regression estimates can be given a causal interpretation.

Module 5: Working with Sectoral Data – Three weeks

This module is purely an application of all four previous modules mentioned above where the idea is to test as to what extent students can meaningfully apply tools and concepts in analyzing a policy matter. Students will select any one topic out of the following broad themes:

  • Public Health
  • Education
  • Rural Development
  • Labour Market
  • Urbanization

and produce an empirical policy brief (3000 words maximum) on the topic.

Assessment Details with weights:

  • First assessment will be an application of data analysis techniques (data visualization, pivot tables, descriptive Statistics, correlation) and a short note (1000 words) regarding policy focus that emerge from this analysis. This assignment will be based on census data or database of international organizations (30%).
  • Second assessment will be thematic area based data analysis (as per interest of students) which will involve the following:
  • Construction of Index & data visualization
  • Regression involving more than two independent variables
  • A critical appraisal of the database used         (30%)
  • Third assessment will be producing empirical Policy Brief on a topic from the thematic areas using the most appropriate data analysis technique (2000 words)      (40%).

Reading List:

  • Field, A., Miles, J., Field, Z. (2012), “Discovering Statistics Using R”, Sage, California.
  • Koop, Gary. (2013), “Analysis of Economic Data”, John Wiley & Sons, Sussex.
  • Larson, R., Farber, B. (2015), “Elementary Statistics: Picturing the World”, Pearson Education Limited, Essex.
  • Mukherjee, Chandan., White, H., Wuyts, M. (1998), “Econometrics and Data Analysis for Developing Countries”, Routledge, London.

ADDITIONAL REFERENCE:

  • Anderson, D, R., Sweeny, D, J., Williams, T, A. (2011), “Statistics for Business & Economics”, Cengage Learning, Delhi.
  • Stock, J, H., Watson, M, W. (2015), “Introduction to Econometrics”, Pearson, Essex.
Top