Taught by the IIHS Urban Informatics Lab, Quantitative Skills for Urban Research and Practice focuses on building basic data interpretation and analysis skills among participants. It prepares them to use quantitative information in their work in a meaningful way. The methods are demonstrated with example problems, largely drawn from urban research and practice. Basic familiarity with MS Excel (or other similar tools) will be useful to have. No prior experience with quantitative data analysis or statistics is needed. The course is delivered online, through a mix of lectures, live demonstrations, quizzes and practice sessions in small groups.
Who this is for:
- Young researchers working in academia or in the social sector
- PhD scholars and Master’s students who would like to acquire data analysis skills
- Practitioners employed in the government, NGOs or private sector, working broadly in the areas of urbanisation, sustainable development or public policy
This course will enable participants to:
- Understand the contents of some of the large public datasets available in India
- Create quantitative and visual summaries of data using tools such as MS Excel
- Create and interpret multivariable indexes for decision making
- Appreciate how sample surveys are conducted
- Read and understand basic results from various statistical tests and regression analysis
Shriya is a faculty member at the Indian Institute for Human Settlements, teaching topics related to urban economic development and quantitative research methods. She anchors the Urban Informatics Lab. Shriya has worked extensively with datasets from the Census of India, the National Sample Survey Organisation (NSSO), and the Economic Census for various research projects. Her research at IIHS is primarily centred on the Indian urban economy and economic geography, with a particular focus on the role of employment in urban development and poverty reduction. Shriya holds a Master’s in Public Affairs with a concentration in Economics from Princeton University, and a Master’s in Mathematics from Cambridge University, UK.
Sooraj works in the Urban Informatics Lab at IIHS. His current focus is in applying statistical models to disaggregate previously aggregated demographic and socioeconomic data from the Census and national-scale sample surveys. He applies computational and statistical methods on urban data to develop a comprehensive understanding of India’s complex urban transformation. Sooraj’s academic training is in computer science and statistics. He has been teaching multiple quantitative methods courses in the Urban Fellows Programme at IIHS. Sooraj was also part of multiple quantitative methods and data visualisation training workshops for different organisations, including Atal Bihari Vajpayee Institute of Good Governance and Policy Analysis (AIGGPA) in Bhopal, and GIZ (Deutsche Gesellschaft für Internationale Zusammenarbeit) and Center for Internet & Society (CIS) in Bangalore.
Herry works in the Urban Informatics Lab at IIHS and applies quantitative methods, mixed methods and spatial data analysis across multiple practice and research projects. He has worked on projects related to urbanisation, economic development and transit-oriented development. In addition to the national-scale public data sets, Herry is familiar with various housing and real estate data sets available at different spatial scales. He regularly teaches courses in the Urban Fellows Programme and has also taught capacity building workshops on data visualisation. Herry has a Bachelor’s in Civil Engineering from Nirma University and a Master’s in Urban Planning from University of Southern California.
Programme Structure
- Delivered through a combination of lectures and discussions, tool demonstrations, hands-on activities in small groups, presentations and quizzes
- Active hand-holding and individual feedback from the faculty
- Ample peer-learning opportunities
Key Differentiators
- Live examples relevant to urban research and practice in the Indian context
- Uses various official statistics and administrative data sets from India
- Combination of conceptual understanding and hands-on practice, to enable immediate application of learning
Session Plan
| Content |
| Session 1 This session introduces the idea of measurement and the complexities involved in measuring attributes of complex entities like people, society and the economy. Further, an overview of various sources of data including the Census of India, Economic Census, National Sample Surveys (NSS), National Family Health Survey (NFHS), India Human Development Survey (IHDS) and a few important administrative data sets is presented. |
| Session 2 This session focuses on how to identify, summarise and communicate meaningful patterns from quantitative data in the context of a research question. In a univariate setting, we explain the idea of the distribution of a variable, and discuss quantitative and visual summaries of distributions. This covers histograms, probability distributions, quantiles, mean and variance using multiple examples. We further discuss quantifying relationships between two variables, covering growth, correlation, scatter plots and contingency tables. Short Excel exercises help the participants apply these ideas and interpret the results. |
| Session 3 In this session, we introduce the basic and commonly used methods for decision-making involving multiple variables. We demonstrate the construction of multi-variable indexes, show how to detect outliers and explain the concept of clustering. Several examples of indexes are discussed, highlighting their uses and limitations. In the later part of the session, participants get the opportunity to work in small groups doing hands-on analysis to practise these concepts using Excel. |
| Session 4 This session introduces the idea of random sampling and discusses the basics of how sample surveys are designed. We briefly discuss multi-stage sampling, stratification and survey weights. Then, with the help of multiple simple examples, we introduce the basics of statistical inference, covering estimation and comparison. We discuss confidence intervals, hypothesis testing and p-values, and estimate these using Excel. We end with a quiz to reinforce these concepts. |
| Session 5 In the last session of the course, we continue the exploration of statistical inference by discussing the idea of regression analysis. With a live demonstration of a simple example, the participants are shown how linear regression can be performed in Excel. Then we spend some time reviewing a few papers and reports that use regression results. In the latter part of the session, the participants work in groups to do statistical analysis, including regression analysis, of data taken from a public sample survey dataset. |
Week 1
| Friday, 14 July 2023 | |
| 02:00 pm – 03:30 pm | Measurement considerations |
| 04:00 pm – 05:30 pm | Overview of Secondary Data Sets |
| Saturday, 15 July 2023 | |
| 02:00 pm – 03:30 pm | Identifying, summarising and communicating Patterns (Part 1) |
| 04:00 pm – 05:30 pm | Identifying, summarising and communicating Patterns (Part 2) |
Week 2
| Friday, 21 July 2023 | |
| 02:00 pm – 03:30 pm | Decision-making using Multiple Variables – Indexes (Part 1) |
| 04:00 pm – 05:30 pm | Decision-making using Multiple Variables – Indexes (Part 2) |
| Saturday, 22 July 2023 | |
| 09:30 am – 11:00 am | Sample Surveys |
| 11:30 am – 01:00 pm | Basics of Statistical Inference |
| 02:00 pm – 03:30 pm | Concepts of Regression Analysis |
| 04:00 pm – 05:30 pm | Interpretation of Regression Results |
<< Back