Cross Section and Panel Data Econometrics -I

Course Type	Course Code	No. Of Credits
Discipline Elective	SLS2EC225	4

Course coordinator and team- Krishna Ram

Does the course connect to, build on or overlap with any other courses offered in AUD?

The course builds on Econometrics -II (offered in the 2nd semester) MA students at AUD.

Specific requirements on the part of students who can be admitted to this course:

(Pre-requisites; prior knowledge level; any others – please specify)

Econometrics-II

No. of students to be admitted (with justification if lower than usual cohort size is proposed):

As per SLS norms.

Course scheduling (semester; semester-long/half-semester course; workshop mode; seminar mode; any other – please specify):

It is a semester-long course to be offered in 3^rd /4^th semester.

How does the course link with the vision of AUD?

The course aligns seamlessly with AUD’s vision of providing advanced skills that are used for data analysis and impact evaluation of programme and polices relevant for society.

How does the course link with the specific programme(s) where it is being offered?

The course familiarises students to the econometric theory of cross-section and panel data regression models along with practical implementation of this theory using real world data and software Stata/R. It offers an understanding of econometrics tools and techniques essential for analysis real world data. It equips students with essentials for conducting impact evaluation studies of programme and policies.

Course Details:

Summary:This course covers various econometrics techniques commonly employed in analysing cross-sectional and panel data sets. It addresses econometric challenges associated with testing economic relationships in developing countries. The course uses both theoretical and empirical techniques to teach various econometric methods. The emphasis would be on imparting skills that enable students to conduct independent empirical research. The objectives include understanding econometric problems and methods used to solve them.

Objectives:

To equip students for analysing panel data regression models, including dynamic panel data regression.
To acquaint the students with theoretical knowledge of Difference in Difference as well as the implementation of theory through software applications like R/Stata
To teach students about Randomised Control Trial (RCT).
To provide valuable skills in conducting impact evaluations using DID and RCT methods.
To enable students to analyse binary regression models in panel data context.
Expected learning outcomes:

Upon successful completion of this course, students will be able to:

Explain how a panel data regression model is different from either a cross-section or time series regression model.
Identify various econometric issues associated with cross-section and panel data regression models.
Estimate & interpret linear panel data regression model using statistical software, R/Stata.
Estimate advanced categorical dependent variable regression models.
Complete empirical project relating to cross-sectional and Panel data set using the statistical package, R/Stata
Complete impact evaluation studies using DID and RCT methods.
Estimate and interpret the quantile regression model using Stata/R.
Overall structure (course organisation, rationale of organisation, outline of each module):

The course consists five main modules :

Endogeneity, Causality and the use of Randomized Control Trial (RCT)
This module begins with a discussion of endogeneity issue of regression model and how it affects causality inferences and properties of OLS estimators. Then, it discusses how RCT take care of the endogeneity problem and gives us the best casual results.

Difference in Difference (DID)

This module includes the basic DID model, Difference in Difference in Difference (DDD), and Staggered DID Models.

Panel Data Regression Models

This module includes both basic panel data regression models. It begins with a discussion of the advantages of panel data, including the estimation of pooled, fixed effect least square dummy variable regression model. The module then covers the estimation of fixed and random effect modes and post-regression diagnostic tests. It deals with both balanced and unbalanced panel data regression.
Ordinal & Multinomial Logit/Probit Regression Model
This module primarily focuses estimation the estimation of advanced categorical dependent regression models, such as ordinal and multinomial models. These models are used when categorical dependent variables have more than two categories.

Quantile Regression

Contents (week-wise plan with readings):
The main textbooks for the course will be:
J. Wooldridge (2010): Cross Section and Panel Data Regression, 2^nd ed. MIT Press, Ch- 6,7,10,12, & 15
[AP] Angrist, J.D and Pischke, J. S. (2008), Mostly Harmless Econometrics: An Empiricist’s Companion, Princeton University Press.
Long, S. J (1997). Regression models for categorical dependent variables, Advanced Quantitative technique in Social Sciences series, Vol 7, Sage Publications, London.

Articles:

Duflo, E., Glennerster, R., & Kremer, M. (2007). Using randomization in development economics research: A toolkit. Handbook of development economics, 4, 3895-3962. Roth, J., Sant’Anna, P. H., Bilinski, A., & Poe, J. (2023). What’s trending in difference-in-differences? A synthesis of the recent econometrics literature. Journal of Econometrics.
Callaway, Brantly, and Pedro H. C. Sant’Anna. “Difference-in-differences with multiple time periods.” Journal of Econometrics, Vol. 225, No. 2, pp. 200-230, 2021.

Week*	Plan/ Theme/ Topic	Core Reading (with chapter no.)	Additional Suggested Readings	Assessment (weights, modes, scheduling)
1-2	Randomised Control Trial (RCT)	AP, Ch -1-2 Duflo et al. (2007)	JPAL resources on RCT: https://www.povertyactionlab.org/research-resources?view=toc#choose-a-view
3-7	Panel Data Regression	Wooldridge, Ch-7, 10 AP- Ch-5
8-11	Difference in Difference (DID)	Wooldridge, ch-6, Roth et al. (2023), Callaway & Sant’Anna(2021), AP- Ch-5	DID resources available on the following repository: https://asjadnaqvi.github.io/DiD/ https://taylorjwright.github.io/did-reading-group/	Mid- Term(50%)
12	Ordinal Regression Model	J.Scott Long - Ch-5 Wooldridge: Ch-16
13-14	Mutinomial Regression Model	J.Scott Long - Ch-5 Wooldridge: Ch- 16		End Term (50%)
15	Quantile Regression	Wooldridge: Ch- 12

Note: *This is only a tentative week plan.

Pedagogy:

. Instructional strategies: lectures.
. Special needs (facilities, requirements in terms of software, studio, lab, clinic, library, classroom/others instructional space; any other – please specify): Classroom equipped with a projector.
. Expertise in AUD faculty or outside: Economics faculty at AUD are competent to handle the course.
. Linkages with external agencies (e.g., with field-based organizations, hospital; any others) NA.