Grading

Your grade in this course will depend on your 5 assignments and Final Exam as follows:

Assignments 60%

Final 40%

You get graded based directly on your assignments, and also indirectly through the exams, which will have code- and paper-based questions based directly on the assignments that you have undertaken. As you can see, the purpose of this course is to get you to do structural econometrics, via the assignments.

Assignments

These are empirical assignments where you need to work with real data to answer real questions. You may use Stata or whatever other software you like (e.g., R). A good start is to do the stata tutorials linked below. All requests for Stata help should be preceded by you googling "help stata whatever" and typing "help whatever" in Stata. In Stata, the help menus have examples at the bottom. Good starts here "help use", "help recode", "help keep" and "help regress".

Final Exam

As noted the final exam will focus on your assignments and the assigned readings. PhD students will also be required to produce an independent research note (due mid August) in which they provide a structural model and estimate its parameters. MA students may choose to produce such a research note in lieu of a Final exam.

Assigned Readings:

Ackerberg, Daniel, et al. "Econometric tools for analyzing market outcomes." Handbook of econometrics 6 (2007): 4171-4276. (BLP primer).

Angrist, Joshua D., and Jorg-Steffen Pischke. Mostly harmless econometrics: An empiricist's companion. Princeton university press, 2008, chapter 3. (regression primer)

Blume, Lawrence E., et al. "Identification of social interactions." Available at SSRN 1660002 (2010). (Manski primer)

Donni, Olivier, and P.A. Chiappori, 2013, "Collective Household Models".

Dunbar, Geoffrey R., Arthur Lewbel, and Krishna Pendakur. "Children's resources in collective households: Identification, estimation, and an application to child poverty in Malawi." The American Economic Review 103.1 (2013): 438-471.

Head, Keith, and Thierry Mayer. "The empirics of agglomeration and trade." Handbook of regional and urban economics 4 (2004): 2609-2669.

Lewbel, Arthur and Krishna Pendakur. 2009. "Tricks with Hicks: The EASI Demand System", American Economic Review.

Lewbel, Arthur and Krishna Pendakur. 2015. "Generalised Random Coefficients: Unobserved Preference Heterogeneity in a Semiparametric Demand Model, with an Application to Energy Taxation", unpublished working paper.

Overman, Henry G., Stephen J. Redding, and Anthony J. Venables. "The economic geography of trade production and income: a survey of empirics." (2001). (gravity primer)

Pendakur, Krishna. "Semiparametric estimates and tests of base-independent equivalence scales." Journal of Econometrics 88.1 (1999): 1-40.

Pendakur, Krishna. "Taking prices seriously in the measurement of inequality." Journal of Public Economics 86.1 (2002): 47-69.

Vermeulen, F. (2002). Collective household models: principles and main results. Journal of Economic Surveys, 16(4), 533-564. (Chiappori primer)

Baldwin, R., and D. Taglioni (Gravity for dummies and dummies for gravity Discussion paper, National Bureau of Economic Research.

Head, K., and T. Mayer (2013): Gravity equations: Workhorse, toolkit, and cookbook. Centre for Economic Policy Research. equations,2006)

Supplementary Reading

There are 3 supplementary textbooks for this course:

Green, William, Econometric Analysis, Prentice Hall, 5th/6th Edition, 2008.

Kennedy, Peter, A Guide to Econometrics, 5th or 6th Edition (Paperback).

Angrist, Joshua and Jorn-Steffen Pischke, Mostly Harmless Econometrics: An Empiricist's Companion (Paperback).

I will try to let you know where to look for relevant supporting material in these textbooks. In addition, I will post links to other material you may find helpful.

Stata Links

Useful links for learning Stata are at UCLA economics Stata Tutorials .

Benjamin Philips' Tips for Using Stata.

Lecture Notes

Endogeneity and Correlated Missing Regressors

long lecture Notes on Endogeneity.

short lecture Notes on Correlated Missing Regressors.

More on Venn Diagrams for Regression, Peter Kennedy, 2002. This paper presents the Ballentine Diagrams discussed in class, relating to Multicollinearity and Endogeneity.

Read Chapter 3 of Mostly Harmless Econometrics.

Lecture notes on Demand.

Lecture notes on Heterogeneity.

Lecture notes on Collective Household Models.

Everyone: Read Taking Prices Seriously in the Measurement of Inequality for Friday 22 May

PhDs and interested MAs: Read Generalised Random Coefficients for Friday 29 May.

PhDs and interested MAs: Read Tricks with Hicks for Friday 29 May.

Everyone: Read Collective Engel Curves for Friday 5 June.

PhDs and interested MAs : Read Children's Resources in Collective Households for Friday 5 June.

PhDs and interested MAs: Read Vermeulen, and read Donni and Chiappori for Friday 5 June.

Empirical Industrial Organisation

Lecture Notes on Characteristics Models, Discrete Demands and BLP.

Lecture Notes on Limited Dependent Variables.

Everyone: Read Ackerberg et al (handbook chapter) pages 1-33. PhDs and interested MAs: Read the rest of Ackerberg et al.

Assignment 1 is due in-class Friday 22 May

Canada has provincial and federal sales taxes. The federal sales tax, called GST, was introduced in 1991 at 7%, and was reduced to 6% on July 1, 2006, and to 5% on January 1, 2008. See wiki articles on the GST and HST. The sales tax reductions in 2006 and 2008 applied only to a subset of all commodities purchased, excluding food at home (aka: foodin), rent, medical expenditures and books (see wikis). Estimate the ATE of the tax change on peoples' spending patterns. Use whatever sample restriction you feel is appropriate, whatever commodities you think are appropriate, and model you think is appropriate. Write a short note (2-3 pages) describing your choices and findings. Do not feel constrained to use my demographic variables z*, nor any or all of my priced goods s* (p*). Pay attention, though, to the nature of rental shelter expenditures s3: they are zero for nonrenters.

Use this datafile, and or this zipped one, plus zipped documentation . It contains the complete Surveys of Household Spending from 1997 to 2009. In the data, the labeling conventions are: s* are spending categories 1-13 in nominal dollars

p* are natural logs of prices for goods 1-13, which vary across province and year only, and are all equal to 0 in Ontario in 2002. Note that good 3 is rental shelter, so p3 is the log of the rental price and s3 is the household expenditure on rental shelter. Consequently, lots of households have s3=0, because they t pay rent. z* are 22 demographic controls, with self-explanatory labels.

yearbuip is 6 decades, with 6 being the most recent. typdwelp is categorical, single-detached, condo etc. hhinctot is the total income of the household. hhszd31p is number of people in the household at December 31. numbedrp is number of bedrooms. numbthrp is number of bathrooms. rpagegrp is age of household head minus 40. rpmarp is marital status of respondent. weight is the sample weight. Use aweight=weight to compute poverty statistics, e.g..

How much heterogeneity is there across individuals in the cost-of-living increase in Canada over 1997 to 2009? Answer this question by estimating a nonhomothetic demand system (of your choice). Please do not use a package to do this estimation. Write the NLSUR or GMM code yourself. Submit: a) your code, with some comments so I can follow it; b) a short note (like 2 pages) describing and defending your measurement and modeling choices; c) a figure or two, and/or a table or two, with a paragraph or 2 describing your answer to the question posed above.

Assignment 3 is due in-class Wednesday 10 June

Read Browning, Chiappori and Lewbel 2013 (at least to page 10) and Lewbel and Pendakur 2008. Estimate indifference scales for men and women using the demand-system methods of BCL 2013 or the Engel-curve methods of Lewbel and Pendakur 2008 (both use the economic model of BCL 2013). Use barten-scales for scale economies, that is a diagonal Gorman price scaling matrix and no overheads. Use whichever goods you think you should use, and whatever sample you think you should use. Use your estimates to discuss the difference between across household inequality and within-household inequality.

Estimate micro-demand system parameters using aggregate (province-year) level data on market-level demands, using simulation-based estimation (as in Pakes 1986). Try to estimate the parameters of a simple QAI demand system with at least 5 goods and at least 2 demographic parameters, using both standard micro-data (as you did in Assignment 1, and using the aggregate market-level data. Write a note that answers: How good is this approach in recovering the micro-level parameters?