2015 Training Course - Productivity and Efficiency Analysis

Event Date
Saly Portudal (Thiès), Senegal



When we look at firms, we notice that the output of each can vary tremendously. If we assume that the firms are using the same technology, then what can account for such disparate outcomes. Productivity and efficiency analysis engages in exactly this exercise, discerning which firms are doing the best with the limited resources they have, and identifying which  firms are lagging behind. Productivity and efficiency methods are widely used by regulators to monitor the behavior of firms in a given industry as well as to track performance over time of firms. Given the broad array of methods, coupled with myriad applications, accessing this literature can be daunting. This class will introduce students to the fundamentals of productivity and efficiency analysis. The class will also discuss in detail implementation of these models using the popular open source software R. The class will take place over five days to ensure maximum coverage of the core topics.

Applications must be submitted by June 15, 2015



Participants will be introduced to a set of parametric, semi- and nonparametric econometric models focusing on the measurement of efficiency and productivity with real world applications that illustrate each of the models. The applications will include production, cost, and distance function estimation. Special emphasis will be given to modeling and estimating production/cost efficiency models. The open source statistical software R will be used for all empirical demonstrations. By the end of the class participants will be able to undertake a research project using either parametric and/or semi- and non-parametric stochastic frontier approaches.

Course Outline

Day 1: 

  • Introduction to R using the basic linear regression model (all notes, data and examples will be provided)
  • Notions of efficiency from a primal perspective will be introduced and the use of both the primal and distance function perspectives will be discussed. The emphasis will be on technical efficiency.
  • Cross-sectional methods: distribution free and maximum likelihood
  • Do distributional assumptions matter?
  • Estimating firms specific inefficiency
  • Computer Tutorial

Day 2:

  • The importance of skewness: tests of skewness, identification, finite sample approaches
  • Inference for firm-specific inefficiency: confidence intervals, prediction intervals and bootstrap approaches
  • Introduction of panel data models and discuss various specifications with or without technical change.
  • Distribution free methods
  • Maximum likelihood estimation
  • Heterogeneity vs. time constant inefficiency
  • Measuring technical change
  • Computer Tutorial

Day 3:

  • An overview of nonparametric smoothing
  • Kernel density and regression estimation
  • Modeling production and cost nonparametrically
  • Determinants of inefficiency
  • Mean vs. variance effects
  • The scaling property of inefficiency
  • Estimation of the stochastic frontier model with limited distributional assumptions
  • Computer Tutorial

Day 4:

  • Semiparametric estimation of the stochastic frontier model
  • Flexible functional forms
  • Imposing economic constraints in production frontier models
  • Model averaging for stochastic frontier models
  • Computer Tutorial

Day 5:

  • Endogeneity in nonparametric models
  • Estimation of cost frontiers: single equation and system estimation
  • Alternative stochastic frontier models
  • Dealing with heterogeneity in stochastic frontier models
  • Computer Tutorial


The course level is appropriate for participants with a background in economics, statistics, mathematics, and/or public policy. A strong background in quantitative analysis is required. Basic knowledge of the statistical software R is desirable. A general fluency in the statistical/econometric lingo at the (post-) doctoral level (hope-fully in a non-statistics/econometric discipline) is required. More specific ally, the Law of Large Numbers and the Central Limit Theorem should be understood.

Software Requirements

This course will heavily leverage implementation in R, a powerful statistical software package that is freely available. R possesses the facilities to implement an impressive array of stochastic frontier methods. Moreover, R's real strength is that users can readily and easily construct their own estimators and tests so that canned approaches do not need to be relied on, allowing users to stand on their legs when conducting empirical research.


In order to apply for this course, AGRODEP members must complete the following by June 15, 2015:

If you would like to practice using Stata before taking the proficiency test, please review the modules below. Information included covers Stata use for beginners, linear regressions, bivariate regressions, and panel data. You will need to know this information to successfully complete the test.

Real Data Nonparametric Applications

Every participant is allowed to submit one application, no later than 4 weeks before the course. A selection will be made from the submitted applications to discuss in detail in the class and to illustrate the practical pitfalls that are encountered with real data. Additionally, applications and data sets taken from published research will also be made available for the class to provides participants with a truly hands on approach to engaging in efficiency analysis.



Christopher F. Parmeter is an Associate Professor in the Economics Department at the School of Business Administration at the University of Miami. His area of expertise is in applied econometrics with special interests in semi- and nonparametric methods, benefit transfers, meta-analysis and efficiency analysis. Dr. Parmeter has coauthored 30 peer reviewed scientific articles in leading econometric and applied economics journals.