Universitat Internacional de Catalunya
Econometric Management Techniques
Other languages of instruction: English, Spanish
If the student is enrolled for the English track then classes for that subject will be taught in the same language.
Teaching staff
Mondays 13:00-14:00 or Wednesdays 16:00-17:00. Location: Beta3, despatx IRAPP. Important: please send an email in advance in order to confirm your meeting with the instructor (tmora@uic.es).
Introduction
This is an introductory econometrics course for undergraduates. Its main focus is to introduce the multiple linear regression model (MLRM), which is the most widely used vehicle for empirical analysis in economics, business and other social sciences. MLRM can be used for estimating economic relationships, testing economic theories, and evaluating and implementing government and business policy. The emphasis in this course is on understanding and interpreting the assumptions of the MLRM in light of actual empirical applications. The course includes regular review sessions containing problems solving and problem sets using the econometrics software Stata. Problem sets will focus on applications in various fields including health economics, labor economics and business economics.
From 2026-27, the mechanics of the analysis (estimation and computation) are delegated to artificial-intelligence tools, with Stata as the reference, and the central aim of the practical sessions becomes for the student to learn to judge critically whether the econometric output is correct —units, assumptions, omitted-variable bias, functional form, specification— and to detect and correct its errors.
Pre-course requirements
Basic knowledge of statistics, probability and matrix algebra is required. Students can refer to appendices A to D in Wooldridge’s “Introductory econometrics” textbook.
Objectives
The main objective is to introduce the student to the basic concepts of econometrics and main steps that involve an applied econometric analysis (specification of the initial model, search of data, application of estimation techniques and statistical inference, interpretation of results and improvement of the model). The student is expected to learn how to correctly interpret and evaluate econometric results. This course should provide an adequate basis for expanding further in more advanced courses both the theoretical and applied econometric skills acquired by the student.
Additional:
To learn which are the most common issues within MLRMs (omission of relevant variables and other specification problems).
To apply computer tools to obtain estimates and test results in order to solve econometric problems.
Competences/Learning outcomes of the degree programme
- 19 - To analyse quantitative financial variables and take them into account when making decisions.
- 41 - To be able to descriptively summarise information.
- 42 - To be able to empirically analyse financial phenomena.
- 43 - To acquire skills for using statistical software.
- 44 - To be able to select appropriate econometric methods.
- 45 - To be able to work with academic papers.
- 47 - To acquire skills for using econometric software.
- 50 - To acquire the ability to relate concepts, analyse and synthesise.
- 51 - To develop decision making skills.
- 52 - To develop interpersonal skills and the ability to work as part of a team.
- 53 - To acquire the skills necessary to learn autonomously.
- 54 - To be able to express one’s ideas and formulate arguments in a logical and coherent way, both verbally and in writing.
- 64 - To be able to plan and organise one's work.
- 65 - To acquire the ability to put knowledge into practice.
- 66 - To be able to retrieve and manage information.
Learning outcomes of the subject
At the end of this course, students will have a basic knowledge of the econometrics software Stata and of linear regression analysis allowing them to design an econometric model, estimate it and interpet its estimation results.
Students will be able to understand empirical studies that use linear regression models.
Students will be able to use real data and linear regression analysis to make economic or business policy recommendations, and to help economic and managerial decision making.
In addition, students will be able to critically assess econometric results generated by artificial-intelligence tools, identify their most common errors (units, omitted-variable bias, over-controlling, functional form, significance versus magnitude) and correct them.
Syllabus
Lesson 1. Introduction.
1.1 Concept of Econometrics.
1.2 Economic and econometric models.
1.3 Elements of the model: relations, variables and parameters.
1.4 Limitations of Econometrics.
Lesson 2. The classical model of multiple linear regression: estimation.
2.1 Specification.
2.2 Basic Assumptions of multiple linear regression model standard.
2.3 Estimation by ordinary least squares (OLS). Statistical properties.
2.4 Analysis of the residuals and estimation of the variance of the disturbance term.
2.5 Measures of goodness of fit and model validation.
2.6 Partial regression and the Frisch–Waugh–Lovell theorem
Lesson 3. The classical model of multiple linear regression: Hypothesis testing and prediction.
3.1 Formulation of hypotheses.
3.2 Comparison of linear constraints.
3.3 Restricted least squares estimation (MQR).
3.4 Comparison of individual and joint significance.
3.5 Point prediction and prediction interval.
Lesson 4. Regression models with the inclusion of qualitative variables.
4.1 Qualitative Variables and dummy variables.
4.2 Specifying dummy variables.
4.3 Including dummy variables in the MLRM and applications.
4.4 Interactions and group-specific effects: reading the reference-group coefficient.
4.5 Group differences and structural change through dummy-variable interactions.
Lesson 5. Specification error and functional form misspecification.
5.1 Errors in the specification of the explanatory variables.
5.2 Problems associated with the omission of relevant variables.
5.3 Consecuences of the inclusion of irrelevant variables.
5.4 Errors in the specification of the functional form and random disturbance.
5.5 Consequences for OLS estimation: alternative estimators.
5.6 Good and bad controls: confounders versus mediators (bad controls).
5.7 Model selection: adjusted R², information criteria (AIC/BIC) and comparison on the same sample.
Lesson 6. Multicollinearity, diagnostics and applied analysis.
6.1 Multicollinearity: detection (VIF) and consequences.
6.2 Influential observations and outliers (leverage, Cook's distance).
6.3 Measurement error and attenuation.
6.4 Integrative applied case: critical judgment of AI-generated econometric output.
Teaching and learning activities
In person
The theory sessions present each technique and alternate with judgment labs. In these labs, the mechanics of the analysis (estimation and computation) are done by an artificial-intelligence tool —with Stata as the reference— and the student's task is to judge whether the econometric output is correct: units, assumptions, omitted-variable bias, functional form, significance versus magnitude and specification. Each lab combines a short consequence simulator (warm-up), a group debate and an individual exit ticket. Mid-course there is an in-class group AI audit (the team uses a live AI and must judge its output, with a log of the prompts used) and a midterm exam. The cases work on real data (WAGE1, sabi05) and a synthetic firm dataset (PIMEs) with a known model.
Evaluation systems and criteria
In person
Fully in-person, in the classroom. Assessment combines four components (70% individual):
- Exit tickets (20%): one per judgment lab; individual, via a Google Form with group and number. You must name the trap and give its correct reading. An absence counts as 0.
- In-class group AI audit (30%): in teams of 4-5, in a face-to-face session where they use a live AI on a case with traps; they submit a reasoned verdict plus the prompt log before leaving. Judgment is graded, not the destination. The two groups work different cases (and in different languages) to prevent leaks.
- Midterm (20%): individual mid-course checkpoint; does NOT exempt material.
- Final June exam (30%): individual audit with 10 traps on real data; covers ALL classes.
To pass the subject you must obtain at least a 5 out of 10 in the final June exam.
Re-sit exam
- If you fail the main exam, you will need to retake it in June. In this case, the final grade of the subject will depend 100% on the final examination of the re-sit exam. That is, the continuous assessment will NOT be taken into account.
- According with the internal rules of the Faculty, the maximum grade you could get in the re-sit exam is a 7.
Observations:
* To pass the course it is essential to get at least a 5 at the final exam of the subject, otherwise you must go directly to the re-sit exam. If the mark of the final exam is less than 5, the maximum total final mark for the subject will be 4,5 (even when accounting for the continuous assessment would lead to a mark greater than 5).
** COMPULSORY ASSISTANCE: In order to attend any exam (final or re-sit exam) you need to attend more than 75% of classes. If you miss more than 4 classes, then you will not be allowed to attend the exam. In this course the professor does not need to know the justification of your absence but you are only allowed to miss 4 classes. Exceptions occur with students that have professional sport competitions duties. In this case, please contact the professor.
Bibliography and resources
Angrist, J. D. & Pischke, J.-S. (2009). Mostly Harmless Econometrics. Princeton University Press.
Artís, M. et al. (1999). Introducció a l'econometria [in Catalan]. Editorial UOC.
Greene, W. H. (1997). Econometric Analysis. 3rd ed. Prentice-Hall.
Gujarati, D. N. (1995). Basic Econometrics. 3rd ed. McGraw-Hill.
Johnston, J. & DiNardo, J. (1997). Econometric Methods. 4th ed. McGraw-Hill.
Newbold, P., Carlson, W. & Thorne, B. (2012). Statistics for Business and Economics. Pearson.
Wooldridge, J. M. (2012). Introductory Econometrics: A Modern Approach. South-Western, 5th ed.