BA Modern Language and Business & Management (Chinese)

The general purpose of this course is to provide students with a non-technical introduction to the basic methods of econometrics. The focus will be on:

1. enabling students to perform basic data handling (uploading, re-categorising, cleaning) in a statistical software and to implement the statistical techniques taught in the course in that software;

2. giving students a basic understanding and working knowledge of multivariate regression;

3. developing students' understanding of the difficulties associated with drawing causal inference;

4. developing students' understanding of popular techniques of establishing causal relationships;

5. understanding issues arising from non-stationary time-series and gain a beginning understanding of time-series modelling and forecasting

6. enabling students to read, understand and critically assess published empirical research using the techniques taught in the unit

 

At the end of this course students should be able to:

• Understand how the use of statistics and econometrics can inform substantive discussion

• Have obtained a firm understanding of summary statistics

• Understand the basic tenants of regression analysis

• Understand issues arising from non-stationary time-series

• Understand the difficulties in establishing causal relationships

• Understand popular techniques of establishing causal relationships

• Be able to handle complex dataset and perform basic data-cleaning tasks

• Be able to perform statistical analysis in a software package (R)

• Read, understand and critically assess published empirical work

ECON20222 Prerequisites: (ECON10071 and ECON10072) or ECON10061 and SOST10062)

(ECON10071 and ECON10072) or (ECON10061 and SOST10062)

The general purpose of this course is to provide students with a non-technical introduction to the basic methods of econometrics. The focus will be on:

1. enabling students to perform basic data handling (uploading, re-categorising, cleaning) in a statistical software and to implement the statistical techniques taught in the course in that software;

2. giving students a basic understanding and working knowledge of multivariate regression;

3. developing students' understanding of the difficulties associated with drawing causal inference;

4. developing students' understanding of popular techniques of establishing causal relationships;

5. understanding issues arising from non-stationary time-series and gain a beginning understanding of time-series modelling and forecasting

6. enabling students to read, understand and critically assess published empirical research using the techniques taught in the unit

The exact syllabus may vary and the following is indicative

An Introduction to R and RStudio and Summary Statistics

Understanding the basic workings of R. Importing data. Basic data operations including summary statistics. How to fix problems. Slicing data in different dimensions and conditional summary statistics.

Multivariate Regression Analysis and Inference - and Applications in R

Assumptions and resulting properties of multivariate regression analysis. Omitted variable bias. Basic inference problem. Test statistics and their distribution under the null hypothesis. P-values. Assumptions and robust inference (as standard!). t-tests and F- tests.

Causal relationships - Selection issues and applications of regression models

An introduction to issues arising when attempting to establish a causal relationship.

Introduce selection problems (on observables and un-observables). Understanding that regression helps when selection is on observables. Selection on unobservable as the source of difficulties.

Panel data and Difference in Difference - and Applications in R

Cross-Section or Panel structure of data. How to use Panel data to remove time-invariant unobservables.

Correlation, Causation and non-Stationarity in Time-Series Data

Understanding the characteristics of non-stationary data. Spurious regressions.

Economic forecasting - Understanding the pitfalls

Use Surveys of Professional forecasters to understand variation in forecasts and

uncertainty embodied in forecasts. Use AR(1) model to produce basic forecasts. Basic tenants of forecast evaluation. Evaluating forecasts for binary outcomes.

Synchronous activities (such as Lectures or Review and Q&A sessions, and tutorials), and guided self-study

At the end of this course students should be able to:

• Understand how the use of statistics and econometrics can inform substantive discussion

• Have obtained a firm understanding of summary statistics

• Understand the basic tenants of regression analysis

• Understand issues arising from non-stationary time-series

• Understand the difficulties in establishing causal relationships

• Understand popular techniques of establishing causal relationships

• Be able to handle complex dataset and perform basic data-cleaning tasks

• Be able to perform statistical analysis in a software package (R)

• Read, understand and critically assess published empirical work

(i) problem-solving skills; (ii) ability to analyse and interpret empirical data; (iii) the

evaluation and critical analysis of arguments, theories and policies; (iv) synthesise and evaluate data.

(i) ability to analyse and interpret empirical data; (ii) good working knowledge of statistical software.

(i) select and deploy relevant information; (ii) communicate ideas and arguments in writing and verbally; (iii) apply skills of analysis and interpretation; (iv) manage time and work to deadlines; (v) use ICT to locate, analyse, organise and communicate information (e.g. internet, on-line databases, search engines, library catalogues, spreadsheets, specialist programs, word processing and presentation software) (vi) ability to work in a small group.

• 10% in-term assessment (R skills, online test)
• 40% group project (2000 words)
• 50% final exam

Online quizzes, Practice questions in computer and exercise classes, office hours, discussion board

Joshua D. Angrist & Jörn-Steffen Pischke (2014) Mastering 'Metrics: The Path from Cause to Effect, Princeton University Press