Timberlake Consultants Ltd, the publisher of OxMetrics, invite you to attend a three days course in Central London, covering the use of Discrete Choice Models in Economics and Marketing. OxMetrics will be the main software used during the course. OxMetrics offers a module DCM dedicated to the estimation of these models.

The Course

The course is designed to introduce participants to the recent empirical literature on industrial organisation. This literature brings together economic theory and recent advances in econometric inference, and enables academics, consultants and policy makers to evaluate a large number of interesting issues such as:

• defining the market
• the measurement of market power
• evaluate the impact of new, yet to be introduced, products
• elicit consumer preferences for both existing and new products
• determine the impact of a tax on product demand
• the impact of a merger on prices

The course combines theory, econometric methodology and where possible, hands-on computer sessions. Topics to be covered will include: demand estimation, the benefits of new products, estimation with a large number of differentiated and merger simulation.

The structure of the course has been designed so as to account for the variation in the participants exposure to econometrics. In particular, sessions will be labelled intermediate, advanced, or both. Intermediate sessions will assume that participants have an undergraduate degree in economics and some basic exposure to statistical and econometric methodology. Advanced sessions will include additional lectures that as a prerequisite requires familiarity with the material covered in the intermediate sessions; this may have been obtained either by taking an optional econometric paper as part of a degree, or hands-on modelling.

A primary objective of the course is that participants should be able to formulate structural models of competition, understand and implement feasible econometric techniques, test hypothesis and perform policy analysis.

Objectives of the course

The objectives of this course are to provide participants with:

• an overview of econometric methodology that will serve as a prerequisite for the more advanced demand modules on emprical IO. This part of the course includes:
  • Underpinnings of discrete choice modelling
  • Discrete Choice: Parameter Interpretation and Identification
  • The Conditional and Multinomial Logit Model
  • An overview of the Method of Maximum Likelihood
• an introduction to the theory and application of industrial organisation
• an overview of demand estimation with homogenous and differentiated products
• a consideration of the evaluation and impact of new products
• an overview of recent developments in discrete choice modelling
• a consideration of product versus characteristic approaches to demand estimation
• how to take a theory to data. This part of the course includes:
  • econometric models which generate flexible substitution patterns
  • estimation with an extremely large choice set
  • dealing with endogeneity in nonlinear choice models
  • hands-on modelling using data from a number of applications including the demand for new motor vehicles and the demand for 3G mobile phones.
• an introduction to Simulation-Based Estimation

The overview of discrete choice modelling is provided as a precursor to an introduction to demand estimation across a set of differentiated products. In this respect the discussion of the specification of the econometric model is designed such that key objects such as cross-price elasticities of demand reflect both similarities and differences across products. We progress from the basic standard two choice logit and probit model, to a class of models which in various ways facilitate the representation of a wide range of choice behaviour, and flexible substitution patterns. This class of model, including mixed (random coeffcient) logit, has been used extensively in empirical industrial organisation. As a natural complement to the material on both the mixed logit and multinomial probit model, we provide a gentle introduction to the use of simulation in a classical setting. We emphasise that although throughout the course an exposition of the underlying econometric issues will be provided, the emphasis will be upon applied issues. To this end a number of applications will be introduced. These applications examine a range of key issues in industrial organisation and marketing including the evaluation of new products, forecasting product penetration, the estimation of own and cross-elasticities across di_erentiated products, and stated preference analysis for mobile communications

Participants are also introduced to two software packages that have been used by experts working in this area. DCM (Discrete Choice Models) a new user-friendly package, which may be used to estimate a wide range of discrete choice models. The latest version of DCM has been significantly revised and includes a large number of new functions that allow the user to estimate demand models for highly differentiated products. Problems of endogeneity can also be addressed. Recently a model involving approximately 2000 choices was estimated. An overview of the Ox Professional package is also provided. Ox Professional is a statistical programming language that has been used to estimate high dimensional demand systems across differentiated products.

Economic Research/ Model Building

Financial Modelling/ Arbitrage Trading

Labour Economists
Quantitative Investment Management

Marketing Research Analysts
Sales and Inventory Forecasting

Traffic Modellers

Energy Load Forecasting

University Instruction

and more

Advantages - The course will

• Review all major econometric models used to model choice.
• Provide a practical and systematic approach to the modelling discrete choice models in a variety of business and financial applications.
  
• Provide hands-on experience in building discrete choice models - each delegate is provided with a computer throughout the course
  
• Provide an opportunity for you to meet with a panel of experienced modellers to discuss industry-specific applications related to discrete choice models.
  

Dr Melvyn Weeks, University Senior Lecturer and Fellow of Clare College, Cambridge University. Dr Weeks main research interests are Microeconometrics, Estimation and Testing of Labour Supply Models. Latent Variables Models. Macroeconometrics, Testing of Non-Linear Threshold Models. Growth Models. Non-Tested Hypothesis Testing and Simulation-Based Inference.

The cost includes course materials, all lunch and refreshments and the use of computers. The number of delegates is restricted. Please register early to guarantee your place. Further instructions will be sent with the joining instructions. If you need assistance in locating hotel accommodation in the area, request the help of our Training Department.

---

Request Enrolment Form Now

Top

---

Request Enrolment Form Now

Top

---

Terms and Conditions