Topics in Nonparametric Econometrics

Instructor:
Dr. Zongwu CAI   
Professor of Statistics & Economics
University of North Carolina at Charlotte, USA and Adjunct Professor, WISE, Xiamen University

Time:
11 May – 3 June, 2007

Office Hours:
2:00pm-4:30pm
20, 27 May & 3 June

Location:
D109 & D110, Economics Building (Lectures)
D210, Economics Building (Tutorials)
Note: Please refer to the lecture timetable posted for intensive course for details.

Location:
D109 & D110, Economics Building (Lectures)
D210, Economics Building (Tutorials)
Note: Please refer to the lecture timetable posted for intensive course for details.

Course Description:

This is the advanced level of econometrics with ideas, theory and applications. Here, our focuses are on both the rigorous THEORY and SKILLS of analyzing real data using nonparametric methods and statistical software R. This is along the line with our WISE’s spirit “STRONG THEORETICAL FOUNDATION and SKILL EXCELLENCE”.

Nonparametric econometrics is referred to statistical techniques that do not require a researcher to specify a functional form for an object being estimated. Rather than assuming that the functional form of an object is known up to a few unknown parameters, we shall substitute less restrictive assumptions such as existence and smoothness for the assumption that the parametric form of, say, a density function is known and equal to, say, the univariate normal distribution. Of course, if there is some prior knowledge about the functional form of the object of interest up to a few unknown parameters (say, mean and variance), then it would be better to use parametric techniques. However, in practice these forms are rarely if ever known, and the unforgiving consequences of parametric misspecification are well known and are not repeated here.

Lectures will provide details on ideas, methodologies, theory and applications. In particular, the theoretical results will be derived in a rigorous way and the computer code for applications will be provided as well as all results will derived under both iid setting and time series contexts. Applications include using nonparametric methods to recover the drift and diffusion functions in Black-Scholes model, to forecast the inflation rate, interest rate and exchange rates, to estimate the frontier production function, and to test if a jump diffusion model is appropriate for a specific financial asset, and so on so forth. There is no a single book serviced as a textbook for this course so that materials will be provided.

Attachment:

nonparametric_syllabus.pdf

codes.rar    data.rar    nonparametric-notes.pdf

PROJECT #1 for Nonparametric Econometrics.pdf

PROJECT #2 for Nonparametric Econometrics.pdf