Breaking the Curse of Dimensionality

Duke Economics Working Paper No. 00-13

30 Pages Posted: 22 Nov 2000

See all articles by Mark Coppejans

Mark Coppejans

BlackRock, Inc; Barclays Global Investors

Abstract

This paper proposes a new nonparametric estimator for general regression functions with multiple regressors. The method used here is motivated by a remarkable result derived by Kolmogorov (1957) and later tightened by Lorentz (1966).

In short, they show that any continuous function of multiple variables can be written as univariate functions. As it stands, this representation is difficult to estimate because of its lack of smoothness. Hence we propose to use a generalization of their representation that allows for the univariate functions to be differentiable. The model will be estimated using B-splines, which have excellent numerical properties. A crucial restriction in this representation is that some of the functions must be increasing.

One of the main contributions of this paper is that we develop a method for imposing monotonicity on the cubic B-splines, a priori, such that the estimator is dense in the set of all monotonic cubic B-splines. A simulation experiment shows that the estimator works well when optimization is performed by using the back-fitting algorithm. The monotonic restriction has many other applications besides the one presented here, such as estimating a demand function. With only r + 2 more constraints, it is also possible to impose concavity.

Key Words: Curse of Dimensionality, Nonparametric Regression, B-splines, Monotonicity Constraints

JEL Classification: C15

Suggested Citation

Coppejans, Mark T., Breaking the Curse of Dimensionality. Duke Economics Working Paper No. 00-13, Available at SSRN: https://ssrn.com/abstract=236812 or http://dx.doi.org/10.2139/ssrn.236812

Mark T. Coppejans (Contact Author)

BlackRock, Inc ( email )

San Francisco, CA
United States

Barclays Global Investors ( email )

45 Fremont Street
San Francisco, CA 94105
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
147
Abstract Views
1,052
rank
237,436
PlumX Metrics