Imputation Via Copula and Transformation Methods, With Applications to Financial and Economic Data

23 Pages Posted: 9 Dec 2010

See all articles by Yangyong Zhang

Yangyong Zhang

Standard & Poor's - Quantitative Analytics

Craig A. Friedman

TIAA-CREF

Jinggang Huang

affiliation not provided to SSRN

Wenbo Cao

Standard & Poor's - Quantitative Analytics

Date Written: December 9, 2010

Abstract

We present new, tractable methods to impute missing values based on conditional probability density functions that we estimate via copula and mixture models. Our methods exploit known analytical results concerning conditional distributions for the Arellano-Valle and Bolfarine’s generalized t-distribution and fast, accurate quadrature methods. We also benchmark our approach on three financial/economic data sets (two of which are publicly available) and show that our methods outperform benchmark approaches on these data.

Keywords: Missing Variable Imputation, Generalized T-Distribution, Arellano-Valle and Bolfarine’s Generalized T−Distribution, Copula, Mixture Models, Quadrature

Suggested Citation

Zhang, Yangyong and Friedman, Craig A. and Huang, Jinggang and Cao, Wenbo, Imputation Via Copula and Transformation Methods, With Applications to Financial and Economic Data (December 9, 2010). Available at SSRN: https://ssrn.com/abstract=1722903 or http://dx.doi.org/10.2139/ssrn.1722903

Yangyong Zhang

Standard & Poor's - Quantitative Analytics ( email )

55 Water Street
New York, NY 10041
United States

Craig A. Friedman (Contact Author)

TIAA-CREF ( email )

730 3rd Ave
New York, NY 10017
United States

Jinggang Huang

affiliation not provided to SSRN ( email )

Wenbo Cao

Standard & Poor's - Quantitative Analytics ( email )

55 Water Street
New York, NY 10041
United States

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
106
Abstract Views
700
rank
290,464
PlumX Metrics