Asset Pricing with Panel Tree under Global Split Criteria

60 Pages Posted: 27 Oct 2021 Last revised: 21 Nov 2022

See all articles by Lin William Cong

Lin William Cong

Cornell University - Samuel Curtis Johnson Graduate School of Management; National Bureau of Economic Research (NBER)

Guanhao Feng

City University of Hong Kong (CityU)

Jingyu He

City University of Hong Kong (CityU)

Xin He

Hunan University - College of Finance and Statistics; City University of Hong Kong (CityU)

Date Written: April 15, 2022

Abstract

This paper develops a unified P-Tree framework (“P” for “panel”) for analyzing (unbalanced) panel data with iterative and global (instead of recursive and local) split criteria. From a dimension reduction perspective, P-Tree is grown top-down to split the cross section of individual stock returns to create leaf basis portfolios, thus constructing the stochastic discount factor (SDF). The SDF construction is guided by its global performance, which is the split criteria for the P-Tree growth. P-Tree partitioning of the characteristics space resembles sequen- tial security sorting, solves the high-dimensional sorting challenge, and visualizes nonlinear characteristics interactions. In an asset pricing study of U.S. equities, a data-driven P-Tree reveals that idiosyncratic volatility and earnings-to-price ratio are significant in driving the cross-sectional return variation through their interactive sequential splitting of the cross section. For risk-adjusted investment, P-Tree five-factor models offer an annualized Sharpe ratio close to 3, plus the significant alphas of about 0.80%.

Keywords: Basis Assets, Cross-Sectional Returns, Decision Tree, Firm Characteristics, Latent Factors.

JEL Classification: C1, G11, G12

Suggested Citation

Cong, Lin and Feng, Guanhao and He, Jingyu and He, Xin, Asset Pricing with Panel Tree under Global Split Criteria (April 15, 2022). Available at SSRN: https://ssrn.com/abstract=3949463 or http://dx.doi.org/10.2139/ssrn.3949463

Lin Cong

Cornell University - Samuel Curtis Johnson Graduate School of Management ( email )

Ithaca, NY 14853
United States

HOME PAGE: http://www.linwilliamcong.com/

National Bureau of Economic Research (NBER) ( email )

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

Guanhao Feng (Contact Author)

City University of Hong Kong (CityU) ( email )

83 Tat Chee Avenue
Kowloon Tong
Hong Kong

Jingyu He

City University of Hong Kong (CityU) ( email )

83 Tat Chee Avenue
Hong Kong
Hong Kong

Xin He

Hunan University - College of Finance and Statistics ( email )

109th Shijiachong Road, Yuelu District
Changsha, Hunan 410006
China

HOME PAGE: http://www.xinhesean.com

City University of Hong Kong (CityU) ( email )

83 Tat Chee Avenue
Kowloon
Hong Kong

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

Paper statistics

Downloads
719
Abstract Views
2,643
rank
53,132
PlumX Metrics