Market Segmentation and Non-Parametric Asset Pricing

Chaudhry, Aditya, McIntire School of Commerce, University of Virginia
Gallmeyer, Michael, McIntire School of Commerce, University of Virginia

I examine market segmentation between equity and bond markets. Although under the no arbitrage principle equity and bond markets should prove integrated, real-world frictions may induce some degree of market segmentation. To assess the extent of this segmentation, I use non-parametric estimators of the stochastic discount factor (SDF). I make four contributions in this work. First, the non-parametric methods I use surmount several econometric limitations of previous such investigations. Second, I propose a novel machine learning-based SDF estimator. Third, I examine time variation in the extent of segmentation between equity and bond markets, which previous work has not empirically tested. Fourth, I use dual-asset-class SDF estimates to examine cross-asset-class trading signals, which have immediate practical applications. I find evidence of integration between equity and bond markets in the full sample. However, cross-asset-class information proves difficult to exploit out of sample in cross-sectional pricing and trading applications.

BSC (Bachelor of Science in Commerce)
Asset Pricing, Finance, Stochastic Discount Factor, Machine Learning, Deep Learning

Global Commerce Scholar

Issued Date: