Bond/Equity Panel Data with 341 Predictors
341 Factors with Alternative Data from “Factor Investing with Delays”: Time-series of value-weighted factors formed with excess bond returns using the OSBAP database and error corrected TRACE data. Factors are very closely aligned regardless of data source. Code available on GitHub includes a script to evaluate the similarity of the 341 factors across the 3 databases.
October 2024 Release: Contains a full panel of corporate bond and stock-based predictors spanning the vast majority of those used in the literature and used in the paper, “Factor Investing with Delays” by Dickerson, Nozawa and Robotti (2024). All predictors are cross-sectionally ranked and then re-scaled into the -1 to 1 interval. All data is sampled at the end of the month t. Included in the panel data are the various machine learning predictions from the paper. The bond-related predictors are all formed with the BAML/ICE data. Many of the equity predictors are from Open Source Asset Pricing and the Global Factor Data repositories respectively. Merge this predictor data to the OSBAP Bond Data or the WRDS Bond Returns data and create your own strategies with PyBondLab. If you use the data, please cite our paper:
@article{Dickerson-Nozawa-Robotti-2024,
title={Factor Investing with Delays},
author = {Alexander Dickerson and Yoshio Nozawa and Cesare Robotti},
journal={Working Paper},
pages={},
year={2024},
publisher={}}
Factors Formed from the 341 Predictors
October 2024 Release: Equal and value-weighted time-series of the out-of-sample corporate bond factor returns. Factors computed with bond returns in excess of the one-month risk-free rate of return and with duration-adjusted bond returns. The factors are constructed using a decile sort, long in P10 and short in P1, and are sign-corrected such that the factor premium is positive. These factors are denoted with an asterisk (*).