Probabilistic Targeted Factor Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Herculano, Miguel C., Montoya-Blandón, Santiago
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917191020969984
author Herculano, Miguel C.
Montoya-Blandón, Santiago
author_facet Herculano, Miguel C.
Montoya-Blandón, Santiago
contents We develop Probabilistic Targeted Factor Analysis (PTFA), a likelihood-based framework for constructing latent factors that are explicitly targeted to variables of economic interest. PTFA provides a probabilistic foundation for Partial Least Squares, allowing supervised factor extraction under uncertainty. The model is estimated via a fast expectation maximization algorithm and naturally accommodates missing data, mixed-frequency observations, stochastic volatility, and factor dynamics. Simulation evidence shows that PTFA improves recovery of economically relevant latent factors relative to standard PLS, particularly in noisy environments. Applications to financial conditions indices, macroeconomic forecasting, and equity premium prediction illustrate the measurement and forecasting gains delivered by targeted probabilistic factor extraction.
format Preprint
id arxiv_https___arxiv_org_abs_2412_06688
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Probabilistic Targeted Factor Analysis
Herculano, Miguel C.
Montoya-Blandón, Santiago
Econometrics
We develop Probabilistic Targeted Factor Analysis (PTFA), a likelihood-based framework for constructing latent factors that are explicitly targeted to variables of economic interest. PTFA provides a probabilistic foundation for Partial Least Squares, allowing supervised factor extraction under uncertainty. The model is estimated via a fast expectation maximization algorithm and naturally accommodates missing data, mixed-frequency observations, stochastic volatility, and factor dynamics. Simulation evidence shows that PTFA improves recovery of economically relevant latent factors relative to standard PLS, particularly in noisy environments. Applications to financial conditions indices, macroeconomic forecasting, and equity premium prediction illustrate the measurement and forecasting gains delivered by targeted probabilistic factor extraction.
title Probabilistic Targeted Factor Analysis
topic Econometrics
url https://arxiv.org/abs/2412.06688