Quantile Factor Models
Quantile Factor Models (QFM) represent a new class of factor models for high-dimensional panel data. Unlike Approximate Factor Models (AFM), where only location-shifting factors can be extracted, QFM also allow to recover unobserved factors shifting other relevant parts of the distributions of observed variables. A quantile regression approach, labeled Quantile Factor Analysis (QFA), is proposed to consistently estimate all the quantile-dependent factors and loadings. Their asymptotic distribution is then derived using a kernel-smoothed version of the QFA estimators. Two consistent model selection criteria, based on information criteria and rank minimization, are developed to determine the number of factors at each quantile. Moreover, in contrast to the conditions required for the use of Principal Components Analysis in AFM, QFA estimation remains valid even when the idiosyncratic errors have heavy-tailed distributions. Three empirical applications (regarding macroeconomic, climate and finance panel data) provide evidence that extra factors shifting the quantiles other than the means could be relevant in practice.
Code (0)
등록된 구현이 없습니다.
Tasks
Model Selectionquantile regressionvalidSimilar Papers 제목 키워드 기반
Robust Quantile Factor Analysis
We propose a factor model and an estimator of the factors and loadings that are robust to weak factors. The factors can have an arbitrarily weak influence on the mean or quantile of the outcome variable at most quantile …
Common Idiosyncratic Quantile Risk
We identify a new type of risk that is characterised by commonalities in the quantiles of the cross-sectional distribution of asset returns. Our newly proposed quantile risk factors are associated with a quantile-specifi…
Composite Quantile Factor Model
This paper introduces the method of composite quantile factor model for factor analysis in high-dimensional panel data. We propose to estimate the factors and factor loadings across multiple quantiles of the data, allowi…
modelInvestigating Growth at Risk Using a Multi-country Non-parametric Quantile Factor Model
We develop a Bayesian non-parametric quantile panel regression model. Within each quantile, the response function is a convex combination of a linear model and a non-linear function, which we approximate using Bayesian A…
regressionEstimation of Characteristics-based Quantile Factor Models
This paper studies the estimation of characteristic-based quantile factor models where the factor loadings are unknown functions of observed individual characteristics while the idiosyncratic error terms are subject to c…