Partially Linear Quantile Regression Model with Time-Varying Loadings

Atak, A. (2018). Partially Linear Quantile Regression Model with Time-Varying Loadings. .

[img]
Preview
Text - Draft Version
Download (527kB) | Preview

Abstract

In this paper, we develop a partially linear varying coe¢ cient quantile regression (QR) model with factor-augmented predictors and time-varying loadings. We propose a two-stage procedure. In the Örst step, we estimate factors from the mean regression model using a local version of the principal component method and we construct an average quantile regression. In the second step, we obtain partially linear varying coe¢ cient quantile regression using the estimated factors derived in the Örst step. The proposed method extracts and combines distributional information for time- varying factors across di§erent probability masses. Uniform consistency and weak convergence of the estimated quantile factor loading processes are established under general assumptions. Results of Monte Carlo simulations demonstrate that the proposed criterion performs well in a wide range of situations. We evaluate the volatility-return relationship in real time applications by observing the behaviour of loadings in lower, mid and upper quantiles. We Önd strong evidence of heterogeneity in dynamic responses.

Item Type: Monograph (Working Paper)
Additional Information: Factor model, Quantile regression, Time-varying factor loadings, Partially Linear Coefficient models
Divisions: School of Social Sciences > Department of Economics
URI: http://openaccess.city.ac.uk/id/eprint/19064

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics