Template-Type: ReDIF-Paper 1.0
Series: Tinbergen Institute Discussion Papers
Creation-Date: 2021-09-16 
Revision-Date: 2023-03-29
Number: 21-083/IV
Author-Name: Bram van Os
Author-Workplace-Name: Erasmus University Rotterdam
Author-Name: Dick van Dijk
Author-Workplace-Name: Erasmus University Rotterdam
Title: Dynamic Conditional Correlations with Partial Information Pooling
Abstract: We propose a novel Dynamic Conditional Correlation model with Conditional
Linear Information Pooling (CLIP-DCC) which endogenously determines an optimal degree of commonality in the correlation innovations. Effectively, this allows a
part of the update of each individual correlation to parsimoniously depend on the
information contained in all asset return pairs. In contrast to existing approaches,
such as the Dynamic EquiCOrrelation (DECO) model, the CLIP-DCC model does
not restrict long-run behavior, thereby naturally complementing target correlation
matrix shrinkage approaches. Empirical findings suggest substantial benefits for a
minimum-variance investor in real-time. Combining the CLIP-DCC model with target shrinkage yields additive improvements, confirming that they address distinct
parts of uncertainty of the conditional correlation matrix.

Classification-JEL: C53, C58, C32
Keywords: Dynamic Equicorrelation, High-dimensional covariance matrices, Covariance shrinkage, Minimum-variance portfolio.

File-URL: https://papers.tinbergen.nl/21083.pdf
File-Format: application/pdf
File-Size: 1.029.570 bytes
Handle: RePEc:tin:wpaper:20210083