Multivariate AutoRegressive Smooth Liquidity (MARSLiQ)

We propose MARSLiQ (Multivariate AutoRegressive Smooth Liquidity), a new multivariate model for daily liquidity that combines slowly evolving trends with short-run dynamics to capture both persistent and transitory liquidity movements. In our framework, each asset's liquidity is decomposed into a smooth time-varying trend component and a stationary short-run component, allowing us to separate long-term liquidity levels from short-term fluctuations. The trend for each asset is estimated nonparametrically and further decomposed into a common market trend and idiosyncratic (asset-specific) trends, and seasonal trends, facilitating interpretation of market-wide liquidity shifts versus firm-level effects. We introduce a novel dynamic structure in which an asset's short-run liquidity is driven by its own past liquidity as well as by lagged liquidity of a broad liquidity index (constructed from all assets). This parsimonious specification-combining asset-specific autoregressive feedback with index-based spillovers-makes the model tractable even for high-dimensional systems, while capturing rich liquidity spillover effects across assets. Our model's structure enables a clear analysis of permanent vs. transitory liquidity shocks and their propagation throughout the market. Using the model's Vector MA representation, we perform forecast error variance decompositions to quantify how shocks to one asset's liquidity affect others over time, and we interpret these results through network connectedness measures that map out the web of liquidity interdependence across assets.