Using VaR and Multiple Factors to Estimate Stock Downside Risk

Summary

This research outline proposes using value at risk (VaR) and stock factors to estimate future downside risk. It examines factors across several dimensions, selects those judged effective, and combines them into a multifactor model intended to quantify potential maximum declines. The stated applications include assessing risk for absolute-return products, collateral in margin financing, stock-pledged lending, and concentrated equity holdings.

The summary reports two illustrations: it says estimated VaR for the CSI 300 and ChiNext indexes fell as the indexes declined, and that an equal-weight portfolio of 20 predicted bear stocks underperformed its benchmark from 2016 onward, with noticeable fluctuations within months. These are reported findings, not a complete validation of the model. The approach simulates future loss distributions from historical market-factor changes, so its estimates may fail out of sample if market conditions change.

Key ideas

• The study combines selected stock factors with VaR to estimate future downside risk.
• It presents the model as a risk measure for products and holdings sensitive to large declines.
• The summary reports falling VaR estimates for the CSI 300 and ChiNext during index declines.
• An equal-weight portfolio of 20 predicted bear stocks reportedly underperformed its benchmark from 2016 onward.
• The estimates rely on historical distributions and may fail when market conditions shift.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.