Routes factor evaluation tasks to cross-sectional or time-series workflows.
npx skills add https://github.com/xingwudao/open-xquant --skill evaluate-factor
Please help me install this Agent Skill. Skill: evaluate-factor Source: https://github.com/xingwudao/open-xquant/tree/main/agent/skills/evaluate-factor Command: npx skills add https://github.com/xingwudao/open-xquant --skill evaluate-factor
This Skill eliminates the risk of selecting the wrong factor evaluation workflow for quantitative research, which leads to invalid or misleading conclusions about whether a factor predicts asset returns.
Use the evaluate-factor skill to test whether the 3-month momentum factor predicts 1-month forward returns for the top 50 US large-cap stocks.
High-intent search queries and answers about installing and using this skill.
To evaluate factor performance correctly, route the quantitative factor evaluation task to the appropriate cross-sectional or time-series workflow based on your symbol universe size and research goal.
Cross-sectional factor evaluation calculates metrics like IC and ICIR for large symbol universes to test stock selection, whereas time-series evaluation measures directional timing metrics like hit rate and decay curves for small rotation sets.
To calculate IC and ICIR for a large universe of stocks, use the cross-sectional factor evaluation workflow, which enforces forward-return alignment and discloses sample size and turnover to ensure valid performance analysis.
Yes, you can test multiple return horizons when evaluating factor performance, as the factor evaluation workflow enforces multi-horizon testing alongside forward-return alignment to prevent biased or misleading conclusions.
Factor evaluation works for small rotation sets by routing the task to the time-series workflow, which calculates directional timing metrics such as hit rate and decay curves instead of cross-sectional IC.
Factor performance analysis produces biased results if it lacks forward-return alignment, multi-horizon testing, or transparency around sample size and turnover, which the evaluation workflow enforces to prevent invalid conclusions.
xjtulycEstimate Fama-French factor models with OLS regression and GRS tests.
wudyeCompute IC/IR statistics and quantile backtests for cross-sectional factor research.
brainbytes-devConstruct market-neutral statistical arbitrage portfolios using PCA-based return decomposition.
GGwujunApply quantitative statistical tests to financial time-series data.
