Repository for R and Python packages and reproduction codes in Weighted Conformalized Selection paper

This repository contains a collection of functions to evaluate investment strategies regarding multiple testing concerns.

Sequential Hypothesis Testing with e-Values and p-Values

Open and reproducible empirical research on cryptocurrency cross-sectional factors, asset-pricing evidence, and robust validation.

Torch-free honest-statistics kernel (Deflated Sharpe, PBO, Diebold-Mariano, HAC, purged walk-forward) — the single source of truth behind a 19-project ML+Finance portfolio

A validation framework that makes it hard for a trading backtest to lie to you: pre-registration, session-clustered statistics, Westfall-Young maxT multiplicity, drift attribution, lookahead detection.

Pre-registered falsification of the commodity carry premium (XS + TS) on 18 CME futures, 2010–2026 — design frozen before data; 0/2 arms promoted; four exchange-data identity traps documented along the way.

LLM agent for p-hacking & selective-reporting risk screening in academic PDFs.

Gate a backtested trading edge before you trust it: multiple-testing, cost-floor, and autocorrelation checks in pure-stdlib Python.

Risk-bounded pairs cointegration stat-arb with multiple-testing correction (Bonferroni + BH-FDR), no vectorised look-ahead, realistic cost model.

Multiple-testing / Deflated Sharpe analysis on 160 BTC rules (DSR = 0.70, fail).

Volatility regime detection with bump-hunt statistical honesty — local vs global significance, trial factors, bootstrap null ladder

ML on high-dimensional gene-expression data: PCA and clustering, cross-validated classification, and from-scratch Benjamini-Hochberg FDR differential expression, on the public Golub leukemia set.