Nonlinear cointegration services for serious practitioners
- Peer-reviewed methods
- Honest validation
- Transparent team
- Academic rigor
How we work with practitioners
Three pathways from theoretical understanding to practical application, each grounded in rigorous methodology and intellectual honesty.
Advanced nonlinear methods
Robust estimation audit
A standalone service for risk-conscious practitioners who suspect their current models are fragile. We stress-test your hedge ratios against heavy-tailed innovations, run structural break diagnostics, and deliver a written assessment of where your assumptions are likely to fail and what robust alternatives exist. This is not a sales pitch disguised as analysis. If your models are sound, we will say so.
Platform and research access
-
Backtesting engine
A modular framework enforcing strict separation between in-sample development and out-of-sample evaluation. Every test is logged, every parameter choice documented, and every failure archived for future reference.
-
Nonlinear model library
A curated collection of threshold autoregressive, Markov-switching, and neural cointegration specifications. Each model includes full documentation of assumptions, estimation procedures, and known limitations.
-
Real-time monitoring dashboard
Live diagnostics tracking model health, residual behaviour, and regime detection triggers. Automatic alerts fire when assumptions break, enabling proactive deleveraging before losses accumulate.
-
Community research access
Periodic workshops and discussion forums where practitioners share implementation challenges, debate methodological choices, and scrutinise each other's assumptions. Intellectual combat, not mutual admiration.
-
Robust estimator suite
Production-ready implementations of M-estimators, trimmed regression, and other techniques that maintain validity when ordinary least squares collapses under heavy-tailed innovations or structural breaks.
-
Reproducible research templates
Standardised code templates and documentation formats that ensure every analysis can be replicated, audited, and extended by others. No black boxes, no hidden parameters, no undocumented choices.
From assessment to deployment
A structured journey that respects the difference between learning, testing, and live execution.
Initial capability assessment
We begin with a candid conversation about your current methodology, data infrastructure, and analytical goals. We identify where linear assumptions may be failing and whether nonlinear frameworks are appropriate for your specific market context.
Curriculum or audit selection
Completion and validation
For training participants, this means reproducing core results independently and passing a rigorous validation exercise. For audit clients, it means receiving a written assessment with specific, actionable recommendations and no vague platitudes.
Strategy deployment support
Practitioner perspectives
Verified feedback from quantitative analysts and portfolio managers who engaged with our research.
"Their nonlinear cointegration framework exposed regime dependencies we had completely missed. Our linear pairs trading book looked clean in backtests but bled in volatile periods. The threshold autoregressive approach changed how we model reversion speed."
"I appreciated their intellectual honesty. They showed us models that failed, not just cherry-picked winners. The robust estimation module on M-estimators under heavy tails was immediately applicable to our emerging markets book."
"The out-of-sample validation discipline is what sold me. Most vendors show in-sample Sharpe ratios and call it research. These people separate training and test periods religiously. It slows down strategy release but prevents disasters."
Ready to challenge your assumptions?
Peer-reviewed nonlinear cointegration frameworks with documented assumptions and limitations
Strict out-of-sample validation protocols that prevent overfitting and false discovery
Transparent team that publishes failures alongside successes for genuine learning
Academic rigor applied to practical market problems without marketing hype