Limitations
What MacroRadar's models do not do
Every model has a clear scope and clear failure modes. Stating them plainly is part of the methodology, not a footnote to it. This page is the honest account of where the regime and recession-probability models stop being useful — so you can read their output with the right amount of confidence.
Why this page exists
Macro analysis touches money, and money is where overconfidence does the most damage. A model that hides its limits invites readers to trust it past the point it deserves. MacroRadar takes the opposite approach: the limits are published as prominently as the outputs, with their own page, so nobody has to dig for them.
This complements the methodology (how the models work) and the data sources (where the numbers come from). Together they are the full, honest account of what MacroRadar is.
Scope & failure modes
Six limits matter most. Each is a place where the models are weakest and where a reader should be most careful.
Descriptive, not prescriptive
The regime model tells you the current macroeconomic state. It does not tell you what to do about it. Historical asset-class returns shown by regime are base rates — what has happened in similar regimes before — not a statement about what will happen this time.
Blind to exogenous shocks
Neither model anticipates events whose cause sits outside the economic-data universe. The 2020 pandemic is the clearest example: no macro indicator anticipated it, so the models identified the contraction coincident with its impact on the data, not ahead of it. The same holds for wars, oil shocks, and policy surprises.
Vulnerable to structural change
The models assume that relationships between indicators that held in the past continue to hold. That is a strong assumption. We treat genuinely unprecedented readings as low-confidence rather than absorbing them as a new normal, but we cannot fully control for structural change in the economy.
Trained on rare events
There have been only a handful of recessions in the historical sample. Any model trained on so few events carries wide uncertainty around its estimates, and any out-of-sample test involves at most one or two new events. The track record is directionally informative, not precise.
US-only
All inputs are US economic data, so the regime and recession-probability outputs describe the US economy. Assets with significant non-US exposure are partly driven by factors the models do not see. Broader geographic coverage is on the roadmap, not in production today.
No single-indicator certainty
No individual indicator drives a classification on its own, and none of them is infallible. A yield-curve inversion, a Sahm-rule trigger, or a credit-spread widening shifts the probability — it does not settle it. The output is a weighing of evidence, not a switch.
Not investment advice
Nothing on MacroRadar is personalised investment advice, a recommendation to buy, sell, or hold any security, or a forecast of future market or economic events. The models are educational and analytical tools. Past model performance does not guarantee future performance, and historical returns by regime do not guarantee future returns.
You are responsible for your own investment decisions. The cited data sources are public and authoritative, but MacroRadar makes no warranties as to their accuracy, completeness, or timeliness beyond republishing our derived analysis as computed.
Errors & corrections
Models and pipelines have bugs, and source data gets revised. When we find a material error in a published output, we fix it at the source and let the daily refresh carry the correction through, rather than quietly overwriting history. The point-in-time record on the recession-probability page reflects what the model would have said in real time, including its misses.
If you spot something that looks wrong, tell us — accuracy on a finance domain is a shared interest, and a flagged error is a better outcome than a confident one.