Bayesian Updating
The disciplined way to revise your probability estimate when new evidence arrives - prior plus evidence equals posterior.
Browse the glossary →Bayesian updating is the mathematics of changing your mind well. You start with a prior, your probability estimate before the new evidence. When evidence arrives, you weigh how likely that evidence would be if your hypothesis were true versus if it were false, and you revise your estimate into a posterior. Strong, surprising evidence moves the estimate a lot; weak or expected evidence moves it a little. The rule keeps belief revision consistent instead of driven by whichever fact was seen most recently.
The framework guards against two common errors. It stops you from ignoring a strong prior in the face of a single dramatic-but-weak piece of evidence, and it stops you from clinging to a prior when the evidence genuinely should move you. It also makes explicit that the same piece of evidence can support very different conclusions depending on what you believed beforehand, which is why two reasonable people can update from the same document to different places.
In litigation this is exactly what discovery does: each document, admission, and deposition is evidence that should revise the odds attached to a contested fact. Juricratic uses this logic so that as new information enters the model, the probabilities move in a principled way rather than by intuition alone, and every update is traceable to the evidence that caused it. That traceability is what separates a disciplined revision from a gut reaction dressed up as analysis.
P(hypothesis | evidence) = P(evidence | hypothesis) x P(hypothesis) / P(evidence)
How it actually shows up
Practically, Bayesian thinking tells you how much a new piece of evidence should actually change your assessment, which prevents both overreaction to a single hot document and underreaction to a slow accumulation of proof. It also frames the value of discovery: the most valuable evidence to seek is the evidence most likely to move your posterior, which ties directly to sensitivity and information-gain thinking about where to spend effort.
- What is Bayesian updating?
- It is the disciplined method for revising a probability estimate when new evidence arrives. You begin with a prior belief, weigh how likely the evidence is under competing hypotheses, and revise into a posterior belief. Strong, surprising evidence moves the estimate substantially; weak or expected evidence moves it little, keeping belief revision consistent.
- How does Bayesian updating apply to litigation?
- Discovery is a stream of evidence, and each document, admission, or deposition should shift the odds on a contested fact. Bayesian updating tells you how far to shift, based on how diagnostic the evidence is. It prevents overreacting to a single dramatic document and underreacting to a gradual accumulation of proof, and it keeps each revision traceable.
- What is a prior and a posterior?
- A prior is your probability estimate before seeing new evidence; a posterior is your revised estimate after incorporating it. The evidence's diagnostic strength, how differently it would appear under competing hypotheses, determines how far the prior moves. The same evidence can yield different posteriors for people who started with different priors, which is why priors must be stated.
This page is an educational explainer, not legal advice, and creates no attorney–client relationship. Juricratic is a simulation engine: every probability-like figure is a dial you set, not a calibrated prediction. Verify every rule, deadline, and figure against the authorities and orders that govern your matter.
Turn the concept into a modeled matter.
Juricratic makes every one of these ideas a live dial: model your case as a solvable game, then watch the optimal line and the settlement window move as the assumptions do.
Request access →