Conditional Probability

Concept

Theoretically, Conditional Probability is the probability that an event occurs given that another event has already occurred. It provides a formal framework for updating probabilities when additional information becomes available and is fundamental to probability theory, Bayesian inference and stochastic modelling. In health economics, conditional probability is used to represent dependent clinical events, sequential treatment pathways and state transitions that depend on prior outcomes or patient history.

Mathematically, Conditional Probability is defined as the probability of the intersection of two events divided by the probability of the conditioning event, provided the conditioning event has non-zero probability. This definition forms the basis for Bayesian updating, Markov models, decision trees and other probabilistic models in which future events depend on preceding events.

In practice, Conditional Probability is estimated from clinical trials, observational studies, epidemiological data or disease registries. It is implemented throughout health economic models to estimate transition probabilities, treatment response, adverse events, diagnostic accuracy and disease progression. Conditional probabilities are routinely incorporated into decision trees, Markov models, microsimulation and Bayesian evidence synthesis.

---

Purpose

Used to estimate the probability of an event given that another event has occurred, enabling dependent clinical events and sequential decision processes to be represented within health economic models.

---

Mathematical Formulae

Primary Formula

P(A ? B) = P(A � B) / P(B)

where:

• P(A ? B) is the probability of event A given event B
• P(A � B) is the joint probability of events A and B
• P(B) is the probability of event B, where P(B) > 0.

Supporting Formulae

Joint probability:

P(A � B) = P(A ? B) ? P(B)

Bayes' theorem:

P(A ? B) = P(B ? A)P(A) / P(B)

Related Mathematical Methods

• Probability theory
• Bayesian inference
• Decision tree analysis
• Markov modelling
• Microsimulation
• Monte Carlo simulation
• Diagnostic test evaluation

---

Example

A diagnostic test is evaluated in a population where 20% of patients have the disease.

The probability of a positive test among patients with the disease is:

P(Positive ? Disease) = 0.90

The probability that a patient both has the disease and tests positive is:

P(Positive � Disease) = 0.90 ? 0.20 = 0.18

This conditional probability is subsequently used to estimate expected treatment costs and health outcomes within a diagnostic decision model.

---

Excel Implementation

Function	Example Formula	Health Economics Application
PRODUCT	=B2*C2	Calculate joint probabilities from conditional and marginal probabilities.
IF	=IF(C2>0,B2/C2,"""")	Calculate conditional probability while avoiding division by zero.
SUMPRODUCT	=SUMPRODUCT(Probabilities,Outcomes)	Calculate expected values using conditional probabilities.
INDEX	=INDEX(TransitionMatrix,CurrentState,NextState)	Retrieve conditional transition probabilities in state-transition models.
XLOOKUP	=XLOOKUP(State,Table[State],Table[ConditionalProbability])	Retrieve conditional probabilities from model inputs.

---

VBA (Optional)

Automate calculation of conditional transition probabilities and update patient pathways dynamically as clinical events occur during simulation.

---

Sources

• Briggs A, Claxton K, Sculpher M. Decision Modelling for Health Economic Evaluation. Oxford University Press; 2006.
• Drummond MF, Sculpher MJ, Claxton K, Stoddart GL, Torrance GW. Methods for the Economic Evaluation of Health Care Programmes. 4th ed. Oxford University Press; 2015.
• Ross SM. Introduction to Probability Models. 12th ed. Academic Press; 2019.
• DeGroot MH, Schervish MJ. Probability and Statistics. 4th ed. Pearson; 2012.
• National Institute for Health and Care Excellence (NICE). Health Technology Evaluation Manual. Latest edition.