In Bayesian statistics, which type of prior belief constrains the parameter by narrowing the plausible values, ranging from weakly informative to strongly informative?

• A. Uninformative prior
• B. Weakly informative prior
• C. Informative prior distribution
• D. Conjugate prior

Answer: (C)

In Bayesian thinking, priors express what we believe about a parameter before seeing data. When a prior constrains the parameter by narrowing the plausible values, it carries prior knowledge and concentrates probability in a believable region. This is the informative prior distribution, which can be weakly informative (lightly constraining) or strongly informative (tight constraints). The stronger the constraint, the more the prior influences the posterior. An uninformative prior aims to exert little influence and spread mass more diffusely, while a conjugate prior is about mathematical form, not necessarily how much it constrains plausible values. The broad idea described—moving from weakly to strongly constraining beliefs—fits the informative prior distribution.