Bayesian inference from measurement information

Bayesian inference about a quantity is made through the probability density function that describes the state of incomplete knowledge acquired from measurement. This approach can be applied advantageously to evaluate the data obtained from repeated measurements of a quantity, with or without added information on the variances or error bounds of the indicated values. Results are compared with those obtained using conventional statistical theory. It is concluded that Bayesian inference allows a flexible and natural characterization of the measurement uncertainty.