White noise is a random process whose "components each have a probability distribution with zero mean and finite variance, and are statistically independent".

White noise is a random process whose "components each have a probability distribution with zero mean and finite variance, and are statistically independent" (Wikipedia). When white noise is distributed like a normal distribution it is called Gaussian white noise.

In statistics and econometrics one often assumes that an observed series of data values is the sum of a series of values generated by a deterministic linear process, depending on certain independent (explanatory) variables, and on a series of random noise values. Statistical model validity of standard time series models often depends on the assumption, and it is routinely assessed (via Ljung-Box, Breusch-Godfrey, ARCH-LM and other tests) in model evaluation.