In standard statistical practice, a correction factor of 0 provides a
maximum likelihood estimate of the variance for normally distributed
variables, while a correction factor of 1 provides an unbiased
estimator of the variance of a hypothetical infinite population.
The correction factor will be subtracted from the number of elements
added (sample points) when working out the divisor.
For more information about correction factors that could be set please
see http://en.wikipedia.org/wiki/Standard_deviation#Estimation
Computes the variance, a measure of the spread of a distribution to quantify how far a set of data values is spread out.
Note that the Welford's algorithm implementation is used to compute the spread of a distribution incrementally when a value is added through addToAverage(). http://en.wikipedia.org/wiki/Algorithms_for_calculating_variance
#Online_algorithm
In standard statistical practice, a correction factor of 0 provides a maximum likelihood estimate of the variance for normally distributed variables, while a correction factor of 1 provides an unbiased estimator of the variance of a hypothetical infinite population. The correction factor will be subtracted from the number of elements added (sample points) when working out the divisor. For more information about correction factors that could be set please see http://en.wikipedia.org/wiki/Standard_deviation#Estimation