scipy.stats.

mvsdist#

scipy.stats.mvsdist(data)[source]#

‘Frozen’ distributions for mean, variance, and standard deviation of data.

Parameters:

dataarray_like: Input array. Converted to 1-D using ravel. Requires 2 or more data-points.

Returns:

mdist“frozen” distribution object: Distribution object representing the mean of the data.
vdist“frozen” distribution object: Distribution object representing the variance of the data.
sdist“frozen” distribution object: Distribution object representing the standard deviation of the data.

See also

bayes_mvs

Notes

The return values from bayes_mvs(data) is equivalent to tuple((x.mean(), x.interval(0.90)) for x in mvsdist(data)).

In other words, calling <dist>.mean() and <dist>.interval(0.90) on the three distribution objects returned from this function will give the same results that are returned from bayes_mvs.

Array API Standard Support

mvsdist has experimental support for Python Array API Standard compatible backends in addition to NumPy. Please consider testing these features by setting an environment variable SCIPY_ARRAY_API=1 and providing CuPy, PyTorch, JAX, or Dask arrays as array arguments. The following combinations of backend and device (or other capability) are supported.

Library	CPU	GPU
NumPy	✅	n/a
CuPy	n/a	⛔
PyTorch	⛔	⛔
JAX	⛔	⛔
Dask	⛔	n/a

See Support for the array API standard for more information.

References

T.E. Oliphant, “A Bayesian perspective on estimating mean, variance, and standard-deviation from data”, https://scholarsarchive.byu.edu/facpub/278, 2006.

Examples

>>> from scipy import stats
>>> data = [6, 9, 12, 7, 8, 8, 13]
>>> mean, var, std = stats.mvsdist(data)

We now have frozen distribution objects “mean”, “var” and “std” that we can examine:

>>> mean.mean()
9.0
>>> mean.interval(0.95)
(6.6120585482655692, 11.387941451734431)
>>> mean.std()
1.1952286093343936