CODEWITHSUNDEEP
pythonscipystandard-error
Eliav S.T.
Eliav S.T.

Reputation: 13

Scipy.stats.sem calculate of standard error

Why am I getting different results?

from scipy.stats import sem
import numpy as np
l = [0,2,4,5,6,7]
print(sem(l))
print(np.std(l)/np.sqrt(len(l)))

1.0645812948447542

0.9718253158075502

Upvotes: 1

Views: 6556

Answers (1)

elemakil
elemakil

Reputation: 3811

The scipy.stats.sem function uses a default value of ddof=1 for the number-of-degrees-of-freedom parameter while numpy.std uses ddof=0 by default. This is also highlighted in the docs:

The default value for ddof is different to the default (0) used by other ddof containing routines, such as np.std and np.nanstd.

Consequently you get:

>>> print(sem(l))
1.06458129484
>>> print(sem(l, ddof=0))
0.971825315808
>>> print(sem(l, ddof=1))
1.06458129484

>>> print(np.std(l)/np.sqrt(len(l)))
0.971825315808
>>> print(np.std(l, ddof=0)/np.sqrt(len(l)))
0.971825315808
>>> print(np.std(l, ddof=1)/np.sqrt(len(l)))
1.06458129484

Upvotes: 4

Related Questions