scipy.stats.tsem(array, limits=None, inclusive=(True, True))
calculates the trimmed standard error of the mean of array elements along the specified axis of the array.
Its formula :-
Parameters :
array: Input array or object having the elements to calculate the trimmed standard error of the mean.
axis: Axis along which the trimmed standard error of the mean is to be computed. By default axis = 0.
limits: Lower and upper bound of the array to consider, values less than the lower limit or greater than the upper limit will be ignored. If limits is None [default], then all values are used.Returns : Trimmed standard error of the mean of array elements based on the set parameters.
Code #1:
# Trimmed Standard error from scipy import stats
import numpy as np
# array elements ranging from 0 to 19 x = np.arange( 20 )
print ( "Trimmed Standard error :" , stats.tsem(x))
print ( "\nTrimmed Standard error by setting limit : " ,
stats.tsem(x, ( 2 , 10 )))
|
Trimmed Standard error : 1.32287565553 Trimmed Standard error by setting limit : 0.912870929175
Code #2: With multi-dimensional data, axis() working
# Trimmed Standard error from scipy import stats
import numpy as np
arr1 = [[ 1 , 3 , 27 ],
[ 5 , 3 , 18 ],
[ 17 , 16 , 333 ],
[ 3 , 6 , 82 ]]
# using axis = 0 print ( "\nTrimmed Standard error is with default axis = 0 : \n" ,
stats.tsem(arr1, axis = 1 ))
|
Trimmed Standard error is with default axis = 0 : 27.1476974115