sciPy stats.bayes_mvs() function | Python

0 0 1 minute read

scipy.stats.bayes_mvs(arr, alpha) function computes mean, variance and standard deviation in the given Bayesian confidence interval.

Parameters :
arr : [array_like] The input data can be multidimensional but will be flattened before use.
alpha : Probability that the returned confidence interval contains the true parameter.

Results : mean, variance and standard deviation in the given Bayesian confidence interval.

Code #1: Working

# stats.bayes_mvs() method    
import numpy as np 
from scipy import stats 
    
arr1 = [[20, 2, 7, 1, 34], 
        [50, 12, 12, 34, 4]] 
  
arr2 = [50, 12, 12, 34, 4] 
  
print ("\narr1 : ", arr1) 
print ("\narr2 : ", arr2) 
  
mean, var, std = stats.bayes_mvs(arr1, 0.9) 
  
print ("\nMean of array1 : ", mean) 
print ("\nvar of array1 : ", var) 
print ("\nstd of array1 : ", std) 
  
mean, var, std = stats.bayes_mvs(arr2, 0.5) 
  
print ("\nMean of array2 : ", mean) 
print ("\nvar of array2 : ", var) 
print ("\nstd of array2 : ", std) 
  

Output :

arr1 : [[20, 2, 7, 1, 34], [50, 12, 12, 34, 4]]
arr2 : [50, 12, 12, 34, 4]

Mean of array1 : Mean(statistic=17.6, minmax=(7.99212522273964, 27.207874777260358))

var of array1 : Variance(statistic=353.2, minmax=(146.13176149159307, 743.5537128176551))

std of array1 : Std_dev(statistic=18.136411760663574, minmax=(12.088497073316974, 27.26818132581737))

Mean of array2 : Mean(statistic=22.4, minmax=(16.090582413339323, 28.709417586660674))

var of array2 : Variance(statistic=725.6, minmax=(269.47585801746374, 754.8278687119639))

std of array2 : Std_dev(statistic=23.872262300862655, minmax=(16.415719844632576, 27.474130900029646))