Lab
1.3 Central Limit Theorem

Central Limit Theorem

  • Experiment N° 0
  • Link: here

Design

Empirical validation of CLT for different distributions.

section-I


import numpy as np
import matplotlib.pyplot as plt
import os
os.getcwd()
'C:\\Users\\juani\\Documents\\3_My_Jupiter_Notebooks\\4_Series_de_Tiempo\\0_2024\\exps_&_reps'
import warnings
warnings.simplefilter(action='ignore', category= FutureWarning)

# general settings
class CFG:
    data_folder = '../input/tsdata-1/'
    img_dim1 = 20
    img_dim2 = 10
    style = 'fivethirtyeight'



# adjust the parameters for displayed figures    
plt.rcParams.update({'figure.figsize': (CFG.img_dim1,CFG.img_dim2)})    

plt.style.use(CFG.style)
import warnings
warnings.simplefilter(action='ignore', category= FutureWarning)

# general settings
class CFG:
    data_folder = '../input/tsdata-1/'
    img_dim1 = 20
    img_dim2 = 10
    style = 'fivethirtyeight'



# adjust the parameters for displayed figures    
plt.rcParams.update({'figure.figsize': (CFG.img_dim1,CFG.img_dim2)})    

plt.style.use(CFG.style)

section-II


Normal Distribution

np.random.seed(42)
population_size = 10000

mu, sigma = 0, 100 # mean and standard deviation
height_population =  np.random.normal(mu,sigma,population_size)
sample_size, no_of_samples = 10 , 10000


sample_means = []


for i in range(no_of_samples):
    sample = np.random.choice(height_population, sample_size)
    sample_mean = np.mean(sample)
    sample_means.append(sample_mean)

plt.hist(height_population, bins = 100, density = True, alpha= 0.8, label = 'Population')
plt.xlabel('Height') , plt.ylabel('Frequency')
plt.title('Population and Sample Means Distribution')

plt.hist(sample_means, bins = 100, density = True, alpha= 0.8, label = 'Sample Means')
plt.legend, plt.show()

png

(<function matplotlib.pyplot.legend(*args, **kwargs)>, None)

Uniform Distribution

np.random.seed(42)
population_size = 10000


mini = -100
maxi = 100

height_population =  np.random.uniform(mini,maxi,population_size)
sample_size, no_of_samples = 10 , 10000


sample_means = []


for i in range(no_of_samples):
    sample = np.random.choice(height_population, sample_size)
    sample_mean = np.mean(sample)
    sample_means.append(sample_mean)

plt.hist(height_population, bins = 100, density = True, alpha= 0.8, label = 'Population')
plt.xlabel('Height') , plt.ylabel('Frequency')
plt.title('Population and Sample Means Distribution')

plt.hist(sample_means, bins = 100, density = True, alpha= 0.8, label = 'Sample Means')
plt.legend, plt.show()

png

(<function matplotlib.pyplot.legend(*args, **kwargs)>, None)

Beta 1 Distribution

np.random.seed(42)
mini = 8
maxi = 2
population_size = 10000
height_population =  np.random.beta(mini,maxi,population_size)
sample_size, no_of_samples = 10 , 10000


sample_means = []


for i in range(no_of_samples):
    sample = np.random.choice(height_population, sample_size)
    sample_mean = np.mean(sample)
    sample_means.append(sample_mean)

plt.hist(height_population, bins = 100, density = True, alpha= 0.8, label = 'Population')
plt.xlabel('Height') , plt.ylabel('Frequency')
plt.title('Population and Sample Means Distribution')

plt.hist(sample_means, bins = 100, density = True, alpha= 0.8, label = 'Sample Means')
plt.legend, plt.show()

png

(<function matplotlib.pyplot.legend(*args, **kwargs)>, None)

Beta 2 Distribution

np.random.seed(42)
mini = 2
maxi = 8
population_size = 10000
height_population =  np.random.beta(mini,maxi,population_size)
sample_size, no_of_samples = 10 , 10000


sample_means = []


for i in range(no_of_samples):
    sample = np.random.choice(height_population, sample_size)
    sample_mean = np.mean(sample)
    sample_means.append(sample_mean)

plt.hist(height_population, bins = 100, density = True, alpha= 0.8, label = 'Population')
plt.xlabel('Height') , plt.ylabel('Frequency')
plt.title('Population and Sample Means Distribution')

plt.hist(sample_means, bins = 100, density = True, alpha= 0.8, label = 'Sample Means')
plt.legend, plt.show()

png

(<function matplotlib.pyplot.legend(*args, **kwargs)>, None)

Beta 3 Distribution

np.random.seed(42)
mini = 0.5
maxi = 0.5
population_size = 10000
height_population =  np.random.beta(mini,maxi,population_size)
sample_size, no_of_samples = 10 , 10000


sample_means = []


for i in range(no_of_samples):
    sample = np.random.choice(height_population, sample_size)
    sample_mean = np.mean(sample)
    sample_means.append(sample_mean)

plt.hist(height_population, bins = 100, density = True, alpha= 0.8, label = 'Population')
plt.xlabel('Height') , plt.ylabel('Frequency')
plt.title('Population and Sample Means Distribution')

plt.hist(sample_means, bins = 100, density = True, alpha= 0.8, label = 'Sample Means')
plt.legend, plt.show()

png

(<function matplotlib.pyplot.legend(*args, **kwargs)>, None)

section-III


section-IV


Credits to Snehil Raj Choubey.