---Now, the purpose of the next is to verify using a test of hypothesis for normally distributed data, and a confidence level equal to 95%, if it is true that each sample mean has the same value as the population mean or it is different. For this purpose, let's adapt the developments made in Track 08 - section 1.4.

from scipy.stats import norm

muz = 0

sigmaz = 1

p = 0.95

alfa = 1 - p

pr = 1 - alfa/2

z = norm.ppf(pr,muz,sigmaz)

print("Given alpha = ",str(round(alfa,2)),", Zcrit = ",round(z,2))

Given alpha = 0.05 , Zcrit = 1.96 

mi = pop_mean_weight

H0 = "The value is equal to " + str(mi)

n = sample_size

s = pop_std_weight

sx = s/(n**(0.5))

print('Null hypothesis:',H0)

for sample_mean in list_means_samples:

  xb = sample_mean

  zobs = (xb - mi)/sx

  #print('For sample_mean:', sample_mean)

  #print("Zobs = ",zobs,"e Zcrit = ",z)

  if (zobs > z)|(-zobs < -z): # Zobs belongs to the critical region

    print("For sample mean ",sample_mean,"Zobs = ",zobs,"Zcrit = ",z," - Reject H0.")

  else:

    print("For sample mean ",sample_mean,"Zobs = ",zobs,"Zcrit = ",z," - Do not reject H0.")