ols3.py

import numpy as np 
import pandas as pd 
import statsmodels.api as sm 
import statsmodels.formula.api as smf 
from itertools import combinations 
import plotnine as p

# read data
import ssl
ssl._create_default_https_context = ssl._create_unverified_context
def read_data(file): 
	return pd.read_stata("https://github.com/scunning1975/mixtape/raw/master/" + file)

coefs = np.zeros(1000)
for i in range(1000):
    tb = pd.DataFrame({
    'x': 9*np.random.normal(size=10000),
    'u': 36*np.random.normal(size=10000)})
    tb['y'] = 3 + 2*tb['x'].values + tb['u'].values

    reg_tb = sm.OLS.from_formula('y ~ x', data=tb).fit()

    coefs[i] = reg_tb.params['x']

p.ggplot() +\
  p.geom_histogram(p.aes(x=coefs), binwidth = 0.01)