Sampling Distribution of a Statistic¶

In [1]:

import pandas as pd
import seaborn as sns

import pandas as pd import seaborn as sns

In [2]:

data = pd.read_csv("../data/loans_income.csv")
data

data = pd.read_csv("../data/loans_income.csv") data

Out[2]:

	x
0	67000
1	52000
2	100000
3	78762
4	37041
...	...
49995	40000
49996	54000
49997	50000
49998	82000
49999	70000

50000 rows × 1 columns

In [3]:

sample_data = pd.DataFrame({
    'income': data["x"].sample(1000),
    'type': "Data"
})
sample_data

sample_data = pd.DataFrame({ 'income': data["x"].sample(1000), 'type': "Data" }) sample_data

Out[3]:

	income	type
12865	50000	Data
39562	47500	Data
12410	35000	Data
37284	82000	Data
9290	53000	Data
...	...	...
21338	110000	Data
23629	44000	Data
35915	45000	Data
9348	84000	Data
16936	59712	Data

1000 rows × 2 columns

In [4]:

sample_mean_5 = pd.DataFrame({
    'income': [data["x"].sample(5).mean() for _ in range(1000)],
    'type': "Mean of 5"
})

sample_mean_20 = pd.DataFrame({
    'income': [data["x"].sample(20).mean() for _ in range(1000)],
    'type': "Mean of 20"
})

samples = pd.concat([sample_data, sample_mean_5, sample_mean_20])
samples

sample_mean_5 = pd.DataFrame({ 'income': [data["x"].sample(5).mean() for _ in range(1000)], 'type': "Mean of 5" }) sample_mean_20 = pd.DataFrame({ 'income': [data["x"].sample(20).mean() for _ in range(1000)], 'type': "Mean of 20" }) samples = pd.concat([sample_data, sample_mean_5, sample_mean_20]) samples

Out[4]:

	income	type
12865	50000.00	Data
39562	47500.00	Data
12410	35000.00	Data
37284	82000.00	Data
9290	53000.00	Data
...	...	...
995	69400.95	Mean of 20
996	67074.20	Mean of 20
997	63600.00	Mean of 20
998	67091.30	Mean of 20
999	45081.80	Mean of 20

3000 rows × 2 columns

In [5]:

import matplotlib.pyplot as plt

g = sns.FacetGrid(samples, col="type")
g.map(plt.hist, 'income', bins=40)

import matplotlib.pyplot as plt g = sns.FacetGrid(samples, col="type") g.map(plt.hist, 'income', bins=40)

Out[5]:

<seaborn.axisgrid.FacetGrid at 0x7fa360cd3770>