Sampling di Python
James Chapman
Curriculum Manager, DataCamp
Ukuran sampel: 5

Ukuran sampel: 20

Ukuran sampel: 80

Ukuran sampel: 320

Rata-rata dari sampel independen berdistribusi kira-kira normal.
Saat ukuran sampel meningkat,
Distribusi rata-rata makin mendekati normal
Lebar distribusi penarikan contoh makin sempit
coffee_ratings['total_cup_points'].mean()
82.15120328849028
Gunakan np.mean() pada tiap distribusi penarikan contoh perkiraan:
| Ukuran sampel | Rata-rata rata-rata sampel |
|---|---|
| 5 | 82.18420719999999 |
| 20 | 82.1558634 |
| 80 | 82.14510154999999 |
| 320 | 82.154017925 |
coffee_ratings['total_cup_points'].std(ddof=0)
2.685858187306438
ddof=0 saat memanggil .std() untuk populasiddof=1 saat memanggil np.std() untuk sampel atau distribusi penarikan contoh| Ukuran sampel | Simpangan baku rata-rata sampel |
|---|---|
| 5 | 1.1886358227738543 |
| 20 | 0.5940321141669805 |
| 80 | 0.2934024263916487 |
| 320 | 0.13095083089190876 |
| Ukuran sampel | Simpangan baku rata-rata sampel | Perhitungan | Hasil |
|---|---|---|---|
| 5 | 1.1886358227738543 |
2.685858187306438 / sqrt(5) |
1.201 |
| 20 | 0.5940321141669805 |
2.685858187306438 / sqrt(20) |
0.601 |
| 80 | 0.2934024263916487 |
2.685858187306438 / sqrt(80) |
0.300 |
| 320 | 0.13095083089190876 |
2.685858187306438 / sqrt(320) |
0.150 |
Sampling di Python