NSFG Data

Section 3.4 NSFG Data

In the previous chapter, we plotted frequency tables of pregnancy lengths for first babies and others. But the sizes of the groups are not the same, so we can’t compare the frequency tables directly. Because PMFs are normalized, we can compare them. So let’s load the NSFG data again and make Pmf objects to represent distributions of pregnancy lengths.

🔗

The nsfg module provides a get_nsfg_groups function that reads the data, selects rows that represent live births, and partitions live births into first babies and others. It returns three DataFrame objects.

🔗

Listing 3.4.1. Python Code

🔗

try:
    import statadict
except ImportError:
    %pip install statadict

Listing 3.4.2. Python Code

🔗

download("https://github.com/AllenDowney/ThinkStats/raw/v3/nb/nsfg.py")
download("https://github.com/AllenDowney/ThinkStats/raw/v3/data/2002FemPreg.dct")
download("https://github.com/AllenDowney/ThinkStats/raw/v3/data/2002FemPreg.dat.gz")

Listing 3.4.3. Python Code

🔗

from nsfg import get_nsfg_groups

live, firsts, others = get_nsfg_groups()

We can use firsts and others to make a Pmf for the pregnancy lengths in each group.

🔗

Listing 3.4.4. Python Code

🔗

first_pmf = Pmf.from_seq(firsts["prglngth"], name="firsts")
other_pmf = Pmf.from_seq(others["prglngth"], name="others")

Here are the PMFs for first babies and others, plotted as bar graphs.

🔗

Listing 3.4.5. Python Code

🔗

two_bar_plots(first_pmf, other_pmf)
decorate(xlabel="Weeks", ylabel="Probability", xlim=[20, 50])

By plotting the PMF instead of the frequency table, we can compare the two distributions without being misled by the difference in sizes of the samples. Based on this figure, first babies seem to be less likely than others to arrive on time (week 39) and more likely to be late (weeks 41 and 42).

🔗

Prev Top Next