NYCPlanning / db-acs

American Community Survey data processing for Population Fact Finder
4 stars 1 forks source link

calculation errors on population's end? #14

Closed SPTKL closed 4 years ago

SPTKL commented 4 years ago

In the social table: for geoid = 1015100 and variable=DfHsUS

Based on the variable look up

"DfHsUS": [
        "DP02_0080"
    ],

pulling pre-calculation data:

>>> dff = df.loc[df.GEO_ID=='1400000US36061015100', ['DP02_0080E', 'DP02_0080M', 'DP02_0080PE', 'DP02_0080PM']]
>>> dff
      DP02_0080E  DP02_0080M  DP02_0080PE  DP02_0080PM
2283      1000.0       402.0         12.0          4.6

In this case, we are taking PE and PM directly from ACS without calculation, so it's a mistake from population? (assuming the variable mapping is correct)

EricaMaurer commented 4 years ago

The estimate and margin of error match the database, the percent and percent MOE should be calculated off of DfHs2. Is that what you are using?