Below are the first 10 and last 10 pages of uncorrected machine-read text (when available) of this chapter, followed by the top 30 algorithmically extracted key phrases from the chapter as a whole.
Intended to provide our own search engines and external engines with highly rich, chapter-representative searchable text on the opening pages of each chapter.
Because it is UNCORRECTED material, please consider the following text as a useful but insufficient proxy for the authoritative book pages.
Do not use for reproduction, copying, pasting, or reading; exclusively for search engines.
OCR for page 126
126 A Guidebook for Using American Community Survey Data for Transportation Planning
Table 7.6. Calculation of index of dissimilarity with confidence intervals.
PUMA a/A SE(a/A) b/B SE(b/B) a/A-b/B SE(a/A-b/B) ID
35.34
3601 0.102 0.0033 0.037 0.0007 0.065 0.0034
3602 0.081 0.0017 0.040 0.0010 0.041 0.0020 SE(ID)
3603 0.078 0.0021 0.063 0.0018 0.016 0.0027 0.51
3604 0.080 0.0017 0.056 0.0016 0.024 0.0024
3605 0.081 0.0015 0.133 0.0036 0.052 0.0040 ME(ID)
3606 0.092 0.0023 0.155 0.0011 0.063 0.0025 0.84
3607 0.034 0.0009 0.177 0.0040 0.144 0.0041
3608 0.097 0.0028 0.077 0.0014 0.020 0.0032
3609 0.079 0.0022 0.033 0.0008 0.046 0.0023
3610 0.098 0.0006 0.012 0.0004 0.086 0.0008
3611 0.078 0.0018 0.041 0.0009 0.037 0.0020
3612 0.025 0.0005 0.120 0.0032 0.095 0.0032
3613 0.075 0.0019 0.056 0.0012 0.019 0.0022
The differences in (ai/A) and (bi/B) are calculated directly. To obtain the standard error of this
difference in estimates, apply the following formula (again, from Section 4 and Census Bureau
guidance) as follows:
In this case, X and Y refer to the (ai/A) and (bi/B) estimates.
The differences in (ai/A) and (bi/B) are then summed, divided by two, and multiplied by 100
to obtain the ID. The standard error of this summation can be calculated using an extension of
the same formula with 13 addends. The final standard error of the calculation can then be mul-
tiplied by 1.65 to obtain the 90 percent confidence level margin of error, so the ID in this case is
35.34 ± 0.84.
(
^ +Y
SE X ^ = SE X
)
^ 2 + SE Y
^ 2
( ) ( )
Calculating a confidence interval on a measure like the ID becomes a useful exercise when
the IDs for different geographies (e.g., one county compared to another), areal units (e.g.,
PUMA-level analysis versus tract-level analysis), or combinations of population groups (non-
Hispanic white compared to non-Hispanic black versus non-Hispanic compared to Hispanic)
are compared.
7.4 Conclusions from the Case Study
This case study has demonstrated how to calculate the ID, which is one application of environ-
mental justice analysis. The power of this measure is in its ability to be calculated for specific areal
units, then imported into a geographic information system (GIS) for mapping and displaying the
uniformity or diversity of a region. The ID plays an important role in estimating impacts within
the environmental justice process and is also applicable to specific transportation projects.
There are two important notes regarding weaknesses of this measure. The first issue involves
the "aspatial" nature of this measure. Although the ID does represent a summary measure of spa-
tial "evenness," it does so only in a very simplified, non-spatial way for a particular areal unit.
