PolicyLink and PERE
119
An Equity Profile of Orange County
Voter, undocumented, and eligible-to-naturalize analysis
Data and methods
the sample size is large enough to make
reasonably accurate estimates for sub-state
geographies. One critical shortcoming of
this dataset for our purposes, however, is
that while it identifies non-citizen
immigrants, it does not identify which non-
citizens are documented and which are not.
In order to figure out who was eligible to
naturalize, we first had to determine who
was undocumented, then assumed that the
remaining non-citizen immigrants were
documented Lawful Permanent Residents
(LPRs).
Our estimation of who was undocumented
is based on a statistical model developed
using the 2014 SIPP that was applied to the
ACS microdata. For those interested in the
details of our methodology, please refer to
the document at:
https://dornsife.usc.edu/assets/sites/731/d
ocs/Methodology_Final_updated_ETN_2017.
pdf. For the current research, we applied the
same methodology to the more recent
aforementioned datasets.
Voter data
Data on voters are from the Statewide
Database at the University of California,
Berkeley (SWDB). Voter data are obtained by
the Statewide Database from individual
Registrars of Voters in each of the 58
counties in California. Because county voter
registration data do not include racial
identifiers, the Statewide Database employs
a surname matching technique to identify
Latinos and Asian American voters. For more
information, please refer to the SWDB
methodology available on their website,
http://statewidedatabase.org/index.html.
Undocumented and eligible-to-naturalize
Pages 91-92 of the equity profile present
estimates that stem from a dataset
PERE/CSII assembled using the 2016 5-year
American Community Survey (ACS)
microdata from IPUMS-USA, covering the
years 2012 through 2016, and the 2014
Survey of Income and Program Participation
(SIPP). We chose the 5-year ACS microdata
because it contains a wide variety of
individual and household characteristics and
With identifiers in place for who was an LPR
among non-citizens in the ACS microdata,
we applied some basic conditions to
determine which of them were likely to be
eligible-to-naturalize adults. We included all
individuals at least 18-years-old who had
been in the United States for at least five
years prior to the survey (or three years if
married to a U.S. citizen).
