Question:
13. [Republican primary likely voters only] Next, if
the 2012 Republican primary for president
were being held today, and these were the
candidates, who would you vote for? [rotate
names and then ask: or someone else?]
28% Mitt Romney
22 Rick Santorum
17 Newt Gingrich
8 Ron Paul
2 someone else (specify)
22 don’t know

Poll Demographics

About this Poll
The PPIC Statewide Survey is directed by Mark Baldassare, president and CEO and survey director at
the Public Policy Institute of California, with assistance from Dean Bonner and Jui Shrestha, co-project
managers for this survey, and survey research associate Sonja Petek. The Californians and Their
Government series is supported with funding from The James Irvine Foundation. We benefit from
discussions with PPIC staff, foundation staff, and other policy experts; but the methods, questions,
and content of this report were determined solely by Mark Baldassare and the survey team.
Findings in this report are based on a survey of 2,001 California adult residents, including 1,601
interviewed on landline telephones and 400 interviewed on cell phones. Interviews took an average
of 20 minutes to complete. Interviewing took place on weekday nights and weekend days from February
21 to 28, 2012.
Landline interviews were conducted using a computer-generated random sample of telephone numbers
that ensured that both listed and unlisted numbers were called. All landline telephone exchanges in
California were eligible for selection, and the sample telephone numbers were called as many as six
times to increase the likelihood of reaching eligible households. Once a household was reached, an
adult respondent (age 18 or older) was randomly chosen for interviewing using the “last birthday
method” to avoid biases in age and gender.
Cell phones were included in this survey to account for the growing number of Californians who use them.
These interviews were conducted using a computer-generated random sample of cell phone numbers.
All cell phone numbers with California area codes were eligible for selection, and the sample telephone
numbers were called as many as eight times to increase the likelihood of reaching an eligible
respondent. Once a cell phone user was reached, it was verified that this person was age 18 or older,
a resident of California, and in a safe place to continue the survey (e.g., not driving).
Cell phone respondents were offered a small reimbursement to help defray the cost of the call. Cell
phone interviews were conducted with adults who have cell phone service only and with those who have
both cell phone and landline service in the household.
Live landline and cell phone interviews were conducted by Abt SRBI, Inc. in English and Spanish according
to respondents’ preferences. Accent on Languages, Inc. translated the survey into Spanish, with
assistance from Renatta DeFever.
With assistance from Abt SRBI we used recent data from the U.S. Census Bureau’s 2007–2009
American Community Survey (ACS) through the University of Minnesota’s Integrated Public Use
Microdata Series for California to compare certain demographic characteristics of the survey sample—
region, age, gender, race/ethnicity, and education—with the characteristics of California’s adult
population. The survey sample was closely comparable to the ACS figures. Abt SRBI used data from the
2008 National Health Interview Survey and data from the 2007–2009 ACS for California both to estimate
landline and cell phone service in California and to compare the data against landline and cell phone
service reported in this survey. We also used voter registration data from the California Secretary of State
to compare the party registration of registered voters in our sample to party registration statewide. The
landline and cell phone samples were then integrated using a frame integration weight, while sample
balancing adjusted for any differences across regional, age, gender, race/ethnicity, education, telephone
service, and party registration groups.
The sampling error, taking design effects from weighting into consideration, is ±3.4 percent at
the 95 percent confidence level for the total sample of 2,001 adults. This means that 95 times
PPIC Statewide Survey
March 2012 Californians and Their Government 26
out of 100, the results will be within 3.4 percentage points of what they would be if all adults in
California were interviewed. The sampling error for subgroups is larger: For the 1,334 registered voters,
it is ±3.8 percent; for the 859 likely voters, it is ±4.2 percent; for the 281 Republican primary likely
voters, it is ±7.4 percent. Sampling error is only one type of error to which surveys are subject. Results
may also be affected by factors such as question wording, question order, and survey timing.
We present results for four geographic regions, accounting for approximately 90 percent of the state
population. “Central Valley” includes Butte, Colusa, El Dorado, Fresno, Glenn, Kern, Kings, Madera,
Merced, Placer, Sacramento, San Joaquin, Shasta, Stanislaus, Sutter, Tehama, Tulare, Yolo, and Yuba
Counties. “San Francisco Bay Area” includes Alameda, Contra Costa, Marin, Napa, San Francisco,
San Mateo, Santa Clara, Solano, and Sonoma Counties. “Los Angeles” refers to Los Angeles County,
and “Other Southern California” includes Orange, Riverside, San Bernardino, and San Diego Counties.
Residents from other geographic areas are included in the results reported for all adults, registered
voters, and likely voters; but sample sizes for these less populated areas are not large enough to report
separately.
We present specific results for non-Hispanic whites and for Latinos, who account for about a third of
the state’s adult population and constitute one of the fastest-growing voter groups. We also present
results for non-Hispanic Asians, who make up about 14 percent of the state’s adult population.
Results for other racial/ethnic groups—such as non-Hispanic blacks and Native Americans—are
included in the results reported for all adults, registered voters, and likely voters; but sample sizes
are not large enough for separate analysis. We compare the opinions of those who report they are
registered Democrats, registered Republicans, and decline-to-state or independent voters; the
results for those who say they are registered to vote in another party are not large enough for
separate analysis. We also analyze the responses of likely voters—so designated by their responses
to voter registration survey questions, previous election participation, intentions to vote in the June
primary, and current interest in politics.
The percentages presented in the report tables and in the questionnaire may not add to 100 due
to rounding.
We compare current PPIC Statewide Survey results to those in our earlier surveys and to those
in national surveys by CBS News/New York Times, NBC News/Wall Street Journal, Pew Research
Center, and USA Today/Gallup. Additional details about our methodology can be found at
http://www.ppic.org/content/other/SurveyMethodology.pdf and are available upon request through
surveys@ppic.org.