Download this release as a PDF document.
List of all releases for this calendar year
PublicMind research for years 2001-2017
MONDAY August 26, 2019
Media Contacts: | Ashley Koning (Rutgers-Eagleton), akoning@rutgers.edu, [redacted] Peter Woolley (FDU), woolley@fdu.edu, [redacted] |
New Brunswick and Madison, New Jersey (August 26, 2019) – More than 80 percent of New Jerseyans say their local school districts include a good mix of races and ethnicities, and just 14 percent say their local schools are segregated, despite research that has found high levels of segregation of black and Latin-American students in the Garden State.
New Jerseyans’ views about the ethnic makeup of their local school districts are the subject of the latest Rutgers-Eagleton/Fairleigh Dickinson University polling partnership, in collaboration with Fairleigh Dickinson University’s School of Public and Global Affairs.
Almost half (49 percent) of respondents report that students in their district represent a variety of racial and ethnic backgrounds. Another third, however, say the students at their local schools are mostly white, and almost one in five say their local schools are mostly black (8 percent) or members of another race or ethnicity (9 percent).
The majority of respondents see no need for change. Nearly two-thirds (64 percent) feel things are “fine the way they are” when it comes to diversity in their local schools; just a quarter (26 percent) say they would like to see more racial and ethnic diversity.
“Despite being one of the most diverse states in the country, research shows New Jersey has the sixth-highest level of segregation of black students and the seventh-highest level for Latin-American students,” said Ashley Koning, assistant research professor and director of the Eagleton Center for Public Interest Polling (ECPIP) at Rutgers University–New Brunswick. “Yet most residents’ perceptions seem at odds with reality, except for those who may experience it firsthand due to their own race, ethnicity, or economic status.”
The Fairleigh Dickinson University Poll asked the same questions earlier this year of a set of national respondents. New Jerseyans are more likely than individuals nationwide to say their local schools have “a good mix” of races (83 percent versus 73 percent) but are also more likely to say their local schools are dominated by students of one race or ethnicity, whether white, black or another group (50 percent versus 43 percent). Additionally, New Jerseyans are more likely than people nationally (64 percent versus 56 percent) to say things are fine the way they are when it comes to diversity in schools.
“If 50 percent say their schools are mostly one race or ethnicity while 83 percent say their school has a good mix, then clearly there are different ideas about what constitutes segregation,” said Peter Woolley, Director of FDU’s School of Public and Global Affairs.
The Rutgers-Eagleton/Fairleigh Dickinson University Poll of New Jerseyans contacted 1,250 adults between March 7 and 22, 2019. Of those, 621 of were contacted by live callers on landlines and cell phones, and 629 were reached through an online probability-based panel. The combined sample has a margin of error of +/-3.6 percentage points; the phone sample has a margin of error of +/-4.5 percentage points, and the online probability-base sample has a margin of error of +/-5.5 percentage points. Interviews were done in English and, when requested, Spanish. The full analysis, along with the poll’s questions and tables, can be found on the Rutgers-Eagleton Poll website and the FDU Poll website.
White residents are more likely than non-white residents to report greater diversity among students in their district (52 percent versus 45 percent) but are also more likely to report students in their district as being mostly white (37 percent to 27 percent). Non-white residents, on the other hand, are more than twice as likely as white residents to report that the students in their local school district are mostly black (13 percent versus 4 percent) or mostly another race or ethnicity (14 percent versus 5 percent), though these numbers are still comparatively small.
Three-quarters of those who report that their local school district is mostly white nevertheless say their district has a good mix of different races and ethnicities. On the other hand, a majority of those who report that local students are mostly another race or a mixture of races say the district has a good mix racially and ethnically.
Younger residents are more likely than older residents to perceive segregation in their local school district and are also less likely to report a variety of racial and ethnic backgrounds among their student population.
Those living in higher-income areas see less diversity in their local school district. Nearly half (46 percent) of those in the highest income bracket say the students in their local schools are mostly white, compared with one in five (22 percent) who say the same among those in the lowest income bracket. Likewise, four in ten (40 percent) of those in the highest income bracket report a mostly mixed student body, compared with almost two-thirds (63 percent) of those in the lowest income bracket.
A similar pattern emerges with education: two-thirds of those with a high school diploma or less say their student population includes a mixture of races and ethnicities, compared with one-third of those who have completed some type of graduate work.
Women are more likely than men (30 percent versus 22 percent) to say they would welcome more diversity – though about two-thirds of each gender are fine with the way things are now.
Democrats are far more likely than Republicans to prefer more racial and ethnic diversity (39 percent versus 5 percent). Independents tend to agree with Democrats, with 29 percent wanting to see more diversity in their schools.
White residents are more likely than non-white residents (72 percent versus 52 percent) to say things are fine the way they are; non-white residents are twice as likely as white residents (38 percent versus 18 percent) to say more diversity is needed.
Some respondents answered the survey questions online, while others spoke by phone with live interviewers. The presence or absence of a live interviewer appeared to affect their expressed diversity preferences. While a small percentage of respondents said they wanted less racial and ethnic diversity in their schools, those who completed the survey online were more than four times likely to express that view than those who spoke with an interviewer (12 percent vs 3 percent).
###
Broadcast interviews: Rutgers University–New Brunswick has broadcast-quality TV and radio studios available for remote live or taped interviews with Rutgers experts. For more information, contact Neal Buccino neal.buccino@echo.rutgers.edu
ABOUT RUTGERS—NEW BRUNSWICK
Rutgers University–New Brunswick is where Rutgers, the State University of New Jersey, began more than 250 years ago. Ranked among the world’s top 60 universities, Rutgers’s flagship university is a leading public research institution and a member of the prestigious Association of American Universities. It is home to internationally acclaimed faculty and has 12 degree-granting schools and a Division I Athletics program. It is the Big Ten Conference’s most diverse university. Through its community of teachers, scholars, artists, scientists, and healers, Rutgers is equipped as never before to transform lives.
ABOUT THE EAGLETON CENTER FOR PUBLIC INTEREST POLLING (ECPIP)
Home of the Rutgers-Eagleton Poll, ECPIP was established in 1971 and is the oldest and one of the most respected university-based state survey research centers in the United States. Now in its 48th year and with the publication of over 200 polls, ECPIP’s mission is to provide scientifically sound, non-partisan information about public opinion. To read more about ECPIP and view all of our press releases and published research, please visit our website: eagletonpoll.rutgers.edu. You can also visit our extensive data archive, Facebook, and Twitter.
ABOUT THE EAGLETON INSTITUTE OF POLITICS
The Eagleton Center for Public Interest Polling is a unit of the Eagleton Institute of Politics at Rutgers University-New Brunswick. The Eagleton Institute explores state and national politics through research, education, and public service, linking the study of politics with its day-to-day practice. The Institute focuses attention on how the American political system works, how it changes, and how it might work better. To learn more about Eagleton programs and expertise, visit eagleton.rutgers.edu.
ABOUT FAIRLEIGH DICKINSON UNIVERSITY
Personal, global and transformational, FDU is also the largest independent, non-profit university in New Jersey, but has an international profile with four campuses in three time zones; two in the Garden State, one in Oxfordshire, England and one in Vancouver, Canada. FDU provides more than 100 undergraduate and graduate degree programs, including doctoral programs in pharmacy, nursing practice, clinical psychology and school psychology; and an AACSB-accredited business school.
ABOUT THE FAIRLEIGH DICKINSON UNIVERSITY POLL
For the second year, the FDU Poll received an “A” rating from statistician Nate Silver’s FiveThirtyEight blog. The ratings measure both accuracy and bias for all major polling services in the United States, providing an update to similar research the poll watchers conducted in 2014. FDU’s “A” rating puts it in the top 15 of the more than 380 polling institutes reviewed and graded from A+ through F. The FDU poll was found to have a 94 percent accuracy rate for predicting election results, and is one of only three A-rated polling institutes with zero bias to their rankings. Please visit our website: publicmind.fdu.edu.
ABOUT FDU’s School of Public and Global Affairs
Home of the FDU Poll, the aim of this unique graduate school is to attract outstanding students from Canada, the U.K. and the U.S. with the goal of preparing them for substantial advancement in public service or non-profit leadership. At its 2018 founding, the school offers three elements of education and research including the Master of Public Administration (MPA) program for those who want to lead governmental organizations and non-profits, whether on a global or local scale; the MA in Global Affairs which is offered to consular and diplomatic staff to students from around the globe, from Argentina to Zambia and the FDU Poll which has engaged since 2001 in original research for corporate, non-profit, and government entities.
The questions covered in this release are listed below. Column percentages may not add to 100% due to rounding. Respondents are New Jersey adults. All percentages are of weighted results. Interpret groups with samples sizes under 100 with caution.
Q. Now let’s talk about your local school district. In the area where you live, would you say the schools are segregated by race and ethnicity or is there a good mix of different races and ethnicities?
| Combined | Phone | Online |
|---|---|---|---|
Segregated | 14% | 12% | 16% |
A good mix | 83% | 82% | 84% |
Don't know (vol) | 3% | 6% | 0% |
Unwght N= | 611 | 312 | 299 |
| Party ID | Gender | Race | Age | Income | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dem | Ind | Rep | Male | Female | White | Non- wht. | 18-39 | 40-64 | 65+ | <$50K | $50K-<$100K | $100K-<$150K | $150K+ | ||
Segregated | 17% | 11% | 12% | 11% | 17% | 12% | 18% | 21% | 12% | 8% | 17% | 15% | 13% | 12% | |
A good mix | 81% | 84% | 86% | 87% | 80% | 85% | 79% | 77% | 85% | 88% | 80% | 84% | 83% | 85% | |
Don't know (vol) | 2% | 6% | 2% | 3% | 3% | 3% | 3% | 2% | 3% | 5% | 3% | 1% | 4% | 3% | |
Unwght N= | 284 | 102 | 211 | 266 | 345 | 426 | 174 | 152 | 292 | 165 | 134 | 210 | 121 | 106 | |
| Education | Region | Schools in community are | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
HS or Less | Some Coll | Coll Grad | Grad Work | Urban | Suburb | Exurban | Phil/ South | Shore | Mostly white | Mostly black | Mostly another race/eth | A variety | |
Segregated | 14% | 14% | 16% | 12% | 21% | 8% | 18% | 17% | 14% | 21% | 52% | 13% | 2% |
A good mix | 83% | 84% | 80% | 85% | 75% | 89% | 80% | 82% | 80% | 75% | 48% | 84% | 96% |
Don't know (vol) | 3% | 2% | 4% | 3% | 3% | 3% | 2% | 1% | 6% | 3% | 0% | 3% | 2% |
Unwght N= | 106 | 170 | 188 | 145 | 77 | 241 | 83 | 103 | 107 | 217 | 38 | 48 | 290 |
Q. Would you say the schools where you live have students who are mostly white, mostly black, mostly another race or ethnicity, or are the students from a variety of racial and ethnic backgrounds?
| Combined | Phone | Online |
|---|---|---|---|
Mostly white | 33% | 34% | 31% |
Mostly black | 8% | 6% | 10% |
Mostly another race/ethnicity | 9% | 7% | 11% |
A variety | 49% | 50% | 49% |
Don't know (vol) | 2% | 4% | 0% |
Unwght N= | 616 | 312 | 304 |
| Party ID | Gender | Race | Age | Income | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dem | Ind | Rep | Male | Female | White | Non- wht. | 18-39 | 40-64 | 65+ | <$50K | $50K-<$100K | $100K-<$150K | $150K+ | |
Mostly white | 36% | 26% | 33% | 32% | 33% | 37% | 27% | 32% | 31% | 36% | 22% | 33% | 33% | 46% |
Mostly black | 10% | 6% | 4% | 7% | 9% | 4% | 13% | 14% | 5% | 3% | 10% | 10% | 9% | 1% |
Mostly another race/ethnicity | 11% | 7% | 7% | 9% | 8% | 5% | 14% | 10% | 9% | 5% | 4% | 11% | 10% | 10% |
A variety | 42% | 60% | 53% | 49% | 49% | 52% | 45% | 41% | 52% | 54% | 63% | 44% | 45% | 40% |
Don't know (vol) | 1% | 1% | 3% | 3% | 1% | 2% | 1% | 2% | 2% | 2% | 1% | 1% | 3% | 4% |
Unwght N= | 286 | 104 | 211 | 268 | 348 | 429 | 176 | 154 | 293 | 167 | 136 | 212 | 125 | 104 |
| Education | Region | |||||||
|---|---|---|---|---|---|---|---|---|---|
HS or Less | Some Coll | Coll Grad | Grad Work | Urban | Suburb | Exurban | Phil/ South | Shore | |
Mostly white | 23% | 34% | 33% | 48% | 9% | 25% | 57% | 44% | 39% |
Mostly black | 6% | 11% | 8% | 4% | 25% | 7% | 1% | 4% | 3% |
Mostly another race/ethnicity | 6% | 5% | 13% | 13% | 20% | 11% | 3% | 3% | 4% |
A variety | 63% | 49% | 43% | 33% | 44% | 55% | 39% | 48% | 51% |
Don't know (vol) | 1% | 2% | 3% | 2% | 2% | 2% | 1% | 1% | 3% |
Unwght N= | 107 | 172 | 188 | 147 | 76 | 245 | 86 | 101 | 108 |
Q. Thinking about the schools where you live would you prefer more racial and ethnic diversity, less racial and ethnic diversity, or are things fine the way they are now?
| Combined | Phone | Online |
|---|---|---|---|
More | 26% | 27% | 25% |
Less | 7% | 3% | 12% |
Fine the way they are now | 64% | 65% | 63% |
Don't know (vol) | 2% | 5% | 0% |
Unwght N= | 610 | 309 | 301 |
| Party ID | Gender | Race | Age | Income | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dem | Ind | Rep | Male | Female | White | Non- wht. | 18-39 | 40-64 | 65+ | <$50K | $50K-<$100K | $100K-<$150K | $150K+ | |
More | 39% | 29% | 5% | 22% | 30% | 18% | 38% | 36% | 24% | 16% | 24% | 30% | 22% | 24% |
Less | 5% | 6% | 12% | 8% | 6% | 7% | 9% | 10% | 8% | 3% | 5% | 11% | 11% | 2% |
Fine the way they are now | 56% | 64% | 78% | 67% | 62% | 72% | 52% | 53% | 67% | 75% | 68% | 57% | 65% | 72% |
Don't know (vol) | 1% | 1% | 5% | 3% | 2% | 3% | 1% | 1% | 2% | 6% | 3% | 2% | 1% | 3% |
Unwght N= | 286 | 99 | 211 | 266 | 344 | 427 | 172 | 152 | 290 | 166 | 134 | 209 | 125 | 104 |
| Education | Region | Schools in community are | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
HS or Less | Some Coll | Coll Grad | Grad Work | Urban | Suburb | Exurban | Phil/ South | Shore | Mostly white | Mostly black | Mostly another race/eth | A variety | |
More | 18% | 30% | 25% | 32% | 41% | 20% | 24% | 26% | 27% | 45% | 63% | 29% | 7% |
Less | 7% | 8% | 7% | 9% | 12% | 9% | 6% | 2% | 6% | 0% | 17% | 29% | 7% |
Fine the way they are now | 71% | 61% | 65% | 57% | 46% | 68% | 69% | 70% | 64% | 54% | 20% | 42% | 84% |
Don't know (vol) | 4% | 1% | 2% | 2% | 1% | 3% | 1% | 2% | 3% | 1% | 0% | 0% | 2% |
Unwght N= | 105 | 170 | 188 | 145 | 77 | 239 | 84 | 102 | 108 | 220 | 38 | 47 | 288 |
NATIONAL
Q. In the area where you live, would you say the schools are segregated by race and ethnicity or is there a good mix of different races and ethnicities?
Segregated | 14% |
|---|---|
A good mix | 73% |
Don't know (vol) | 11% |
Refused (vol) | 2% |
Unwght N= | 1000 |
| Party ID | Gender | Race | Education | Schools in community are | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dem | Ind | Rep | Male | Female | White | Non- wht. | HS grad or less | Some coll | Coll grad+ | Mostly white | Mostly black | Mostly another race/eth | A variety | |
Segregated | 20% | 10% | 11% | 14% | 15% | 14% | 15% | 16% | 9% | 17% | 22% | 45% | 33% | 4% |
A good mix | 69% | 77% | 77% | 75% | 71% | 73% | 72% | 72% | 78% | 70% | 63% | 46% | 63% | 88% |
Don't know (vol) | 10% | 13% | 10% | 10% | 13% | 12% | 11% | 12% | 10% | 11% | 14% | 8% | 3% | 6% |
Refused (vol) | 1% | 0% | 2% | 2% | 2% | 1% | 2% | 0% | 2% | 2% | 0% | 1% | 0% | 1% |
Unwght N= | 366 | 168 | 357 | 501 | 499 | 712 | 288 | 224 | 303 | 463 | 309 | 49 | 54 | 503 |
Q. Would you say the schools where you live have students who are mostly white, mostly black, mostly another race or ethnicity, or are the students from a variety of racial and ethnic backgrounds?
Mostly white | 29% |
|---|---|
Mostly black | 5% |
Mostly another race/ethnicity | 9% |
A variety | 50% |
Don't know (vol) | 6% |
Refused (vol) | 1% |
Unwght N= | 1000 |
| Party ID | Gender | Race | Education | ||||||
|---|---|---|---|---|---|---|---|---|---|---|
Dem | Ind | Rep | Male | Female | White | Non- wht. | HS grad or less | Some coll | Coll grad+ | |
Mostly white | 31% | 30% | 34% | 30% | 28% | 36% | 21% | 27% | 22% | 35% |
Mostly black | 6% | 4% | 3% | 5% | 5% | 4% | 5% | 5% | 6% | 4% |
Mostly another race/ethnicity | 9% | 5% | 8% | 8% | 9% | 4% | 15% | 12% | 12% | 5% |
A variety | 47% | 53% | 50% | 51% | 48% | 49% | 51% | 48% | 51% | 49% |
Don't know (vol) | 6% | 7% | 4% | 5% | 8% | 6% | 7% | 7% | 7% | 5% |
Refused (vol) | 1% | 0% | 1% | 1% | 1% | 1% | 1% | 1% | 2% | 1% |
Unwght N= | 366 | 168 | 357 | 501 | 499 | 712 | 288 | 224 | 303 | 463 |
Q. Thinking about the schools where you live would you prefer more racial and ethnic diversity, less racial and ethnic diversity, or are things fine the way they are now?
More | 30% |
|---|---|
Less | 3% |
Fine the way they are now | 56% |
Don't know (vol) | 8% |
Refused (vol) | 3% |
Unwght N= | 1000 |
| Party ID | Gender | Race | Education | ||||||
|---|---|---|---|---|---|---|---|---|---|---|
Dem | Ind | Rep | Male | Female | White | Non- wht. | HS grad or less | Some coll | Coll grad+ | |
More | 43% | 29% | 14% | 25% | 34% | 27% | 33% | 21% | 27% | 36% |
Less | 2% | 4% | 4% | 4% | 3% | 3% | 4% | 7% | 4% | 1% |
Fine the way they are now | 48% | 60% | 71% | 60% | 53% | 60% | 51% | 62% | 59% | 52% |
Don't know (vol) | 5% | 6% | 8% | 8% | 8% | 8% | 9% | 10% | 6% | 9% |
Refused (vol) | 2% | 1% | 3% | 3% | 2% | 2% | 3% | 1% | 4% | 3% |
Unwght N= | 366 | 168 | 357 | 501 | 499 | 712 | 288 | 224 | 303 | 463 |
About the Rutgers-Eagleton/Fairleigh Dickinson Polling Partnership
For almost 50 years, the Rutgers-Eagleton Poll – established in 1971 at Rutgers University’s Eagleton Institute of Politics – has been conducted by telephone, using what is known as a probability-based sample to survey New Jersey residents. That methodology has since been used by all other academic organizations that have conducted surveys in New Jersey – including Fairleigh Dickinson University (established in 2001), Monmouth University (established in 2005), and Quinnipiac University.
The polling landscape has dramatically transformed within the last decade, however. Due to technological changes (like cell phones and caller ID), behavioral changes (like fewer people answering their phones and responding to surveys), and an increased number of unsolicited calls (like telemarketing and spam), telephone surveys have become far more difficult and far more expensive. Response rates are now in the single digits, meaning more call attempts have to be made than ever before to achieve a single completed interview – which, in turn, means more time and more money. It now costs almost three times as much to complete a telephone interview than it did just five years ago, with fielding costs reaching over $100 per completed interview at some of the most well-known and respected telephone survey call centers.
The polling profession has started to adapt by moving online but has faced a major hurdle – the current inability to take a probability-based sample of Internet users. The industry has attempted to tackle this problem in two ways:
A number of research studies have found that the results of probability and non-probability samples are similar, if weighted correctly at the end. But probability samples are still slightly more accurate, may have better reliability over time, and allow for the computation of sampling error – a statement of the probabilities of how likely the poll is to be accurate.
Because of the need to move away from telephone surveys, the Rutgers-Eagleton Poll at Rutgers-New Brunswick’s Eagleton Institute of Politics and the FDU Poll at Farleigh Dickinson University have combined their resources to conduct one of the first ever in-depth experiments testing the effects of both survey mode and type of sample on statewide public opinion polling. The extensive study involves testing an identical questionnaire on three different samples:
The results reported on in this series of releases by Rutgers-Eagleton and FDU will report results only from the combined samples of the telephone survey and online probability-based panel. The questionnaire was developed and all data analyses were completed in house by Dr. Ashley Koning and Dr. Cliff Zukin at the Eagleton Center for Public Interest Polling (ECPIP) at Rutgers University-New Brunswick and Dr. Krista Jenkins at Fairleigh Dickinson University. William Young and Kyle Morgan assisted with preparation of the questionnaire and analysis and preparation of this release. This poll is paid for and sponsored by both the Eagleton Institute of Politics at Rutgers University-New Brunswick and Fairleigh Dickinson University.
Telephone Methodology
The telephone survey was conducted by live callers on both landlines and cellular phones between March 7 and 12, 2019, with a scientifically selected random sample of 621 New Jersey adults, 18 or older. Persons without a telephone could not be included in the random selection process. Respondents within a household are selected by asking randomly for the youngest adult male or female currently available. If the named gender is not available, the youngest adult of the other gender is interviewed. The poll was available in Spanish for respondents who requested it. This telephone poll included 258 adults reached on a landline phone and 363 adults reached on a cell phone, all acquired through random digit dialing. Distribution of household phone use in this sample is:
Cell Only: 34%
Dual Use, Reached on Cell: 24%
Dual Use, Reached on LL: 39%
Landline Only: 2%
The data were weighted to be representative of the non-institutionalized adult population of New Jersey. The weighting balanced sample demographics to target population parameters. The sample is balanced to match parameters for sex, age, education, race/ethnicity, region and phone use. The sex, age, education, race/ethnicity and region parameters were derived from 2017 American Community Survey PUMS data. The phone use parameter was derived from estimates provided by the National Health Interview Survey Early Release Program.[1][2][3]
Weighting was done in two stages. The first stage of weighting corrected for different probabilities of selection associated with the number of adults in each household and each respondent’s telephone usage patterns. This adjustment also accounts for the overlapping landline and cell sample frames and the relative sizes of each frame and each sample. This first stage weight was applied to the entire sample which included all adults.
The second stage of the weighting balanced sample demographics, by form, to match target population benchmarks. This weighting was accomplished using SPSSINC RAKE, an SPSS extension module that simultaneously balances the distributions of all variables using the GENLOG procedure. Weights were trimmed to prevent individual interviews from having too much influence on the final results. The use of these weights in statistical analysis ensures that the demographic characteristics of the sample closely approximate the demographic characteristics of the target population.
An adjustment was incorporated into the raking to ensure that the party ID distribution of both forms were similar to each other. This was done by first raking the entire sample to target population benchmarks and extracting from that weighted data a party ID “benchmark”. Then the final weighting by form included all the weighting demographics listed above, plus the party ID distribution derived from the first raking.
All surveys are subject to sampling error, which is the expected probable difference between interviewing everyone in a population versus a scientific sampling drawn from that population. Sampling error should be adjusted to recognize the effect of weighting the data to better match the population. In this poll, the simple sampling error for 621 New Jersey adults is +/-3.9 percentage points at a 95 percent confidence interval. The design effect is 1.31, making the adjusted margin of error +/- 4.5 percentage points. Thus, if 50 percent of New Jersey adults in this sample favor a particular position, we would be 95 percent sure that the true figure is between 45.5 and 54.5 percent (50 +/- 4.5) if all New Jersey adults had been interviewed, rather than just a sample.
Sampling error does not take into account other sources of variation inherent in public opinion studies, such as non-response, question wording, or context effects.
This telephone survey was fielded by Braun Research, Inc.
Weighted Telephone Sample Characteristics
621 New Jersey Adults
Male | 48% |
| Democrat | 36% |
| 18-34 | 25% |
| HS or Less | 30% |
| White | 58% |
Female | 52% |
| Independent | 41% |
| 35-49 | 24% |
| Some College | 30% |
| Black | 12% |
|
| Republican | 23% |
| 50-64 | 30% |
| College Grad | 22% |
| Hispanic | 19% | |
|
|
|
|
|
| 65+ | 20% |
| Grad Work | 17% |
| Other | 12% |
Online Methodology
The online survey was conducted between March 13 and 22, 2019, using the web-enabled KnowledgePanel®, a probability-based panel designed to be representative of the U.S. population. Initially, participants are chosen scientifically by a random selection of telephone numbers and residential addresses. Persons in selected households are then invited by telephone or by mail to participate in the web-enabled KnowledgePanel. For those who agree to participate, but do not already have Internet access, Ipsos provides at no cost a laptop/netbook and ISP connection. People who already have computers and Internet service are permitted to participate using their own equipment. Panelists then receive unique log-in information for accessing surveys online, and then are sent emails throughout each month inviting them to participate in research. This survey contained 629 New Jersey adults, 18 or older and was available in Spanish for respondents who requested it.
The data were weighted to be representative of the non-institutionalized adult population of New Jersey. The sample was balanced, by form, to match target population benchmarks for sex, age, education, race/ethnicity, region and phone use. The sex, age, education, race/ethnicity and region parameters were derived from 2017 American Community Survey PUMS data. The phone use parameter was derived from estimates provided by the National Health Interview Survey Early Release Program.[4][5][6]
This weighting was accomplished using SPSSINC RAKE, an SPSS extension module that simultaneously balances the distributions of all variables using the GENLOG procedure. Weights were trimmed to prevent individual interviews from having too much influence on the final results. The use of these weights in statistical analysis ensures that the demographic characteristics of the sample closely approximate the demographic characteristics of the target population. The IPSOS KnowledgePanel base weight was used as the input weight for the weighting.
An adjustment was incorporated into the raking to ensure that the party ID distribution of both forms were similar to each other. This was done by first raking the entire sample to target population benchmarks and extracting from that weighted data a party ID “benchmark”. Then the final weighting by form included all the weighting demographics listed above, plus the party ID distribution derived from the first raking.
All surveys are subject to sampling error, which is the expected probable difference between interviewing everyone in a population versus a scientific sampling drawn from that population. Sampling error should be adjusted to recognize the effect of weighting the data to better match the population. In this poll, the simple sampling error for 629 New Jersey adults is +/-3.9 percentage points at a 95 percent confidence interval. The design effect is 2.02, making the adjusted margin of error +/- 5.5 percentage points. Thus, if 50 percent of New Jersey adults in this sample favor a particular position, we would be 95 percent sure that the true figure is between 44.5 and 55.5 percent (50 +/- 5.5) if all New Jersey adults had been interviewed, rather than just a sample.
Sampling error does not take into account other sources of variation inherent in public opinion studies, such as non-response, question wording, or context effects.
This online survey was fielded by Ipsos. Ipsos is an independent market research company controlled and managed by research professionals. Visit www.ipsos.com/en-us to learn more about Ipsos’ offerings and capabilities.
Weighted Online Sample Characteristics
629 New Jersey Adults
Male | 47% |
| Democrat | 41% |
| 18-34 | 25% |
| HS or Less | 34% |
| White | 59% |
Female | 53% |
| Independent | 38% |
| 35-49 | 26% |
| Some College | 25% |
| Black | 11% |
|
| Republican | 20% |
| 50-64 | 28% |
| College Grad | 24% |
| Hispanic | 19% | |
|
|
|
|
|
| 65+ | 21% |
| Grad Work | 17% |
| Other | 11% |
Telephone + Online Combined Probability Sample Methodology
The entire survey was conducted between March 7 and March 22, 2019 with a combined total sample of 1,250 New Jersey adults, 18 or older. Distribution of the combined sample is as follows:
Reached on Cell: 30%
Reached on LL: 20%
Reached online: 50%
All surveys are subject to sampling error, which is the expected probable difference between interviewing everyone in a population versus a scientific sampling drawn from that population. Sampling error should be adjusted to recognize the effect of weighting the data to better match the population. In this poll, the simple sampling error for 1,250 New Jersey adults is +/-2.8 percentage points at a 95 percent confidence interval. The design effect is 1.67, making the adjusted margin of error +/- 3.6 percentage points. Thus, if 50 percent of New Jersey adults in this sample favor a particular position, we would be 95 percent sure that the true figure is between 46.4 and 53.6 percent (50 +/- 3.6) if all New Jersey adults had been interviewed, rather than just a sample.
Sampling error does not take into account other sources of variation inherent in public opinion studies, such as non-response, question wording, or context effects.
Weighted Combined Sample Characteristics
1,250 New Jersey Adults
Male | 47% |
| Democrat | 39% |
| 18-34 | 25% |
| HS or Less | 32% |
| White | 58% |
Female | 53% |
| Independent | 40% |
| 35-49 | 25% |
| Some College | 28% |
| Black | 11% |
|
| Republican | 22% |
| 50-64 | 29% |
| College Grad | 23% |
| Hispanic | 19% | |
|
|
|
|
|
| 65+ | 21% |
| Grad Work | 17% |
| Other | 11% |
National Survey Methodology
Interviews collected nationally come from a survey conducted by the Fairleigh Dickinson University Poll. A random sample was drawn of adults nationwide, including in Alaska and Hawaii, and interviews were conducted on landlines and cellphones between January 28 through February 13, 2019. Respondents were screened in order to interview an adult, 18 or older.
A total of 1000 interviews were administered by ReconMR in San Marcos, Texas. 296 interviews were conducted on landlines and 704 were conducted on cellphones by professionally trained interviewers using a CATI (Computer Assisted Telephone Interviewing) system. All interviews were conducted in English. Telephone numbers were purchased by ReconMR through Marketing Systems Group.
Results for the total sample have a margin of sampling error of +/- 4 percentage points, including the design effect.
Survey results are also subject to non-sampling error. This kind of error, which cannot be measured, arises from a number of factors including, but not limited to, non-response (eligible individuals refusing to be interviewed), question wording, the order in which questions are asked, and variations among interviewers. Thus, if 50 percent of adults in this sample favor a particular position, we would be 95 percent sure that the true figure is between 46 and 54 percent (50 +/- 4) if all adults had been interviewed, rather than just a sample.
Sampling error does not take into account other sources of variation inherent in public opinion studies, such as non-response, question wording, or context effects.
Weighting was applied to the sample to more accurately treat the respondents as representatives of the total population of the United States. 2019 estimates of the U.S. population by Claritas were used to weight the data. In this case, the proportions of three characteristics were used; Race, Age and Gender. Each respondent falls into one, and only one, set and no respondent is left out.
Weighted Sample characteristics
1000 adults nationwide
Male | 49% |
Female | 51% |
18-34 | 28% |
35-59 | 38% |
60+ | 28% |
Refused | 7% |
White | 57% |
Black | 11% |
Hispanic | 18% |
Other | 14% |
White | 57% |
Non-white | 43% |
[1] NCHS, National Health Interview Survey, 2012-2016; U.S. Census Bureau, American Community Survey, 2011-2015; and infoUSA.com consumer database, 2012-2016.
[2] Blumberg SJ, Luke JV. Wireless substitution: Early release of estimates from the National Health Interview Survey, July–December 2015. National Center for Health Statistics. May 2016.
[3] Blumberg SJ, Luke JV. Wireless substitution: Early release of estimates from the National Health Interview Survey, January-June 2018. National Center for Health Statistics. December 2018.
[4] NCHS, National Health Interview Survey, 2012-2016; U.S. Census Bureau, American Community Survey, 2011-2015; and infoUSA.com consumer database, 2012-2016.
[5] Blumberg SJ, Luke JV. Wireless substitution: Early release of estimates from the National Health Interview Survey, July–December 2015. National Center for Health Statistics. May 2016.
[6] Blumberg SJ, Luke JV. Wireless substitution: Early release of estimates from the National Health Interview Survey, January-June 2018. National Center for Health Statistics. December 2018.