skip to main content

Survey Methods

The 2017 Stress in America™ survey was conducted online within the United States by The Harris Poll on behalf of the American Psychological Association (APA) between Aug. 2 and 31, 2017, among 3,440 adults age 18+ who reside in the U.S. Interviews were conducted in English (n=3,187) and Spanish (n=253). Data were weighted to reflect their proportions in the population. Weighting variables included age, gender, race/ethnicity, education, region and household income. Propensity score weighting also was used to adjust for respondents’ propensity to be online. Hispanic respondents were weighted for acculturation taking into account respondents’ household language as well as their ability to read and speak in English and Spanish. Because the sample is based on those who were invited and agreed to participate in The Harris Poll online research panel, no estimates of theoretical sampling error can be calculated.

All sample surveys and polls, whether or not they use probability sampling, are subject to multiple sources of error, which are most often not possible to fully estimate and control, including sampling error, coverage error, error associated with nonresponse, error associated with question wording and response options, and post-survey weighting and adjustments. Therefore, The Harris Poll avoids the words “margin of error” as they are misleading. All that can be calculated are different possible sampling errors with different probabilities for unweighted, random samples with 100 percent response rates. These are only theoretical because no published polls – whether conducted by telephone or online - come close to the ideal probability sample given the sources of error previously noted. Because the sample is based on those who were invited and agreed to participate in an online research panel, no estimates of theoretical sampling error can be calculated.

expand all
Sample Size

Throughout this report different segments of adults are discussed. Demographic sub-groups of adults include and are defined below:

2017 Main Survey (n=3,440 total)

  • Gender: Male (n=1,376); Female (n=2,047)
  • Race/Ethnicity: White (n=1,088); Hispanic (n=810); Black (n=808); Asian (n=506); Native American or Alaskan native (n=206)
  • Generation: Millennials (18-38 years old) n=1,267; Xers (39-52 years old) n=767; baby boomers (53-71 years old) n=1,176; matures (age 72 or older) n=230
  • Poverty level: At or below 200 percent of the annual federal poverty guidelines (n=1,122); More than 200 percent of the annual poverty guidelines (n=2,087)
  • Income: Less than $50,000 (n=1,612); Greater or equal to $50,000 (n=1,615)
  • Region: East (n=772); Midwest (n=615); South (n=1,224); West (n=829)
  • Urbanicity: Urban: (n=1,367); Suburban: (n=1,472); Rural: (n= 601)
  • Chronic condition status: Yes (n=2,205); No (n=1,180)
  • Insurance status: Yes (n=3,112); No (n=328)
  • LGBT status: LGBT (n=237); Non-LGBT (n=3,129)
  • Parents: Parents (n=1,182); No children (n=2,258)
  • Political party affiliation: Democrat (n=1,454); Republican (n=698); Independent (n=672)
Race/Ethnicity Definition

The Harris Poll’s methods for asking about and categorizing race and ethnicity are in accordance with the approach taken by the U.S. Census Bureau1 which treats race and ethnicity as two separate and distinct categories, examined in two separate questions. Per the Census’ framework, ethnicity is categorized as either ‘Hispanic or Latino’ or ‘not Hispanic or Latino.’ Race is comprised of five categories: White, Black/African-American, Asian, Native American/Alaskan Native, Hawaiian Native or other Pacific Islander. The Census further describes that the concept of race reflects self-identification by people according to the race or races with which they most closely identify and that people who report themselves as Hispanic can be of any race.

Using the framework described above and the questions below, if a respondent identified as Hispanic at Q1, for the purposes of this research they were included in the Hispanic sub-group regardless of their responses to the subsequent questions which examined race. All other groups were identified based solely on their answers Q2. Very few indicated they were of mixed race or some other race. Those who did are included in the total sample but have been excluded from the racial/ethnic analysis as there were too few to analyze separately (1 percent of the total sample).

BASE: U.S. RESPONDENTS

Q1: Are you of Spanish or Hispanic origin, such as Latin American, Mexican, Puerto Rican, or Cuban?

  • Yes, of Hispanic origin
  • No, not of Hispanic origin
  • Decline to answer

BASE: U.S. RESPONDENTS

Q2: Do you consider yourself…?

  • White
  • Black
  • Native American or Alaskan native
  • Mixed racial background
  • Other race
  • Hispanic
  • African American
  • First Nation/Native Canadian
  • South Asian
  • Chinese
  • Korean
  • Japanese
  • Other Asian
  • Filipino
  • Arab/West Asian
  • Pacific Islander
  • Decline to Answer

BASE: OTHER RACE (Q2/6)

Q3: What other race do you consider yourself?

[TEXT BOX]

BASE: MIXED RACIAL BACKGROUND (Q2/5)

Q4: You indicated that you consider yourself of a mixed racial background. With which of the following racial groups do you most closely identify? Please select all that apply.

  • White
  • Black
  • Native American or Alaskan native
  • Mixed racial background
  • Other race
  • Hispanic
  • African American
  • First Nation/Native Canadian
  • South Asian
  • Chinese
  • Korean
  • Japanese
  • Other Asian
  • Filipino
  • Arab/West Asian
  • Pacific Islander
  • Decline to Answer
Poverty Level Definition

The proportion of respondents in poverty is calculated based on the Federal Poverty Guidelinesopens in new window. The calculation takes into account annual household income, as well as the number of persons living in the household. For the purposes of this research, poverty was defined as being at or below 200 percent of the federal annual poverty guidelines. For example, for a family of four is considered to be living in poverty if their annual household annual income is $49,200 or less.

LGBT Definition

Using the three questions below, LGBT was defined as those who indicated they were Transgender or do not identify as female, male or transgender (Q268); or who selected Male or Female at Q268 but did not select the same option at Q268B; or who consider themselves to be Lesbian, Gay, Bisexual, Queer, Pansexual, Asexual or Other sexual orientation (Q498). Non-LGBT was defined as those who identify as Male or Female exclusively (Q268) and sex assigned at birth (Q268B) matches their choice in Q268 and selected Heterosexual (Q498).

BASE: US RESPONDENTS

Q268: Are you…?

  • Male
  • Female
  • Transgender
  • Do not identify as female, male, or transgender

BASE: US RESPONDENTS

Q268B: What sex were you assigned at birth, on your original birth certificate?

  • Male
  • Female

BASE: SEXUAL ORIENTATION TO BE PRESENTED AND 18 OR OLDER

Q498: Of the following, which do you consider yourself to be?

  • Heterosexual (Straight)
  • Lesbian
  • Gay
  • Bisexual
  • Queer
  • Pansexual
  • Asexual
  • Other sexual orientation
  • Not sure
  • Decline to answer

Political Party Affiliation Definition

Using the question below, respondents were asked to select which political party for which they are currently registered.

BASE:  ALL QUALIFIED RESPONDENTS (Q99/1)

Q1554a: What political party are you currently registered as?

  • Democrat
  • Republican
  • Independent
  • Other
  • I am not registered
  • Decline to answer

1 https://www.census.gov/population/hispanic/about/faq.htmlopens in new window

Last updated: December 2023Date created: 2017

Contact APA Office of Public Affairs