Methodology

The Stress in America™ survey was conducted online within the United States by Harris Interactive, Inc. on behalf of the American Psychological Association between Aug. 3 and 31, 2013, among 1,950 adults ages 18+ and 1,018 teens, ages 13 to 17, who reside in the U.S. Results were weighted as needed for age, sex, race/ethnicity, education, region and household income. Propensity score weighting also was used to adjust for respondents’ propensity to be online.

Throughout this report, different segments of adults and teens are discussed. For adults (n=1950 total), demographic subgroups include gender (men: n=847; women: n=1103); generation (Millennials [18- to 34-year-olds]: n=392; Generation Xers [35- to 48-year-olds]: n=379; Baby Boomers [49- to 67-year-olds]: n=808; Matures [68 years and older]: n=371); and region ([2013: East n=442; Midwest n=535; South n=578; West n=395]; [2012: East n=274; Midwest n=235; South n=282; West n=243]; [2011: East n=299; Midwest n=259; South n=389; West n=279]; [2010: East n=539; Midwest n=419; South n=640; West n=422]). Adults were also segmented by how many hours per night they sleep (fewer than eight hours: n=1374; at least eight hours: n=576), how often they exercise (less than once a week or not at all: n=795; once a week or more: n=1155) and their self-reported stress level (high stress [eight, nine or 10 on a 10-point scale]: n=386; low stress [one, two or three on a 10-point scale]: n=633). In addition, the sample size of parents with a child under age 18 in the household was 333.

Teens (n=1018) were segmented in similar ways including by gender (boys: n=432; girls: n=586); and age groups (younger teens [13- to 14-year-olds]: n=294; older teens [15- to 17-year-olds]: n=724). Additional segments for analysis included younger girls (n=160), older girls (n=426), younger boys (n=134), older boys (n=298), those with low reported stress in the past school year (n=174) or the past month (n=338), as well as those with high stress in the past school year (n=316) or past month (n=149). As with adults, the survey examined the amount of sleep teens get (fewer than eight hours on a school night [n=503]; at least eight hours on a school night [n=514]), as well as how often they exercise (less than once a week or not at all [n=216]; once a week or more [n=802]).

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 quantify or estimate, including sampling error, coverage error, error associated with nonresponse, error associated with question wording and response options, and post-survey weighting and adjustments. Therefore, Harris Interactive, Inc. avoids the words “margin of error,” as they are misleading. All that can be calculated are different possible sampling errors with different probabilities for pure, unweighted, random samples with 100 percent response rates. These are only theoretical because no published polls come close to this ideal.

Respondents for this survey were selected from among those who have agreed to participate in Harris Interactive, Inc. surveys. The data have been weighted to reflect the composition of the U.S. population ages 18+. Because the sample is based on those who were invited and agreed to participate in the Harris Interactive, Inc. online research panel, no estimates of theoretical sampling error can be calculated.

Measuring Stress: 10-Point Scale Versus Perceived Stress Scale

Since APA’s Stress in America research began, Americans’ stress levels over the previous month have been measured using a 10-point scale, where one means “no stress at all” and 10 means “a great deal of stress.” The average score has typically been reported. We have also reported the proportion who report “high” (eight, nine or 10 on the 10-point scale) or “low” stress (one, two or three on the same scale).

In 2013, the survey maintained the self-reported measure of stress using the 10-point scale described above. In addition, the survey included a 10-item scale, the Perceived Stress Scale (PSS), developed by Sheldon Cohen, PhD, a professor of psychology at Carnegie Mellon University.

10-point scale: On a scale of one to 10 where one means you have “little or no stress” and 10 means you have “a great deal of stress,” how would you rate your average level of stress during the past month?

PSS 10-item scale: In the last month, how often have you …? (very often, fairly often, sometimes, almost never, never)

  • Felt confident about your ability to handle your personal problems?
  • Felt that you were on top of things?
  • Been able to control irritations in your life?
  • Felt that things were going your way?
  • Felt nervous and stressed?
  • Been angered because of things that were outside your control?
  • Been upset because of something that happened unexpectedly?
  • Felt difficulties were piling up so high that you could not overcome them?
  • Found that you could not cope with all the things that you had to do?
  • Felt that you were unable to control the important things in your life?

Items were scaled on a 5-point scale ranging from zero (never) to four (very often). Of the 10 items, four items were worded in a positive direction, so they were reverse-scored. The responses to the 10 items were then summed to create a psychological stress score, with higher scores indicating greater psychological stress.

The results of the two approaches for measuring stress were compared. We found a high correlation between the two (.682), meaning that those who reported a high stress level on the 10-point scale also had a high stress level on the 10-item scale. The single item question appears to be an efficient assessment of stress.