The Stress in America™ survey was conducted online within the United States by Harris Poll on behalf of the American Psychological Association (APA) between Aug. 4-29, 2014, among 3,068 adults ages 18 and older 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 are discussed. Adults’ (n=3068 total) demographic subgroups include: gender (men: n=1204; women: n=1864); generation (millennials [18 to 35 years old]: n=720; Gen Xers [36 to 49 years old]: n=548; baby boomers [50 to 68 years old]: n=1324; and matures [69 years or older]: n=476); income (<$50,000: n=1499; >$50,000: n=1379); region (East: n=670; Midwest: n=776; West: n=637; South: n=984); and emotional support (yes: n=2042; no: n=649). In addition, the sample size of parents with a child under 18 in the household was 569.
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 postsurvey weighting and adjustments. Therefore, 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 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 Poll surveys. The data have been weighted to reflect the composition of the U.S. population ages 18 and older. 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.
In order to determine whether there were statistically significant differences in how various subgroups changed in perceptions over time, multiple linear regression was used to relate the following constructs to the overall stress rating (Q605): (1) time (eight waves over eight years); (2) main effect of the subgroup in question; and (3) interaction between subgroups and time. This analysis was conducted separately to make comparisons by gender, income and age. Significance of items (1), (2) and (3) above was determined by p-values smaller than .05. All values were smaller. All values but one (main effect for Gen Xers) were less than .01.
