{"id":104652,"date":"2022-04-07T13:57:34","date_gmt":"2022-04-07T18:57:34","guid":{"rendered":"https:\/\/alpha.pewresearch.org\/pewresearch-org\/2022\/04\/07\/black-americans-and-science-methodology\/"},"modified":"2024-07-22T11:09:38","modified_gmt":"2024-07-22T15:09:38","slug":"black-americans-and-science-methodology","status":"publish","type":"post","link":"https:\/\/alpha.pewresearch.org\/pewresearch-org\/science\/2022\/04\/07\/black-americans-and-science-methodology\/","title":{"rendered":"Methodology"},"content":{"rendered":"\n

Overview<\/h4>\n\n\n\n

The American Trends Panel (ATP), created by Pew Research Center, is a nationally representative panel of randomly selected U.S. adults. Panelists participate via self-administered web surveys. Panelists who do not have internet access at home are provided with a tablet and wireless internet connection. Interviews are conducted in both English and Spanish. The panel is being managed by Ipsos.<\/p>\n\n\n\n

Data in this report is drawn from the panel wave conducted from Nov. 30 to Dec. 12, 2021. A total of 14,497 panelists responded out of 22,612 who were sampled, for a response rate of 65%. This includes 9,964 respondents from the ATP and an oversample<\/a> of 4,533 Black or Hispanic Americans from Ipsos\u2019 KnowledgePanel. The cumulative response rate accounting for nonresponse to the recruitment surveys and attrition is 2%. The break-off rate among panelists who logged on to the survey and completed at least one item is 3%. The margin of sampling error for the full sample of 14,497 respondents is plus or minus 1.2 percentage points.<\/p>\n\n\n\n

Panel recruitment<\/h4>\n\n\n\n
\"Table<\/a><\/figure>\n\n\n\n

The ATP was created in 2014, with the first cohort of panelists invited to join the panel at the end of a large, national, landline and cellphone random-digit-dial survey that was conducted in both English and Spanish. Two additional recruitments were conducted using the same method in 2015 and 2017, respectively. Across these three surveys, a total of 19,718 adults were invited to join the ATP, of whom 9,942 (50%) agreed to participate.<\/p>\n\n\n\n

In August 2018, the ATP switched from telephone to address-based recruitment. Invitations were sent to a stratified, random sample of households selected from the U.S. Postal Service\u2019s Delivery Sequence File. Sampled households receive mailings asking a randomly selected adult to complete a survey online. A question at the end of the survey asks if the respondent is willing to join the ATP. Starting in 2020 another stage was added to the recruitment. Households that do not respond to the online survey are sent a paper version of the questionnaire, $5 and a postage-paid return envelope. A subset of the adults returning the paper version of the survey are invited to join the ATP. This subset of adults receive a follow-up mailing with a $10 pre-incentive and invitation to join the ATP.<\/p>\n\n\n\n

Across the four address-based recruitments, a total of 19,822 adults were invited to join the ATP, of whom 17,472 agreed to join the panel and completed an initial profile survey. In each household, the adult with the next birthday was asked to go online to complete a survey, at the end of which they were invited to join the panel. Of the 27,414 individuals who have ever joined the ATP, 11,704 remained active panelists and continued to receive survey invitations at the time this survey was conducted.<\/p>\n\n\n\n

The U.S. Postal Service\u2019s Delivery Sequence File has been estimated to cover as much as 98% of the population, although some studies suggest that the coverage could be in the low 90% range.[11. numoffset=”11″ AAPOR Task Force on Address-based Sampling. 2016. \u201cAAPOR Report: Address-based Sampling<\/a>.\u201d] The American Trends Panel never uses breakout routers or chains that direct respondents to additional surveys.<\/p>\n\n\n\n

About the Ipsos KnowledgePanel<\/h4>\n\n\n\n

The Ipsos KnowledgePanel (KP) is an online probability-based panel representative of the U.S. adult population. Households without internet connection are provided with a web-enabled device and free internet service. KnowledgePanel\u2019s recruitment process was originally based on a national RDD sampling methodology. In 2009, the panel switched to using an ABS methodology. Additional information about the recruitment, sampling and weighting procedures for the Ipsos KnowledgePanel are available here<\/a>.<\/p>\n\n\n\n

Sample design<\/h4>\n\n\n\n

The overall target population for this survey was non-institutionalized persons ages 18 and older, living in the U.S., including Alaska and Hawaii. It featured a stratified random sample from the ATP in which panelists were assigned to the first matching stratum in the following order: tablet households, foreign-born Hispanics, U.S.-born Hispanics, people not registered to vote, people with a high school education or less, foreign-born Asian Americans, people ages 18 to 34, non-Hispanic Black adults, people who use the internet weekly or less, non-volunteers and a final stratum comprised of any remaining panelists not assigned to any of the above. Panelists recruited Sept. 16 to Nov. 1, 2021, were selected with certainty. The remaining strata were sampled at rates designed to ensure that the share of respondents in each stratum is proportional to its share of the U.S. adult population to the greatest extent possible. Respondent weights are adjusted to account for differential probabilities of selection as described in the Weighting<\/a> section below.<\/p>\n\n\n\n

The ATP was supplemented with an oversample from the KnowledgePanel, in which all panelists who had previously identified as Black or African American, or Hispanic (including those who identify as Hispanic or Black in combination with another race) were included in the sample.<\/p>\n\n\n\n

Questionnaire development and testing<\/h4>\n\n\n\n

The questionnaire was developed by Pew Research Center in consultation with Ipsos. The web program was rigorously tested on both PC and mobile devices by the Ipsos project management team and Center researchers. The Ipsos project management team also populated test data that was analyzed in SPSS to ensure the logic and randomizations were working as intended before launching the survey.<\/p>\n\n\n\n

Incentives<\/h4>\n\n\n\n

All respondents were offered a post-paid incentive for their participation. Respondents could choose to receive the post-paid incentive in the form of a check or a gift code to Amazon.com or could choose to decline the incentive. Incentive amounts ranged from $5 to $20 depending on whether the respondent belongs to a part of the population that is harder or easier to reach. Differential incentive amounts were designed to increase panel survey participation among groups that traditionally have low survey response propensities.<\/p>\n\n\n\n

Ipsos operates an ongoing modest incentive program for KnowledgePanel to encourage participation and create member loyalty. The incentive program includes special raffles and sweepstakes with both cash rewards and other prizes to be won. Typically, panel members are assigned no more than one survey per week. On average, panel members complete two to three surveys per month with durations of 10 to 15 minutes per survey. An additional incentive is usually provided for longer surveys.<\/p>\n\n\n\n

Data collection protocol<\/h4>\n\n\n\n

The data collection field period for this survey was Nov. 30-Dec. 12, 2021. Postcard notifications were mailed to all ATP panelists with a known residential address on Nov. 30, 2021. <\/p>\n\n\n\n

Invitations were sent out in two separate launches: soft launch and full launch. Sixty ATP panelists and 526 KP panelists were included in the soft launch, which began with an initial invitation sent on Nov. 30, 2021. The ATP panelists chosen for the initial soft launch were known responders who had completed previous ATP surveys within one day of receiving their invitation. All remaining English- and Spanish-speaking panelists were included in the full launch and were sent an invitation on Dec. 1, 2021.<\/p>\n\n\n\n

All panelists with an email address received an email invitation and up to four email reminders if they did not respond to the survey. All ATP panelists that consented to SMS messages received an SMS invitation and up to four SMS reminders.<\/p>\n\n\n\n

\"Table<\/a><\/figure>\n\n\n\n

Data quality checks<\/h4>\n\n\n\n

To ensure high-quality data, the Center\u2019s researchers performed data quality checks to identify any respondents showing clear patterns of satisficing. This includes checking for very high rates of leaving questions blank, as well as always selecting the first or last answer presented. As a result of this checking, five ATP and three KP respondents were removed from the survey dataset prior to weighting and analysis.<\/p>\n\n\n\n

<\/a>Weighting<\/h4>\n\n\n\n
\"Table<\/a><\/figure>\n\n\n\n

The data was weighted in a multistep process that accounts for multiple stages of sampling and nonresponse that occur at different points in the survey process. First, each panelist begins with a base weight that reflects their probability of selection for their initial recruitment survey. These weights were then adjusted to account for each panelist\u2019s probability of being sampled to participate in this wave.<\/p>\n\n\n\n

Next, respondents were placed into groups defined by the cross-classification of panel (ATP vs. KnowledgePanel), Black identification and Hispanic identification. Within each group, the weights for each respondent were scaled to be proportional to that group\u2019s effective sample size. The groups were then recombined and the weights were poststratified so that the weighted proportions of non-Hispanic Black, Hispanic Black and other Hispanic adults matched that of the U.S. adult population.<\/p>\n\n\n\n

The weights were then further calibrated to align with the population benchmarks identified in the accompanying table and trimmed at the 1st and 99th percentiles to reduce the loss in precision stemming from variance in the weights. In a final step, the trimmed weights were again poststratified to ensure that the weighted proportion of non-Hispanic Black, Hispanic Black and other Hispanic adults matched that of the U.S. adult population. Sampling errors and test of statistical significance take into account the effect of weighting.<\/p>\n\n\n\n

Some of the population benchmarks used for weighting come from surveys conducted prior to the coronavirus outbreak that began in February 2020. However, the weighting variables for ATP members recruited in 2021 were measured at the time they were recruited to the panel. Likewise, the profile variables for existing panelists were updated from panel surveys conducted in July or August 2021. For KnowledgePanel respondents, many of the weighting variables were measured on this wave.<\/p>\n\n\n\n

This does not pose a problem for most of the variables used in the weighting, which are quite stable at both the population and individual levels. However, volunteerism may have changed over the intervening period in ways that make their 2021 measurements incompatible with the available (pre-pandemic) benchmarks. To address this, volunteerism is weighted to an estimated benchmark that attempts to account for possible changes in behavior.<\/p>\n\n\n\n

The weighting parameter is estimated using the volunteerism profile variable that was measured on the full American Trends Panel in 2021 but weighted using the profile variable that was measured in 2020. For all other weighting dimensions, the more recent panelist measurements were used. For ATP panelists recruited in 2021, the 2020 volunteerism measure was imputed using data from existing panelists with similar characteristics.<\/p>\n\n\n\n

The following table shows the unweighted sample sizes and the error attributable to sampling that would be expected at the 95% level of confidence for different groups in the survey.<\/p>\n\n\n\n

\"Table<\/a><\/figure>\n\n\n\n

Sample sizes and sampling errors for other subgroups are available upon request. In addition to sampling error, one should bear in mind that question wording and practical difficulties in conducting surveys can introduce error or bias into the findings of opinion polls.<\/p>\n\n\n\n

Dispositions and response rates<\/h4>\n\n\n\n
\"Table<\/a><\/figure>\n\n\n\n
\"Table<\/a><\/figure>\n\n\n\n

Adjusting income and defining income tiers<\/h4>\n\n\n\n

To create upper-, middle- and lower-income tiers, respondents\u2019 2020 family incomes were adjusted for differences in purchasing power by geographic region and household size. \u201cMiddle-income\u201d adults live in families with annual incomes that are two-thirds to double the median family income in the panel (after incomes have been adjusted for the local cost of living and household size). The middle-income range for the American Trends Panel is about $42,000 to $125,900 annually for an average family of three. Lower-income families have incomes less than roughly $42,000, and upper-income families have incomes greater than roughly $125,900 (all figures expressed in 2020 dollars).<\/p>\n\n\n\n

Based on these adjustments, 30% of respondents are lower income, 47% are middle income and 18% fall into the upper-income tier. An additional 6% did not offer a response to the income question or the household size question.<\/p>\n\n\n\n

For more information about how the income tiers were determined, please see here<\/a>.<\/p>\n\n\n\n

Focus groups<\/h4>\n\n\n\n
\"Table<\/a><\/figure>\n\n\n\n

Pew Research Center completed a series of focus groups from July 13-22, 2021. Six groups were conducted with Black Americans and another six groups were conducted with Hispanic Americans. The focus groups were coordinated by Research Explorers. Those with Black Americans were moderated by Lisa Gaines McDonald of Research Explorers, Inc. Those with Hispanic Americans were moderated by Martha Garma Zipper of MGZ Research.<\/p>\n\n\n\n

Each group discussion was held online for 90 minutes and included three to six men and women; there were a total of 28 Black American and 29 Hispanic American participants.<\/p>\n\n\n\n

Each group was designed to include younger and older age groups and people with higher and lower levels of education. Those with higher education levels included any who had a four-year college degree or a master\u2019s degree. Those with lower education levels included those with a two-year associate\u2019s degree or less education. Those currently working in professional roles in a STEM occupation were not eligible to participate.<\/p>\n\n\n\n

Groups with Black Americans included those living in the metropolitan areas of Atlanta, GA; Chicago, IL; Charlotte, NC; and Houston, TX. Groups with Hispanic Americans were conducted in English or in Spanish with those living in the metropolitan areas of Chicago, IL; Houston, TX; Phoenix, AZ; and Los Angeles, CA. The focus group design is shown in the table.<\/p>\n\n\n\n

The moderator guide is included here<\/a>. Discussions covered a wide range of topics including:<\/p>\n\n\n\n