Certain metrics are published with the American Community Survey (ACS) results to help the U.S. Census Bureau and data users assess the accuracy and reliability of the estimates released in the survey. For example, a statistic called the “margin of error (MOE)” is published with each estimate. The MOE indicates the likelihood that the ACS sample estimate is within a certain range (the MOE) of a true population value. For the ACS, MOEs are provided at a 90 percent confidence level, which means that the estimate is expected to contain the true or population value within a range defined by the associated MOE 90 percent of the time.
Data Planet has published MOE values for the last four 5-year releases of the American Community Survey (2013-2017, 2014-2018, 2015-2019, 2016-2020).
The American Community Survey (ACS) conducted by the United States Census Bureau provides estimates of the characteristics of the population over a specific time period. The ACS collects data from the 50 states, Washington, DC, and Puerto Rico, where it is called the Puerto Rico Community Survey. It is a continuous survey, in which each month a sample of housing unit addresses receives a questionnaire, with approximately three million addresses surveyed each year. Each year the survey produces data pooled to produce 1-year, 3-year, and 5-year estimates for geographic areas in the United States and Puerto Rico, ranging from neighborhoods to congressional districts to the entire nation. Data for each release of the 5-year estimates were collected over a 5-year period ending December 31 of the reference year (e.g., data in the 2014-2018 5-year estimates were collected January 1, 2014 - December 31, 2018). The statistics reported represent the characteristics of the population for the entire period vs. a specific year within that period.
The 5-year estimates are published for areas with populations of all sizes and are the most reliable and precise of the ACS period estimates as well as the most comprehensive, albeit the least current. (The 1-year and 3-year estimates provide data on areas with populations of 65,000+ and 20,000+, respectively. Note that the ACS 3-year estimates were discontinued with the 2011-2013 release.) The ACS estimates provide information about the social and economic needs of communities and are used to help determine how more than $400 billion in federal and state funds are distributed each year. It is conducted under the authority of Title 13, United States Code, Sections 141 and 193. Note that counts of the population are provided by the Census of Population and Housing conducted by the U.S. Census Bureau every 10 years; and official estimates of the population are derived from the previous census and from the Census Bureau’s Population Estimates Program.
Source: U.S. Census Bureau. American Community Survey. Accessed May 25, 2020, https://www.census.gov/programs-surveys/acs/technical-documentation/summary-file-documentation.html.
ATTN DATA PLANET SUBSCRIBERS: Be sure you are logged into your library's network in order to access the Data Planet database from the links provided in these guides.
Questions, comments, suggestions, technical support requests? Contact us at:
Email: onlinesupport@sagepub.co.uk
Website: https://us.sagepub.com/en-us/nam/dataplanet
ATTN Library Administrators: Please feel free to re-use and customize Data Planet guides for your institution.
As you explore the American Community Survey statistics in Data Planet, you will notice that the data values present an estimated statistic and a margin of error (MOE) statistic for most indicators. The MOE indicates the likelihood that the ACS sample estimate and the actual population value differ by no more than the value of the MOE within a specific confidence interval (more on the confidence interval below). Let's take a closer look at the MOE in Data Planet.
The default view of a chart using ACS data in Data Planet is a ranking view. For example in the chart below, two indicators have been selected (counts of males under age 6 with vs. without health insurance) for South Carolina counties. With two indicators selected, two items per county (represented by horizontal bars) appear in the chart—both of which are showing the number of persons, which is the number of male children under 6 years of age with and without health insurance coverage:
If you're only interested in the estimated count of population, this default view works for you. However, if you are interested in seeing the MOE data displayed, look at the far-left side of the criteria panel featuring the "Plot Options" and select "Margin of Error +/-" instead:
As mentioned above, the MOE indicates the likelihood that the ACS sample estimate and the actual population value differ by no more than the value of the MOE, at a certain confidence level. For the ACS, the Census Bureau sets this level at 90%, meaning the the estimate is expected to contain the true or population value within a range defined by the associated MOE 90 percent of the time.
Let's look at an example: We find in B19019 that the ACS estimate for Median Household Income in 3-person households reported in B19019 for the state of Delaware is $84,232 with an MOE of +/-$1,752:
By adding and subtracting the MOE from the estimate, we can calculate the 90 percent confidence interval for that estimate—meaning we expect the true population value to be within this range 90 percent of the time:
The chart below shows the calculated Upper Limit of the Confidence Interval, the Lower Limit of the Confidence Level, and the estimate: