Documentation: | ACS 2011 (5-Year Estimates) |
you are here:
choose a survey
survey
document
chapter
Publisher: U.S. Census Bureau
Survey: ACS 2011 (5-Year Estimates)
Document: | The 2007-2011 ACS 5-Year Summary File Technical Documentation |
citation: | Social Explorer; U.S. Census Bureau; American Community Survey 2007-2011 Summary File: Technical Documentation. |
Chapter Contents
The Census Bureau publishes data for 1-year, 3-year, and 5-year estimates, with population thresholds set for the 1-year and 3-year estimates to produce reliable data. Here is a brief comparison of the three types of estimates:
For more information on the ACS estimates, users are encouraged to visit the ACS website http://www.census.gov/acs/www/guidance_for_data_users/estimates/.
1-year Estimates | 3-Year Estimates | 5-Year Estimates |
|
|
|
|
|
|
|
|
|
For more information on the ACS estimates, users are encouraged to visit the ACS website http://www.census.gov/acs/www/guidance_for_data_users/estimates/.
For data quality and geographic reasons, some tables are published with specific geography restrictions. For example, the table B05001-PR, Citizenship Status in Puerto Rico, is produced for Puerto Rico only, and the table B08501, Means Of Transportation To Work By Age For Workplace Geography, is only produced for the work place geographies. Appendix E has a complete list of tables and their geography restrictions, and Appendix F has a complete list of ACS 3-year published summary levels and components. Other examples include the quality measures tables (the B98 series) and detailed occupation tables.
Some data values represent unique situations where either the information to be conveyed is an explanation for the absence of data, represented by a symbol in the data display, such as "(X)", or the information to be conveyed is an open-ended distribution, such as 115 or greater, represented by 115+.
The following special data values can appear in the ACS Summary File table as an explanation for the absence of data:
A missing string indicates that the estimate is unavailable. (This appears in the estimates and margins or error files as two commas adjacent to each other without anything between them, or if the last cell in a data file is filtered then you get a comma followed immediately by a carriage return or EOF.) A missing value indicates when an estimate is missing because of filtering for geographic restrictions, coefficients of variations (CV), or was removed due to the Disclosure Review Board's (DRB) requirements. For more detail on filtering, please see Appendix C.5.
A dot indicates when the estimate has no sample observations or too few sample observations. In the margin of error files, this value could also indicate that the margin of error is unavailable for a median estimate that has been replaced with a jam value.
A "0" entry in the margin of error column indicates that the estimate is controlled. A statistical test for sampling variability is not appropriate. This is similar to the "*****" symbol used in American FactFinder.
This indicates that an estimate does not contain a Margin of Error. Tables B00001, B00002, and tables starting with B98 and B99 do not have margin of error (MOE) associated with them. The MOE calculations are set to -1 for these tables.
The following is a listing of the jam values for medians. For example, if there is an estimate of "2499" for table B10010, then it does not indicate a dollar amount. It means that the median is somewhere below 2,500 and thus isn't calculated.
The following special data values can appear in the ACS Summary File table as an explanation for the absence of data:
- Missing Value = ""
A missing string indicates that the estimate is unavailable. (This appears in the estimates and margins or error files as two commas adjacent to each other without anything between them, or if the last cell in a data file is filtered then you get a comma followed immediately by a carriage return or EOF.) A missing value indicates when an estimate is missing because of filtering for geographic restrictions, coefficients of variations (CV), or was removed due to the Disclosure Review Board's (DRB) requirements. For more detail on filtering, please see Appendix C.5.
- Dot = "."
A dot indicates when the estimate has no sample observations or too few sample observations. In the margin of error files, this value could also indicate that the margin of error is unavailable for a median estimate that has been replaced with a jam value.
- Zero = "0"
A "0" entry in the margin of error column indicates that the estimate is controlled. A statistical test for sampling variability is not appropriate. This is similar to the "*****" symbol used in American FactFinder.
- Negative 1 = "-1"
This indicates that an estimate does not contain a Margin of Error. Tables B00001, B00002, and tables starting with B98 and B99 do not have margin of error (MOE) associated with them. The MOE calculations are set to -1 for these tables.
- Jam Values for Medians
The following is a listing of the jam values for medians. For example, if there is an estimate of "2499" for table B10010, then it does not indicate a dollar amount. It means that the median is somewhere below 2,500 and thus isn't calculated.
Jam Value | Actual Meaning | Use for Medians |
0 | 1 or less | Age, Duration of Marriage |
9 | 9.0 or more | Rooms |
10 | 10.0 or less | Gross Rent as Percentage of Income, Owner Costs as Percentage of Income |
50 | 50.0 or more | Gross Rent as Percentage of Income, Owner Costs as Percentage of Income |
99 | 100 or less | Rent, Gross Rent, Selected Monthly Owner Costs, Monthly Housing Costs |
101 | 101 or more | Duration of Marriage |
116 | 115 or more | Age |
199 | 200 or less | Tax |
1001 | 1,000 or more | Selected Monthly Owner Costs |
1939 | 1939 or earlier | Year Built |
1969 | 1969 or earlier | Year Moved In |
2001 | 2,000 or more | Rent, Gross Rent |
2005 | 2005 or later | Year Built, Year Moved In |
2499 | 2,500 or less | Income, Earnings |
4001 | 4,000 or more | Selected Monthly Owner Costs, Monthly Housing Costs |
9999 | 10,000 or less | Value |
10001 | 10,000 or more | Tax |
200001 | 200,000 or more | Income |
250001 | 250,000 or more | Income, Earnings |
1000001 | 1,000,000 or more | Value |
B00001, B00002, B98001, and B98002 are sample counts, not estimates, and do not have margin of error (MOE) associated with them. Tables in series B99* imputation tables and B98* (except B98001 and B98002) quality measure tables do not provide margin of error calculations. The margin of error calculations are set to -1 for these tables.
There are a few special rules on how certain margin of error are determined for ACS estimates. The accuracy of the estimate (decimal place) within the detailed tables determines how many digits the margin of error is rounded.
There are a few special rules on how certain margin of error are determined for ACS estimates. The accuracy of the estimate (decimal place) within the detailed tables determines how many digits the margin of error is rounded.
Filtering rules, based on statistical reliability of the survey estimates, are used because certain geographic areas contain detailed tables include estimates whose level of reliability is unacceptable. The data release rules for the American Community Survey data tables include the following.
Every base table consists of a series of estimates. If more than half the estimates are not statistically different from 0 (at a 90 percent confidence level), then the table fails. Each estimate is subject to sampling variability that is summarized by its standard error. Dividing the standard error by the estimate yields the coefficient of variation (CV) for each of the estimates. (If the estimate is 0, a CV of 100 percent is assigned.) To implement this requirement for each table at a given geographic area, CVs are calculated for each of the table's estimates, and the median CV value is determined. If the median CV value for the table is less than or equal to 61 percent, the table passes for that geographic area; if it is greater than 61 percent, the table fails. Tables that are too sparse will fail this test. In that case, the table will not be published for that geographic area. Whenever a table fails, a simpler table that collapses some of the detailed lines together can be substituted for the original, more detailed table. The rules are then applied to the simpler table. If it passes, the simpler table is released. If it fails, none of the estimates for that particular table is released for this geographic area. These rules are applied to single-year period estimates and multi-year period estimates based on three years of sample data.
Every base table consists of a series of estimates. If more than half the estimates are not statistically different from 0 (at a 90 percent confidence level), then the table fails. Each estimate is subject to sampling variability that is summarized by its standard error. Dividing the standard error by the estimate yields the coefficient of variation (CV) for each of the estimates. (If the estimate is 0, a CV of 100 percent is assigned.) To implement this requirement for each table at a given geographic area, CVs are calculated for each of the table's estimates, and the median CV value is determined. If the median CV value for the table is less than or equal to 61 percent, the table passes for that geographic area; if it is greater than 61 percent, the table fails. Tables that are too sparse will fail this test. In that case, the table will not be published for that geographic area. Whenever a table fails, a simpler table that collapses some of the detailed lines together can be substituted for the original, more detailed table. The rules are then applied to the simpler table. If it passes, the simpler table is released. If it fails, none of the estimates for that particular table is released for this geographic area. These rules are applied to single-year period estimates and multi-year period estimates based on three years of sample data.
The estimates in the summary files are stored using standard notation instead of in scientific notation. The estimates are stored as whole numbers. The largest estimate in a Summary File contains 14 digits.
There are eight tables with more than the maximum 245 cells that cannot fit into a single sequence, so each of these tables is broken into multiple sequence files. The table below shows the tables that contain multiple sequences:
Table ID | Table Title | Sequences |
B24121 | Detailed Occupation By Median Earnings In The Past 12 Months For The Full-Time, Year-Round Civilian Employed Population 16 Years And Over | 81,82,83 |
B24122 | Detailed Occupation By Median Earnings In The Past 12 Months For The Full-Time, Year-Round Civilian Employed Male Population 16 Years And Over | 84,85,86 |
B24123 | Detailed Occupation For The Full-Time, Year Round Civilian Employed Population 16 Years And Over | 87,88,89 |
B24124 | Detailed Occupation For The Full-Time, Year Round Civilian Employed Male Population 16 Years And Over | 90,91,92 |
B24125 | Detailed Occupation For The Full-Time, Year Round Civilian Employed Male Population 16 Years And Over | 93,94,95 |
B24126 | Detailed Occupation For The Full-Time, Year Round Civilian Employed Female Population 16 Years And Over | 96,97,98 |
The last six tables on the list are only produced at the United States national level (summary level 010), and the files for these sequences will be blank for all other summary levels.