Transcription

ACS 2005 Summary File: Technical Documentation PrototypeAmerican Community Survey OfficeU.S. Census BureauAmerican Community Survey Summary FileVersion 1Issue Date: February 14, 2007Page 1 of 84

TABLE OF CONTENTSCHAPTERS12345678Abstract . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3How to Use the ACS Summary File. . . . . . . . . . . . . . . . . . . . . . . . . 9Subject Locator . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16Summary Level Sequence Chart. . . . . . . . . . . . . . . . . . . . . . . . . . . 62List of Detailed Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 65Data Dictionary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 67Accuracy of the Data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 69User Updates . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 70APPENDICESABCDEFGHIACS Geographic Terms and Concepts . . . . . . . . . . . . . . . . . . . . . . 71Subject Definitions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 75Data Collection and Processing Procedures . . . . . . . . . . . . . . . . . . 76Questionnaire . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 77Data Products and User Assistance . . . . . . . . . . . . . . . . . . . . . . . . 78Maps . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .79Code Lists . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 80Examples of Standard Error Calculations . . . . . . . . . . . . . . . . . . . 81Sample SAS Programs . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 84American Community Survey Summary FileVersion 1Issue Date: February 14, 2007Page 2 of 84

Chapter 1AbstractCONTENTSCitationType of FileSubject ContentGeographic ContentDocument OverviewUser UpdatesCITATIONU.S. Census Bureau, American Community Survey 2005 Summary File: TechnicalDocumentation.TYPE OF FILESummary statistics.SUBJECT CONTENTThe American Community Survey (ACS) is the largest household survey in the UnitedStates, with an annual sample size of about 3 million addresses. Every year the ACSsupports the release of single-year estimates for geographic areas with populations of65,000 or more.This release of the American Community Survey Summary File (ACS-SF) is a prototypeusing the 2005 detailed tables (a.k.a. “base tables”). The Census Bureau ACSprogramming staff plans to begin implementation of the production summary file seriesno later than December 2007. This prototype of the ACS-SF is meant to provide datausers with an early version of the ACS-SF. We encourage data users to providecomments on this prototype to help us design and implement the full version of the ACSSF. Please send any comments you have via email to: [email protected] 2007 we may issue updates and corrections to this prototype ACS-SF. Wewill keep users aware of these updates via the ACS Alert from the ACS website:www.census.gov/acs/www.The ACS-SF contains the sample data, which is information about the characteristics oflocal communities compiled from the questions asked of a sample of people and housingunits. The topics listed below are covered by the ACS and focus on demographic, social,housing, and economic characteristics and cover a broad spectrum of geographic areas inthe United States and Puerto Rico.American Community Survey Summary FileVersion 1Issue Date: February 14, 2007Page 3 of 84

Demographic:o Sexo Households by typeo Relationshipo Ageo Raceo Hispanic originSocial:oooooooSchool enrollmentFertilityVeteran statusU.S. citizenship statusMartial statusYear of entryGrandparents caring for childrenoooooooEducational attainmentResidence one year agoDisability statusLanguage spoken at homePlace of birthAncestryWorld region of birth of foreign bornEconomic:ooooEmployment statusClass of workerIndustryPoverty statuso Commuting to worko Income and benefitso OccupationHousing:oooooooHousing occupancyUnits in structureNumber of roomsHouse heating fuelOccupants per roomMortgage status and costsYear householder moved into unitoooooooHousing tenureYear structure builtNumber of bedroomsHousing valueVehicles availableUtility costGross rentThe statistics produced from the ACS describe the characteristics of population andhousing in the United States and Puerto Rico. The Census Bureau uses the data collectedby the ACS to create estimates and variances, which are termed statistics, for thesecharacteristics. The ACS releases statistics in several forms – totals, proportions,percentages, means, medians, averages, and ratios. There are three sets of data files inidentical format with one field per estimate. One file contains the estimates, another filecontains the standard errors, and the third file contains the margin of error.The ACS-SF contains a total of 1207 unique detailed tables (a.k.a. “base tables”). Ofthese tables, ID’s beginning with the letter “C” are collapsed versions of tables (i.e. thesetables have fewer detailed cells). These detailed tables include both U.S. and Puerto Ricopopulation and housing characteristics for the housing unit population and for a limitedAmerican Community Survey Summary FileVersion 1Issue Date: February 14, 2007Page 4 of 84

list of race and Hispanic or Latino groups. Population and housing items may be crosstabulated. Selected aggregates and medians are also provided. A complete listing ofsubjects in this file is found in the section, “Subject Locator”.GEOGRAPHIC CONTENTThe ACS Summary File includes all detailed tables for all geographies published by the2005 ACS. The main directory of the ACS-Summary File's FTP server(ftp://www2.census.gov/acs/summaryfile) contains documentation on using the ACS-SFand 54 subdirectories, for the United States, the 50 states, the District of Columbia, andPuerto Rico. The tables are identical for all files, but the geographic coverage differs.This abstract lists the most frequently accessed geographic levels. The “Summary LevelSequence Chart” section outlines the hierarchical and inventory geographic summaries intheir entirety. Two summary level sequence charts are provided: one for the state filesand one for the final national file.State FilesACS-SF for states, the District of Columbia, and Puerto Rico provides data for theseareas:o Stateo Countyo County subdivisiono PlaceACS-SF for states also has inventory (complete) summaries for the following geographicareas:o Stateo Countyo Placeo Congressional district (109th Congress)o Public Use Microdata Area (PUMA)National FilesThe ACS-SF national file provides summary data for the entire United States. The filestructure includes, but is not limited to, the following geographic entities:o United Stateso Regiono Divisiono Stateo Countyo County subdivisiono PlaceAmerican Community Survey Summary FileVersion 1Issue Date: February 14, 2007Page 5 of 84

ooooooMetropolitan statistical areaCombined statistical areaNew England City and Town Area (NECTA)Urban areaCongressional district (109th Congress)Public Use Microdata Area (PUMA)DOCUMENT OVERVIEWA brief summary of the chapters in the documentation is listed below:1. Chapter 1: Abstract contains an overview of the American Community Survey(ACS) and how to use the ACS Summary File technical documentation.2. Chapter 2: How to Use the Summary File gives users the background informationon the data tables. It also describes the naming conventions on the table names,and it gives a brief summary of the geographies.3. Chapter 3: Subject Locator is an index designed to help users quickly identify thetables in the summary file. This index is arranged in alphabetical order by thename of a subject.4. Chapter 4: Summary Level Sequence Chart has a detailed list on the geographiesand their summary level. The summary level is a three-character code that theACS uses for identifications on geographies. The summary level is used in theproduction of the ACS data.5. Chapter 5: List of Detailed Tables contains information on the file identification,the table’s identification number, title of the table, how many cells are the table,the start position for the table, and the sequence numbers.6. Chapter 6: Data Dictionary includes the table shells. A table shell is an overviewof the table including the table identification, the title, and the stubs (label for therows).7. Chapter 7: Accuracy of the Data provides data users with a basic understanding ofthe sample design, estimation methodology, and accuracy of the data.8. Chapter 8: User Updates informs data users about corrections, errata, and relatedinformation. Users can find unique characteristics, changes, or correctionsassociated with the data. American Community Survey Notes and Errata, whichcontain user updates for individual files, are located .American Community Survey Summary FileVersion 1Issue Date: February 14, 2007Page 6 of 84

Additional reference materials can be found in the appendices of this document:A. Appendix A gives a brief explanation of the Census Bureau’s common terms aswell as details on specific geographic areas presented in the AmericanCommunity Survey data products. Information on American Community Surveygeographic terms and concepts can be found in Appendix A.B. Appendix B identifies and defines 53 population variables, and 42 housingvariables to help users understand the results of the American Community Survey.These definitions include information on how the data were collected and howthey are presented in data products. Subject definitions can be found in AppendixB.C. Appendix C gives an overview on American Community Survey’s collectionmethods and procedures. Data Collection and Processing Procedures are locatedin Appendix C.D. The ACS questionnaire is in Appendix D.E. Information on data products and user assistance can be found in Appendix E.F. Appendix F contains maps of areas published by the 2005 ACS for the “nation”,“counties and places”, “PUMAs”, “Core Based Statistical Areas”, “the 108thCongressional District”, and “the 109th Congressional District”.G. Appendix G contains ACS code lists for “Ancestry”, “Hispanic Origin”,“Industry”, “Language”, “Occupation”, “Place of Birth, Migration, and Place ofWork”, “Race”, and “State”.H. Appendix H consists of the document “Examples of Standard Error Calculations”which contains examples based on the real data to demonstrate the use of theformulas referenced in the Accuracy of the Data Document in Chapter 7.I. FTP documentations can be found in Appendix I. The documents also include theReadMe file and sample SAS programs.USER UPDATESThe section on User Updates informs data users about corrections, errata, and relatedexplanatory information. These updates provide information about unique characteristics,changes, or corrections. However, sometimes this information becomes available too lateto be reflected in the tables or related documentation. American Community Survey userupdates are available on the Census Bureau’s Internet site . Users also can register toreceive user updates by e-mail by contacting Customer Services Center, MarketingServices Office, U.S. Census Bureau on 301-763-INFO ([email protected]).A problem was recently discovered in the collection of the 2005 travel time to work datafor Coweta County, Georgia. No other characteristics appear to have been affected. Thedata tables containing travel time estimates for Coweta County have been removed oraltered on the American FactFinder. A excel spreadsheet file will contain the list of allaffected tables along with a description of the action taken for each table. For each table,an explanatory note is provided for the users. This problem is currently under review andusers will be notified as soon as corrected data are available.American Community Survey Summary FileVersion 1Issue Date: February 14, 2007Page 7 of 84

As stated earlier, this summary file is a prototype and we welcome any user comments orsuggestions. Please send any comments or suggestions you have via email to:[email protected] Community Survey Summary FileVersion 1Issue Date: February 14, 2007Page 8 of 84

Chapter 2How to Use the ACS Summary FileCONTENTSINTRODUCTION . 9DATA FORMAT AND ACCESS TOOLS . 9FILE NAMING CONVENTIONS . 10Figure 2.1 Zip File Naming Convention Example. 11Figure 2.2 ASCII File Naming Convention Example. 11READING THE GEOGRAPHIC HEADER RECORD. 11Table 2.1 Geographic Header Record for the ACS Summary File. 12GEOGRAPHIC HIERARCHY PRIMER. 13Figure 2.3 Hierarchy of ACS Geographic Entities . 13RECORD IDENTIFICATION . 14Figure 2.4 Linking Geographic Header File to the Data Files. 14DATA STRUCTURE AND SEGMENTATION . 15Figure 2.5 Contents in an ACS Summary File Overview. 15INTRODUCTION“How to Use the ACS Summary File” is intended to be used as a guide for data users tothe American Community Survey (ACS) summary file and the documentation. Newusers should review this chapter before using the ACS Summary File.DATA FORMAT AND ACCESS TOOLSAll ACS Summary File (ACS-SF) are available in the .zip format, which is a compressedformat to reduce the file size. Users can download the .zip files through the File TransferProtocol (FTP) from the American Community Survey FTP site located at URL:ftp://www2.census.gov/acs/summaryfile/. The ACS-SF will need to be unzipped beforethey can be read. There are many free file extraction tools available on the World WideWeb. Users may perform keyword searches on search engines to see what is available.Before installing the software, be sure to check for the system requirements and select theappropriate download. Most file extraction tools also have tutorials available to guideusers on how to use the software. Generally, users will find the tutorial for a particulartool through the website that offers the download.Many operating systems today also have file extraction tools readily available in thesoftware. In this case, users may use the extraction tool that comes with the operatingsystem, and to find out how to unzip files in an operating system, users can perform aweb search or visit the operating system's official website.American Community Survey Summary FileVersion 1Issue Date: February 14, 2007Page 9 of 84

The FTP site has 54 directories for the data, which include the United States, the 50states, Washington D.C., Puerto Rico, and example SAS programs. In each directory,there is a geography file for the selected area, and the .zip files are then organized by thegeographies. For the user’s convenience, if users want the .zip files for all thegeographies under a particular directory, the file all state dc pr us .zip contains all thefiles in the directory. This allows the users to save time and not have to download eachindividual file.After unzipping the ACS-SF, three ASCII (plain text) files are available, of which onefile is for the estimates, one is for the margins of error and the last one is for the standarderrors. Each ACS-SF includes detailed tables for all of the geographies published in2005 and a geographic header record file in a fixed field; the geographic header recordfile's data portion includes a geographic link in the comma-delimited format. For moreinformation on the files and their purposes refer to the README file in the maindirectory on the FTP site.FILE NAMING CONVENTIONSThe .zip file names for all of the geographic header files follow a predefined structure.For the ACS-SF, all geography header files are named state abbreviation geo.20051y r . The state abbreviation is the United States Postal Service (USPS) two-characterabbreviation for the state. The geo field includes a 7-character geographic sequence, ofwhich the first three characters are always “000” and the last four characters incrementfrom 0001 0150. The “r” indicates the release time period of the product. The “r” fieldis only used after the initial file release, and any subsequent releases, the “r” field isreplaced by an alpha sequence letter (a, b, etc.). The extension .2005-1yr is used for boththe state files and the national file, for single year estimates. The naming convention willenable a user and/or a computer program to determine the contents of a file from itsname. See Figure 2.1 and Figure 2.2 for an overview of the file naming conventions.American Community Survey Summary FileVersion 1Issue Date: February 14, 2007Page 10 of 84

Figure 2.1 Zip File Naming Convention Exampleal0000001.2005-1yr.zip“al” forAlabama7-charactergeographic sequence(First 3 characters 000 arealways constant, and the last 4characters increment from0001 0150)Data published yearNumber of year(s) usedto compute the estimates(1, 3, or 5)Figure 2.2 ASCII File Naming Convention Exampleal0000001e.2005-1yr“al” forAlabama7-charactergeographic sequence(First 3 characters 000are always constant, and thelast 4 characters incrementfrom 0001 0150)Data published yearNumber of year(s) usedto compute the estimates(1, 3, or 5)Type of Datae-estimatesm-margins of errors-standard errorsREADING THE GEOGRAPHIC HEADER RECORDThe geographic header record (see Table 2.1 below) provides the data dictionaryreference name, description and size. A slightly different presentation of the geographicheader record appears in the identification section in Chapter 6: the Data Dictionary. InTable 2.1, the information in each summary level column is a guide to the presence orabsence of additional geographic information on that specific summary level. In eachrow of a particular geographic area code, there is a listing of the summary levels thatcontain the area code. For example, the “CTY” code does not contain information for thestate summary level 040; this is perfectly logical.American Community Survey Summary FileVersion 1Issue Date: February 14, 2007Page 11 of 84

Table 2.1 Geographic Header Record for the ACS Summary FileData DictionaryReference NameRECORD ICAREA CODESUSREGION CDIVISION CSTCTYMCDPLAINDNCBSAMETDIV MetroCSACNECTANECTANECTADIVUA UrCD2000BSTPUMA5SDELM SchSDSEC SchSDUNI SchURMEMI MetroMEMIRPCICD1990 19FIPSMCDFIPSPL Always equal to ACS Summary FileidentificationState postal abbreviation, "PR" or "US"Summary levelComponent identification numberStarts with "0000001" for the first record andincrements for each one61All Summary Levels2327791214All Summary LevelsAll Summary LevelsAll Summary LevelsAll Summary LevelsUS 1 or missingensus Regionensus DivisionFederal Information Processing Standardsstate codeCounty of current residenceMinor Civil Division of current residencePlace of current residenceAmerican Indian and Alaska Native AreaMetropolitan and Micropolitan StatisticalAreapolitan DivisionCombined Statistical AreaNew England City and Town CombinedStatistical AreaNew England City and Town AreaNew England City and Town Area Divisionban Area106 Congressional DistrictFederal Information Processing Standardss