The National Academies

NCHRP 08-36/Task 135 [Completed]

Addressing Margins of Error in Small Areas of Data Delivered through the American Fact Finder or the Census Transportation Planning Products Program
[ NCHRP 08-36 (Research for the AASHTO Standing Committee on Planning) ]

  Project Data
Funds: $74,997
Research Agency: The RAND Corporation
Principal Investigator: Tom Krenzke (Westat)
Effective Date: 9/25/2015
Completion Date: 5/1/2017



As the Census Bureau has moved to the American Community Survey the sample size surveyed has shrunk dramatically when compared to the now discontinued Long Form.  After five years of data collection, small area data are delivered either through American Fact Finder or the Census Transportation Planning Products Program (CTPP).  When working with small, but sometime larger areas, margins of error (MOE) that are a large proportion of the estimate, and that may in some cases exceed the estimate itself, may be encountered. 


The American Community Survey (ACS) data is now the only source of large national data on Journey to Work and the huge amount of commensurate demographic data that accompanies it.  The ACS and CTPP are routinely used by planners at all levels of government to develop long range plans, validate and calibrate traffic models, and provide information to decision makers to deploy transportation dollars.  Inappropriate handling of the inherent vagaries of the data can negatively impact the quality of information used for decision-making.  Guidance on how best to address these issues is needed.


Project Objective


The objective of this research is to provide guidance on how to appropriately handle large MOEs that is tailored to the application of the data, e.g. long range planning or calibrating a travel demand model.  The guidance should also address how to communicate MOE when data are represented visually, e.g. in heat maps or pie charts, and when the use of ACS data is spread too thinly to constitute an appropriate use of the data.


Research Plan


The NCHRP is seeking the insights of proposers on how best to achieve the research objective.  Proposers should develop and include in their proposal a detailed research plan for accomplishing the project objective that can realistically be accomplished within the constraints of available funds and contract time.  Proposals must present the proposers' current thinking in sufficient detail to demonstrate their understanding of the issues and the soundness of their approach to meet the research objective.

The research plan should be divided into tasks, and the work proposed in each task must be described in detail.  The research plan should include a description of proposed deliverables for each task or group of tasks along with a detailed project schedule.  A technical memorandum should be delivered following the completion of each major task.  The research plan should include two web-enabled conference calls with the project panel: (1) a project kick-off conference call within 45 days of contract execution, and (2) a conference call mid-way through the project.  Final deliverables include (1) a final report that meets the project objectives and (2) a PowerPoint presentation with speaker notes that provides an overview of the research and its conclusions.

Links to the final products:






To create a link to this page, use this URL: http://apps.trb.org/cmsfeed/TRBNetProjectDisplay.asp?ProjectID=4078