Researchers using survey data must always deal with the problem of nonignorable non-response among the intended sample for a survey. Often, nothing more is known about a non-respondent individual or household other than the geographic location of their primary residence. However, this information can often be linked to the census sociodemographic characteristics of the approximate locality of each intended sample member. For example, in the absence of individual-specific data, some progress can be made in the task of sample selection correction by utilizing Census tract level information. We report upon the construction of a set of fifteen orthogonal factors that capture 88.7% of the variability across Census tracts in the 2000 Census. Since these factors are calculated using the universe of tracts, they may be interpreted as population measures, rather than sampling estimates. Our fifteen factors are available to other researchers, and can be accessed using a password available from the authors. In addition to their utility for survey sample selection corrections, this set of variables may also be useful as controls for neighborhood level heterogeneity in ordinary modeling contexts.
Download Info
To download:
If you experience problems downloading a file, check if you have the
proper application to
view it first. Information about this may be contained
in the File-Format links below. In case of further problems read
the IDEAS help
file. Note that these files are not on the IDEAS
site. Please be patient as the files may be large.
References listed on IDEAS Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.: