High-dimensional data structures are the focus of this session. We use the adjective complex in place of high-dimensionality because the problems that we describe arise both from the measurement of thousands of attributes and from the intricate logical conditioning of the measurement process. Our paper provides answers to three questions associated with these data structures.

A significant structure always underlies data collected for scientific analysis. The question is, How do we reveal that structure to support statistical analysis? Time is an implicit dimension of a data structure. The design of a data collection is not always identical over time. Some of our discussion is devoted to how time is represented when measurements are asymmetric to different time points.

Others in Series

Working Paper

Applications of a Matched File Linking SIPP and Economic Data

July 1985

Attention is focused on uses of a SIPP file linked to micro-level data from the economic censuses an other data sets maintained by the Bureau of the Census.

Working Paper

Some Aspects of SIPP

April 1986

This paper provides background information and references to work in progress and work completed in a number of areas important to the SIPP.

Working Paper

Measuring the Frequency and Consequences of Job Separations

1989

The purpose of this paper is to provide a description of the frequency of voluntary and involuntary job separations among population subgroups.

Related Information

Survey of Income and Program Participation Working Papers

Page Last Revised - October 8, 2021

Some content on this site is available in several different electronic formats. Some of the files may require a plug-in or additional software to view.

Is this page helpful?
Thumbs Up Image

Yes

NO THANKS

255 characters maximum

255 characters maximum reached

Thank you for your feedback.
Comments or suggestions?

Top