|
Activity Number:
|
89
- SPEED: Survey Methods, Transportation Studies, SocioEconomics, and General Statistical Methods Part 2
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, July 28, 2019 : 5:05 PM to 5:50 PM
|
|
Sponsor:
|
Survey Research Methods Section
|
|
Abstract #307936
|
|
|
Title:
|
Use of Matching Algorithms to Determine Unit Eligibility
|
|
Author(s):
|
Brandon Hopkins* and Kimberly Ault
|
|
Companies:
|
RTI International and RTI International
|
|
Keywords:
|
fuzzy matching;
sounds-like matching;
automation
|
|
Abstract:
|
Matching algorithms are often used to link data sources to build unit-level data files to develop a population frame for a study. Developing the rules to define a good match can be complex and challenging. This paper discusses how algorithms were used to identify unit level matches within schools and institutions to assist with developing the study population for an education survey. There were three algorithms used to match the current year to the previous years: (1) exact name matches, (2) fuzzy matches, and (3) phonetic matches. The resulting matches were grouped by types including one-to-one, one-to-many, many-to-one, and non-matches. The evaluation criteria for the quality of the match was determined by examining magnitude of differences in between the data sources. The evaluation showed the matches acquired through use of the algorithms were good, but improvements for future cycles would be beneficial. The data used for this presentation was simulated based on the original design of the education survey.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2019 program
|
