Statistical Challenges in Linking a Retail Gasoline Price Survey with Commercial Data

• Activity Number: 662 - Statistical Challenges in Combining Survey and Administrative Data
• Type: Topic Contributed
• Date/Time: Thursday, August 2, 2018 : 10:30 AM to 12:20 PM
• Sponsor: Survey Research Methods Section
• Author(s): Maura Bardos* and Amerine Woodyard and Jeramiah Yeksavich
• Companies: Energy Information Administration and Energy Information Administration and Energy Information Administration
• Keywords: Record linkage; Commercial Data; GIS; Administrative Records; Establishment Survey; Total Survey Error

Abstract

As part of ongoing modernization efforts, the U.S. Energy Information Administration (EIA) is conducting research on utilizing third-party sources to supplement survey data. EIA is uniquely situated since a number of its surveys collect information that is also compiled and sold by commercial vendors. These commercial vendors can provide almost real-time frequency of data that when linked with surveys, have the potential to reduce respondent burden and enhance data products. However, there are statistical challenges including record linkage and evaluation of potential sources of error in commercial sources such as coverage error, specification error, measurement error, and missing data. EIA purchased price data from a commercial vendor for about 110,000 retail gas stations and also created a tool to obtain gas prices via a crowdsourced website. This paper examines the challenges in integrating data from these commercial sources with data collected from the Motor Gasoline Price Survey (EIA-878). EIA conducts this weekly mandatory survey to produce point-in-time gasoline price estimates by geographic area, grade, and formulation from a sample of retail gas stations