By integrating a “big” dataset of Internet Speedtest® measurements from Ookla® with data on household incomes from the American Community Survey (ACS), we attempt to measure Internet speeds across income tiers. In the Ookla data, each measurement is technically rigorous but the sample frame is unknown. The ACS provides necessary information on income and Internet access from a known sample frame. Our likelihood combines these data and endogenizes selection effects to identify Internet speed distributions by income tier. We credibly identify the speed distribution for middle and high-income households. However, because the participation rate of low-income households in the Speedtest data is so limited, the speed estimates for these households are not identified.

Related Insights

Working Paper

A Comparative Analysis of Ookla Speedtest and Measurement Labs Network Diagnostic Test (NDT7)

A comparative analysis of two popular speed test tools: Ookla's Speedtest and Measurement Lab's Network Diagnostic Test.
May 24, 2022
Working Paper

What Can We Learn from Selected, Unmatched Data: Measuring Internet Inequity in Chicago

By integrating a “big” dataset of Speedtest Intelligence from Ookla that measures Internet performance and income data from the American...
May 05, 2022

A Tale of Three Datasets: Characterizing Mobile Broadband Access in the U.S.

We compare LTE coverage data from the FCC with a crowdsourced dataset from Skyhook for New Mexico.
Mar 01, 2022