Census, Current Population Survey, and “questions”

|

The Census was all over the news yesterday, as changes to health insurance coverage questions raised concerns that quality of data could be degraded, especially with regard to the Affordable Care Act. Specifically, the Current Population Survey (CPS) will see changes to the wording of certain questions.

From the New York Times:

The Census Bureau, the authoritative source of health insurance data for more than three decades, is changing its annual survey so thoroughly that it will be difficult to measure the effects of President Obama’s health care law in the next report, due this fall, census officials said.

The changes are intended to improve the accuracy of the survey, being conducted this month in interviews with tens of thousands of households around the country. But the new questions are so different that the findings will not be comparable, the officials said.

Predictably, some folks weren’t happy, with either the changes or the timing. Others felt the need to address the idea of ACA-related “conspiracy theories” behind the change (and timing), while pointing out that the point may be moot if the American Community Survey is a better source than the CPS anyway.

Others, including Sarah Kliff writing for VOX, felt the criticism was premature:

The survey will make it difficult to compare the uninsured rate for 2012, the last year for the old questions, and 2013, the first year for the new questions. But making the change now means that 2013 and 2014 – the year before and after Obamacare’s big programs started – are using the same question set.

Finally, Census Director John Thompson had issued his own statement, defending the changes and the process that led them to making those changes:

The recent changes to the Current Population Survey’s questions related to health insurance coverage is the culmination of 14 years of research and two national tests in 2010 and 2013 clearly showing the revised questions provide more precise measures of health insurance through improved respondent recall.

This change was announced in September 2013 and implemented because the evidence showed that reengineering the questions provides demonstrably more accurate results. The Census Bureau only implements changes in survey methodology based on research, testing, and evidence presented for peer review.