Since we published our new estimates of the illegal immigrant population and my article in National Review on those estimates, a number of people have emailed me asking about the quality of the Census Bureau data we used. They wonder if the decline and then rebound in the number of illegal immigrants we show reflects a decline in data quality (more immigrants missed) and then an improvement (fewer missed), creating a seemingly larger falloff and rebound than was actually the case. The key things to keep in mind are that we did not estimate the illegal immigrant population in 2020, at the height of the pandemic, and that the government reports that the monthly data during Covid-19 was still of high quality.
As a reminder, our analysis was based on the monthly Current Population Survey, which is collected by the Census Bureau for the Bureau of Labor Statistics (BLS). We estimated the illegal population in January 2019, 2021, and 2022. We make no claims about the illegal population in 2020, at the height of the pandemic. What we can say is that the number of illegal immigrants at the start of 2021 was more than one million lower than at the start of 2019. And by the start of this year, the number had rebounded by more than one million. If there is any problem with the data in 2020, it would not directly impact our estimates.
As for data quality during the pandemic, the BLS reports that response rates to the CPS for much of 2020 and 2021 were lower than prior to Covid-19, though rates improved after hitting a low in June 2020. Nonetheless, in June 2020 the BLS stated that “Although the response rate was adversely affected by pandemic-related issues, BLS was still able to obtain estimates that met our standards for accuracy and reliability.” In January 2021, BLS reported an overall response rate to the CPS for that month of 78.2 percent. This really is not that much lower than the average 82.5 percent in the 12 months prior to the start of to the pandemic in March 2020. There is simply no reason to doubt the monthly CPS for January 2021 and 2022, upon which we based our estimate.
It is worth adding that BLS published a host of its standard employment figures throughout the pandemic based on the CPS. If the survey was off, then so are the nation’s unemployment rate, the reported labor force participation rate, and the number of people unemployed and employed. But, again, BLS states the numbers are still good. Of course, any survey has sampling error, which we report in our analysis.
To sum up, the government states that the data was good throughout the pandemic and we only use the data in 2021, by which time the response rates had recovered. Moreover, the government continued to publish statistics from the monthly CPS during the pandemic. Policy-makers from Congress to the Federal Reserve based policy in part on those numbers. All of this gives us confidence in our new CPS-based estimates of the illegal immigrant population in 2019, 2021, and 2022.