The most recent estimates of the illegal immigrant population from the Center for Migration Studies (CMS) show 10.8 million illegal immigrants living in the country. The estimates, prepared by well-respected researcher Robert Warren, who is a pioneer in creating estimates of this kind, may be correct. However even if one accepts the estimates, it must remembered that new illegal immigrants continue to arrive in large numbers, but are offset by return migration, legalizations, and deaths, so the total illegal population may not grow or even decline. But it is still the case that the illegal population remains huge, and modest declines that are almost certainly within the margin of error are not an indication that the problem has been solved.
As we pointed out the last time the Center for Immigration Studies discussed CMS illegal estimates, there are several things to keep in mind:
- The CMS estimate is based in part on the American Community Survey (ACS) collected by the Census Bureau. The margin of error must be about ±106,000 for a population of this size if a 90 percent confidence level is used. The margin of error must be about ±127,000 if a 95 percent level is used. CMS never reports any of this information.
- CMS's 2013 estimate was 11 million, so a reasonable interpretation of their numbers is that there was no statistically significant change in the illegal population between 2013 and 2016. But this is not how CMS chooses to present their findings. Instead, they argue their newest estimate clearly represents a continuation of prior declines.
- The above discussion of a margin of error only deals with the statistical properties of the ACS, not the added error associated with trying to estimate illegal immigrants based on the survey. Warren's methodology requires him to calculate in-migration, out-migration, and mortality. He must also incorporate administrative data on lawful permanent residents, temporary non-immigrants (e.g. guestworkers and students), and others. All of this information introduces additional error, which he does not discuss.
- The Pew Research Center actually states in the figure that accompanies their own recent estimates of illegal immigrants that "the 2009-2016 change is not statistically significant." This a recognition that there is significant error in all estimates of illegal immigration.
- It may be worth adding that Pew's preliminary estimate for 2016 is 11.3 million, about 500,000 larger than that of CMS. Moreover, Pew finds a decline of 200,000 from 2009 to 2016, while CMS finds a decline of 1.1 million. (CMS's prior estimate for 2009 can be found here.) The rather sizable differences in the Pew and CMS estimates reflect different assumptions and errors (statistical and non-statistical) that are inherent in making estimates of this kind. This does not mean that Pew is correct and CMS is mistaken. Rather, there is significant error surrounding these numbers and it would be helpful if CMS reported that, rather than making the claim that relatively modest changes are definitive.
- By focusing only on the total size of the illegal population, CMS also likely leaves less knowledgeable readers with the mistaken impression that few new illegals are coming. But a stable or even declining total number of illegal immigrants does not mean that new illegal immigrants aren't coming. CMS, the Pew Research Center, and CIS have all estimated that 300,000 to 400,000 new illegal immigrants arrive each year, though the number coming is clearly lower than it was a decade ago. New arrivals are offset by deportations, return migration, legalizations, and deaths, so even if several hundred thousand new people successfully cross the border illegally or overstay a temporary visa each year, the overall size of the illegal population may not increase. In short, the illegal population remains huge, and modest declines that are almost certainly within the margin of error are not an indication that America has solved its illegal immigration problem.