A new survey released by the Center for Immigration Studies and conducted by Zogby International has received considerable attention since its release on December 29, 2009. However, the poll has serious methodological shortcomings, and results should be viewed with considerable caution.
Most significantly, the Zogby poll is not based on a scientific random sample of Americans but rather on an opt-in online panel survey. Even though Zogby attempts to balance the panel to make it representative of the U.S. population, the fact remains that this self-selected pool of respondents (i.e., the people who agree to and have the means to participate in online panels) differ significantly from the general population. Why does this matter? Without a random sample such as a random digit dial telephone poll, there is no way to say that the results of this poll accurately reflect opinions in the U.S. general population.
In addition to these serious sampling deficiencies, the question wording is problematic in several places. For example, the first question of the survey contains three consecutive sentences emphasizing the high number of “legal and illegal immigrants” currently residing in the U.S. This emphasis through repetition at the beginning of the poll has the effect of biasing survey respondents toward thinking that there are already too many immigrants living in the country. The second question also contains an additional sentence emphasizing the number of “illegal immigrants” (“there are currently estimated to be 11 to 12 million illegal immigrants in the U.S.”). Additionally, there are also other problematic question wording issues, such as unbalanced response options in forced-choice questions (e.g., in question #2), which bias respondents toward one answer.
Counterpoint: Results from the American National Election Study (ANES)
Other more scientific surveys, such as the American National Election Study conducted by the University of Michigan and Stanford University, have found significantly different results.
- The 2008 ANES found that 54% of Americans say immigration levels should either stay the same or should be increased, compared to 46% who said it should be decreased. Among Catholic Americans, numbers are a bit stronger for continued immigration rates: 61% say immigration levels should stay the same or increase, versus 39% who say they should decrease.
- The 2008 ANES also found that nearly half (49%) of Americans say the U.S. government should make it possible for illegal immigrants to become U.S. citizens, compared to only about one-third (34%) who oppose such a policy. Again, a higher number of Catholics support a legal path to citizenship (56%), compared to only 3-in-10 who oppose such a policy.
About the ANES: The American National Election Studies have been conducted at regular intervals (usually every two years) since 1948. It is the most comprehensive and rigorous national political survey of Americans that is publicly available. It has been based at the University of Michigan since its inception and has been run in partnership with Stanford University since 2005.