How many US Muslims? Our best estimate

Call it "the Muslim question." Since Sept. 11, America has grappled with public-policy decisions on security, immigration, and border control, racial profiling, and so on. When issues as sensitive as Muslim profiling are raised, it helps to have firm facts and figures.

But the drive for information has hit a roadblock: Neither the Census Bureau nor the Immigration and Naturalization Service is allowed to collect information rooted in religious faith. How can we debate such thorny problems when we have no official idea how many Muslims are in America?

To establish a credible figure, we must wade through a swamp of conflicting data. Opposing experts promote their own figures: 1 million to 7 million. These variations arise from differing approaches: estimates from individual surveys, indirect calculations based on data from places of worship, and proxy measures such as ancestry and country of origin. Each has drawbacks, but some are better than others.

The most prominent study using ancestry data put the Muslim population at 4 million. Using US Census Supplemental Survey data on ancestry, this study assumed that the number of Muslims in this country of a specific ancestry matched the proportion in their countries of origin. The study then adjusted for African-American Muslims and immigration and birth rates.

But estimates from ancestry data usually fail to account for deaths, emigration, or conversions. Also, immigrants often differ markedly from the general population in their countries of origin. Russian immigrants at the turn of the century were predominantly Jewish, not Russian Orthodox; immigrants from Lebanon were mainly Christian, not Muslim.

So if we can't get a reliable estimate this way, can we rely on statistics from places of worship? The most prominent example is the 2000 Mosque Study Project. This produced the estimate of 6 million to 7 million Muslims in America, the press's most-cited figure. The project surveyed individual mosques, finding that 340 adults and children participated at the average mosque and that another 1,629 were "associated in any way" with the average mosque's activities, yielding a figure of 2 million Muslims. The authors then adjusted the estimate to 6 million to 7 million overall to take into account family members and unaffiliated Muslims.

With impressive candor, the Mosque Study Project's lead researcher, Ihsan Bagby of Shaw University in North Carolina, conceded to The Associated Press that the number was a "guesstimation." That's because the project has methodological flaws.

Mosques (just like any other body) could have inflated their rolls by counting "members" who were no longer active. For example, the Los Angeles Times reported on Oct. 25 that "the Southern Baptist Convention conducted an audit of membership rolls a few years ago and found 25 percent of those listed had died or left the faith." Others may have intentionally inflated their estimates. Given the loose definition of who is "associated in any way" with a mosque's religious life, it is likely that some individuals were "associated" with more than one mosque, resulting in duplicate counting.

Moreover, almost 15 percent of Muslims in the Mosque Study Project sample came from only two mosques (each claimed almost 50,000 affiliates). The sample also appears biased toward larger mosques, distorting the size of the "average" mosque.

Surveying individuals might provide better data. Tom Smith of the National Opinion Research Center at the University of Chicago was recently commissioned by the American Jewish Committee to come up with a better estimate of Muslims in America. Smith drew his estimate from his center's most recent General Social Survey, which found 1.4 million adult Muslims. To estimate the number of Muslim adults and children, Smith took the General Social Survey data and made two assumptions: Every Muslim respondent represented a Muslim home and every non-Muslim respondent represented a non-Muslim home. This yielded an estimate of 1.7 million.

Case closed? Not quite. The City University of New York recently released its 2001 American Religious Identification Survey, asking members of 50,000 American households to identify their own religious affiliation, if any, and that of their spouse or partner. The survey estimated 1.1 million adult Muslims, further adjusted to 1.8 million adults and children.

Being drawn from wider, scientifically representative samples, the estimates provided by the American Religious Identification Survey and the General Social Survey both seem reasonable. Delicate policy decisions require information, but knowing how accurate that information is can be at least as important as having it at all. While a precise figure remains elusive, "2 million Muslims, give or take a few hundred thousand" appears to be America's most accurate number - for now.

Howard Fienberg is research analyst and Iain Murray is senior analyst with the Statistical Assessment Service (STATS), a nonpartisan research organization.