Posts by D'Vera Cohn

As the 2010 Census information-gathering phase winds down and the Census Bureau turns to quality-checking and data-processing, Director Robert Groves offered some statistics at a recent operational briefing to assess how the national count has gone thus far. One indicator, the quality of the address list, appears to have improved since the 2000 Census.  Another, the share of proxy interviews–information obtained from neighbors and building managers instead of the householders themselves–has worsened.

The foundation of a good census is having a complete list of addresses because Americans are counted at their homes or the other places they are living. The quality of the address list is important in aiding census-takers who head out on follow-up visits to people who did not return their mailed-out questionnaires.

During the recent non-response follow-up operation, Groves said, census-takers found fewer non-existent addresses on their rounds in 2010 than their counterparts had in 2000. In 2000, 6 million non-existent addresses were deleted from the list because census-takers could not find them. In 2010, 4.1 million were deleted. During follow-up visits, census-takers also are supposed to look for addresses that are not on the official list, so they can be added. In 2010, Groves said, “we had fewer adds proportionately” compared with 2000, although he said this is not as much of a “hard quality indicator” because it could mean that census-takers did not follow procedures for including new addresses.

On another quality measure, Groves said census-takers who were trying to collect information at addresses from which census forms were not received had to rely more heavily on neighbors and building managers than was the case during the 2000 Census. In 2010, about 22% of interviews were from proxies, not from the householders themselves, compared with 17% in 2000.  This is of concern because proxy data traditionally have been less accurate and complete than information that people provide about themselves.  Groves said “this fits the expectation we had with regard to the cooperation of the American public.” Some people were never home during repeated visits by census-takers; others refused to provide information about themselves.

In addition, Groves said census operations so far have been on schedule and “significantly under budget.” Previously, census officials had reported a better-than-expected mail participation rate–72% of occupied households returned their forms, the same as in the 2000 Census.

Getting under way now are a series of quality-check operations “to make sure we’ve gotten it right,” in Groves’ words. This page will have more information on these operations in a later posting.

What would happen if Americans were not required by law to respond to census surveys? This is of interest because Canadian government officials have decided to drop the mandatory long form in next year’s census and replace it with a voluntary household survey. All Canadian households will still be required to answer basic questions on the census short form.

The Census Bureau tested this idea a few years ago when it researched how response rates to the American Community Survey would change if survey response was not required. The American Community Survey, a monthly survey that has replaced the census long form, includes questions about topics that include educational attainment, commuting, citizenship, income and housing costs. The bottom line: There is a “significant drop in mail cooperation” when respondents are not required to respond, Census Bureau researchers reported. Read more

Statistics Canada has announced that the nation’s 2011 Census will include the same eight basic questions that were asked of everyone in the 2006 count, and that the mandatory long form will be replaced with a voluntary survey.

The census long form went to one-in-five households and had been part of the national census for 35 years. The voluntary National Household Survey will be sent to one-in-three households within a month after the May 2011 census is conducted. Government officials say they hope the larger mail-out will result in an adequate number of responses. The household survey will ask the same questions about citizenship, ethnicity, religion, income, work, housing and other topics that had been on the long form. However, it will not include a request for consent to release individual-level data after 92 years, which had been included on the long form.

The short form includes questions asking for the name, age and gender of each person living in each household, as well as each person’s relationship to “Person 1.” Among the relationship options are “same-sex married spouse” and “same-sex common-law partner.” For each person in the household, there also is this language question: “What is the language that this person first learned at home in childhood and still understands?” (Here is a link to the list of short-form questions.)

According to some news accounts, the long form is being replaced because a growing number of Canadians do not want to answer personal questions, but some statisticians are concerned that a voluntary survey will not achieve the same data quality as a mandatory one. Some genealogists have criticized the decision to stop releasing individual-level data after 92 years, saying that it will impose severe limits on historians and people seeking to do family research.

In a posting on his blog, Census Bureau Director Robert Groves says that census-takers are nearly done with knocking on doors of households from which 2010 Census forms were not received. As of June 28, 99.6% of the interviews were completed.

The bureau is conducting quality-assurance audits to make sure the interviews were conducted correctly (see this report about 10,000 households in Brooklyn whose information will be redone because two managers allegedly used online databases to fill in census forms rather than contacting the householders directly). Additional quality-assurance operations will examine the status of addresses deemed to be vacant on April 1, Census Day; addresses that could not be found and were recommended for deletion from the address list; and addresses added too late to be visited by census-takers during the non-response follow-up phase.

A new report on childless women from the Pew Research Center uses data from the Current Population Survey to track recent trends and describe this group’s demographic characteristics. The report finds that childlessness among 40-44-year-old women has risen in all racial and ethnic groups, and most education levels, but has declined over the past decade among women with advanced degrees. Highly educated women still are the most likely to be childless.

The Census Bureau today released 2009 population estimates for cities, villages, boroughs and minor civil divisions that will be the last such numbers published for these incorporated places before the 2010 Census results are available.

Here is the Associated Press take on these estimates, and here is a first look from USA Today. The themes of their coverage include growth in Texas and decline in the Rust Belt.

The Census Bureau is clearing its data cupboard to make room for results of the 2010 Census. Today, the bureau released 2009 state and county housing unit estimates, the last ones before decennial results are compiled.

Last week, the bureau released population estimates by age, sex, race and Hispanic origin for the nation, states and counties.  The baseline for these estimates is the 2000 Census, updated with data from the American Community Survey and recent government records such as birth and death certificates, immigration statistics and building permits. The reference date for these estimates is July 1, 2009.

All sets of estimates can be found on the Census Bureau’s population estimates page.

Government leaders in India have agreed that the nation’s 2011 census could include a tally of castes, the complex structure of traditional social classes that last were officially measured in 1931. Those caste numbers are the basis of quotas for government employment and university enrollment, and help determine spending on social welfare programs. A council of government ministers is now developing a plan that may implement the count.

As this Associated Press story indicates, the caste system is not as dominant as it once was, but still has clout. The proposal to add the caste question to the national census remains controversial, according to a Global Post account.

Facing similar obstacles of cost and people’s reluctance to participate in national enumerations, some European countries are trying innovative ways to count their populations, according to an article on census-taking in Europe published (in English) by the Institut national d’études démographiques (INED). Among the new methodologies are expanded use of administrative records from municipal population registers and information collection from ad hoc or existing sample surveys.

The article cites the U.S. Census Bureau’s American Community Survey as one example of a new way of gathering demographic, social and economic data about households. The Census Bureau confronts similar problems to those of European countries, in the form of growing costs and increased public reluctance to participate. The Census Bureau makes limited use of  administrative records to collect population data, and has done research into expanded uses, including an experiment during the 2000 Census. Although the results were not definitive due to the limited nature of the experiment, researchers said use of administrative records has great potential in a number of realms.

Census Bureau data can help answer the question of how likely it is that a long-lasting marriage, such as the 40-year-union of Al and Tipper Gore, will come to an end.

Only a small share of long-duration marriages end in divorce each year, but the likelihood that a first marriage remains intact dwindles with each anniversary. According to a new Pew Research Center report on long-duration marriages and divorce, only about half the first marriages begun in the early 1970s lasted until their 25th anniversaries.