Sampling and the Census: A Case against the Proposed Adjustments for Undercount

Sampling and the Census: A Case against the Proposed Adjustments for Undercount

Sampling and the Census: A Case against the Proposed Adjustments for Undercount

Sampling and the Census: A Case against the Proposed Adjustments for Undercount

Synopsis

In an attempt to address an inaccuracy at the national level, sampling would seriously undermine the reliability of census data at the state and local levels.

Excerpt

As we all know, the decennial census mandated by the Constitution is a matter of great importance. the census provides the basis for establishing political boundaries, including boundaries for state and local political districts as well as congressional districts. It also serves as a basis for fund allocation: not only federal funds, but state, local, and private funds are often distributed on the basis of census data. the census enables scholars, government officials, business people, planners, and citizens to understand trends and developments in individual communities as well as in the nation as a whole.

The census is not, and never has been, 100 percent accurate. It misses some people, though the two most recent censuses have apparently missed less than 2 percent of the total. the great issue facing us as the census for the year 2000 approaches is this: Will the effort to make the census more accurate by adjusting for undercount cause it instead to be less accurate?

The adjustment process involves the use of sampling, and the casual newspaper reader might get the impression that the debate is over the validity of sampling and its legality in conducting the census. the political and legal battle has taken that form. But the real scientific debate is not over sampling as a technique. Sampling is a wellestablished statistical tool with many very useful functions. This volume makes it clear that the critical debate is over the proposed adjustment method itself, not the use of sampling as such. As the author points out, even an otherwise valid statistical analysis tends to produce faulty results . . .

Search by... Author
Show... All Results Primary Sources Peer-reviewed

Oops!

An unknown error has occurred. Please click the button below to reload the page. If the problem persists, please try again in a little while.