Category Archives: The Census
Two interesting posts from Frontloading HQ:
Here is an NPR radio segment about the upcoming 2010 census.
I especially like this comment about the piece:
“It is always disheartening to witness otherwise intelligent, capable leaders engage in ideology induced idiocy as Mr. Gingrich did while talking about sampling and statistical methods.
Statistical procedures, which include simple frequency counts, can be manipulated or misinterpretted by the people who use them. The key is to have people use the tools at our disposal fairly in order to get an accurate count in 2010. But Mr. Gingrich voiced a distrust that the mathematical procedures are valid – a point that is unjustified scientifically but ideologically convenient.
Congress (and Mr. Gingrich himself) have benefited from the same “theoretical” statistical modeling and research sampling he opposes for this situation. Billions of dollars are appropriated by Congress on the trust that pilot studies, exploratory research, and statistical probabilities can be trusted – including defense projects, engineering projects, and everything NASA has ever done. More immediately, I’m sure that Mr. Gingrich takes medicines tested during research studies, not tested on everyone in the country. He trusts that the sampling is adequate in these cases… yet not appropriate for determining the population of the country.
I’ve recently become fascinated by politics of the Census, and, with a Census coming up in 2010, I think it’s a perfect topic for StatsInTheWild.
Politics and the census have been an issue for decades. Here is a piece from the New York Times from August 1909. In it, they cite a letter from President Taft to the Secretary of Commerce and Labor, requesting that politics be removed from the process of the Census. However, it looks as if Taft’s pleas for a non-partisian Census are not being heeded by todays politicians.
Recently, I posted an article about Obama nominating a new head of the Census who is an expert in sampling which has ruffled Republican feathers. Why would republicans be against sampling, a process that makes the Census more accurate and, ultimately, less expensive? Well, here is a very good article from 1998 explaining the Republican opposition to using sampling techniques for the Census.
The basic gist of the article is that government officials from the Clinton administration wanted to use sampling methods to account for the traditional undercount of minorities. Republicans likely blocked this from happening because the people who the Census tends to miss are people who tend to vote Democrat. Republicans (led by former speaker Newt Gingrich and Bobb Barr) argued that sampling was unconstituational and was a violation of the Census Act. Their argument held up in court, and no sampling was allowed to be used for the allocation of federal funds or redistricting.
Here is a good quote from the article if you don’t want to read the whole thing:
“The Bureau wants to do better. By using sophisticated data-gathering and statistical-sampling techniques to augment the direct count, it believes it can reduce the total and differential undercounts and save money to boot. The National Academy of Sciences agrees, as does about every statistician worth his or her salt. In 1990, the Census Bureau thought such sampling were the way to go, but Republican officials in the Bush Administration overruled the Bureau’s experts. The courts refused to intervene. ”