Quality in a Census, Part 1

Print This Post Print This Post

Written by: Director Robert Groves

As we begin the last stages of the 2010 Census data collection, our thoughts are turning more and more to evaluating how the country did in this census.

I thought it might be good to talk a little about how censuses are usually assessed. There are some basic ideas that are crucial to any notion of statistical quality.

First, the basic quality criteria are simple. An oft-mentioned goal of the 2010 Census is “enumerating each resident of the US once, only once, and in the right place.” Thus, there are three basic threats to quality in a census: 1) failure to enumerate a person, 2) enumerating someone more than once, and 3) assigning an enumerated person to the wrong physical location. We also seek accurate reports of attributes of the persons enumerated (e.g., age, race/ethnicity).

Second, the quality of a census depends on its use. For example, the first use of the census is distribution of members of the House of Representatives based on population of states. The key quality of that use is whether we assigned counted persons to their appropriate state of residence. The next important use of the census is redistricting within states, based on counts of persons within blocks. For that use, we need accurate assignment to the correct block of their residence. (This is a much stricter quality hurdle than assignment to the correct state of residence.)

Third, uses based on count totals face tougher quality challenges than those for distributional purposes. For example, if the census count is used by a program to provide $2.17 for every person in an area, its allocations will be affected by every person not counted and every person counted twice. If there is an undercount, fewer dollars are allocated than intended. On the other hand, if a program allocates a fixed sum of funds, say $50 million to the states based on the proportion of the total population in each state, then getting the relative counts right is necessary. For example, if we fail to count exactly 1% of every state’s population, the relative share for each state in the census counts is the same as the relative share truly. But if one state is undercounted by 2% and another by 0.5%, the first is relatively harmed versus the second. (There are many uses of censuses that are distributional, like the apportionment of the House.) It’s easy to see, therefore, why there is great interest in the differential undercount for distributional purposes; that is, the extent to which different groups experience different levels of undercount or overcount in the census.

These are merely conceptual notions of quality, not measures of quality. I’ll talk about those in a later post.

Please submit any questions pertaining to this post to ask.census.gov

This entry was posted in Quality Assurance. Bookmark the permalink.

12 Responses to Quality in a Census, Part 1

  1. Valerie LaHart says:

    What a shame not everyone in the US will have a chance to be counted. I am sure our household is not alone in being ignored/overlooked with a census form. We could not receive one in the mail because we use a PO box, no one has come to see us nor has “a yellow bag with census information” been left on our door knob.
    I am very disappointed in this year’s census efforts. Your ads are misleading and in fact, a big lie.

  2. Disappointed says:

    Director Groves, the 2010 Census is the poster child for the old business maxim, “Fast, cheap, good–pick two.” The quality of every operation has been compromised by haste. The checks built into the system were compromised by the pressures to meet unrealistic deadlines.

  3. Donald says:

    A message to the Director:
    From an experienced enumerator, to his boss; I hope you’re listening. Yes, I can understand that you hope this 2010 Census will be better than all the others, and I understand how quality is so important, too, all the while trying to get the count as right as right can be. Balancing quality with quantity takes a lot of skill, doesn’t it? Problem is; as right as you’re trying to get it right now, revisiting so many of the already enumerated housing units over and over again as you are doing right now is not only draining your workforce of temporary enumerators, it’s too often turning the public against us as we revisit housing units that not long ago once responded freely to our visits. And all those helpful “proxies” we once relied on? They too are often annoyed of our return as well… “Can’t you get it right?” they keep asking. For all the housing units we did first visit, I thought we did a good job, Mr. Groves. And why are we now re-enumerating some of the same housing units who already mailed their original census forms back? That’s a question no one seems willing to answer. So if getting it right is your greatest concern, look where we haven’t looked before, but going back over and over again to those who have already responded isn’t going to make it any better than what it already is. If it isn’t broken, please don’t try to fix it, Mr. Groves. But if it is broken, it’s probably already too late to make it any righter than what it is right now. And it doesn’t hurt to look outside the box, either. Hey, you’ve had nine years to get ready to get this one right, haven’t you? Yet like many of the others; the one thing learned from past mistakes is that few have listened. It’s your army of census enumerators who have already marched to your orders and brought back the data that you asked for…under challenging sometimes difficult conditions. Trust me, Mr. Groves, working as a field enumerator was tough work as always again this year. Nonetheless, at least for me, I got it right once more.

  4. JHC says:

    Quality Assurance:
    In my two months plus working as an enumerator, I feel that alot of time well spent could give a more accurate count in inner city and transient areas. I really feel many of these areas are lacking true head counts for a variety of reasons. How do those in charge identify those areas and assign follow-up in the next few weeks could greatly effect local/state/national goverments.
    I feel that many of us working these areas could be of great help but I have a feeling we will never be asked to come back to work or asked for our input. Some AA’s I have worked may have counts 10% to 20% that were never reported because of property managers reluctance to give information and cenus workers time/management restraints to get a case closed. I think to get the count right people should be chosen who worked problem areas and also were good at getting good proxy information. A simple review of EQ’s can pinpoint those who did the job in phase I thoroughly and should be part to phase II. At $1,500 a head or $15,000 for 10 years makes a correct count in my state(NY) very important not to let any person slip through a crack in the count/system.
    Another area of concern is seasonal residents that spend some months in Southern/Western States in the winter and never get counted anywhere because of policy.

  5. tmp says:

    I returned my census form within days of receiving it. Today, a woman came to my door with a census form with my address on it, asking for more information. I’m wondering why my original form was not counted. I gave all the information that can legally be asked of me. All you need to know is how many people live in the home. It’s a waste of my tax dollars to have someone come to my home when I have already responded. I watched as she also went to 2 neighbor’s homes, who also returned their forms months ago.

  6. CLA says:

    I have visited addresses that have been visited numerous times before. Some residents have answered questionairs 2 to 3 times, who is KEEPING TRACK. A friend never sent his in, and never got a visit. Something is wrong with the system.

  7. DLS says:

    All of the information that can be legally asked of you is on the Census Form–including race, gender, age, etc.
    See http://www.factcheck.org/2010/03/just-the-facts-2010-census/

  8. Ron says:

    Just a few days ago, the population clock showed over 309 mill. Today, it shows only 300 mill. what happened to the 9 million? I think it was 2005,they made such a big deal in the news about hitting the 300 million mark, so that was wrong? Are we now at 300 or 309 million? which one is correct?

  9. Bill says:

    tmp, you stated “I gave all the information that can legally be asked of me. All you need to know is how many people live in the home.”
    Your understanding of what can be “legally asked” does not agree with the law (or, indeed with the law of the land… the Constitution). You’ve been paying attention to political crazies like Michelle Bachman and her ilk. Those wingnuts were either ignorant or lying when they claimed that the Constitution specifically enumerates questions that can be asked. You can read it here: (http://www.usconstitution.net/const.html). It says the census can ask whatever questions Congress authorizes it to ask. And it has.
    The “All you need to know…” portion of a statement is your opinion (with which I have no quarrel), but it has nothing to do with the law. So congratulations. You cost yourself tax dollars (in the form of necessitating a personal visit) by doing what you wanted to do instead of what you were legally obligated to do. And probably hassled one or more Census enumerators who didn’t need the irritation when they came to your door.

  10. Disappointed American says:

    I can guarantee that the Northern part of Missouri didn’t get counted correctly! As a enumerator myself, I was ordered by Kelly (our crew leader) to proxy each other on “what we thought” about households we couldn’t reach or were “scary places”. Or look up the address on the internet and just fill something in, because Steve (her boss) wanted binders turned in quicker. Alot of my neighbors wasn’t even contacted even though their block was supposedly finished and binder turned in. We were constantly told to “rush and make up” so that Steve could have his binder counts higher because we were going over budget. We would have daily meetings at a public cafe so we could check each others work and make changes so they didn’t get kicked back, because Kelly had a new job at the Moose Lodge and didn’t have time. The whole experience was sad to say very typical of our government, and BIG FAT JOKE! Signed Ashamed to be a enumerator!!

  11. Enumerator in the Field... says:

    You need to REPORT this problem to your LCO or maybe your Regional Census Office, see the Census Directors Blog, July 12th “Repairing a Problem….” to see what they found and did in New York. I’ve been working for the 2010 Census for all the operations as a Enumerator & CLA and some staff that where selected as FOS, CL’s should NEVER have gotten the job!!!! Thank goodness for us dedicated enumerator’s out in the filed trying to do the proper job we were trained for and according to the manuals….

  12. Paul A.Morales says:

    To whom it may concern I Paul A.Morales did the office remodel in Riverside,CA. 92505 and was never paid in full for my services. All my subcontractors are not getting paid also your office has rely hurt our local Americans.Your office was starting to operate in the office on the day they needed to start the job in their office. So why CAN YOU PLEASE PAY ME GOD BLESS!

Leave a Reply

Your email address will not be published. Required fields are marked *