income between and within agencies. Each agency
Data at the Local Level
creates its own web site and its own data dissemi-
Assuming the statistical accuracy of the American
nation system with little or no regard for the user,
Community Survey is reasonable for small geograph-
who has to go to more than a dozen sites and learn
ical areas’ income, education, and employment data,
a dozen approaches to get a complete review of the
these data will significantly enhance one’s ability to
socioeconomic data of the United States. Indeed,
measure the effects of policy and social change. Yet,
if the user wants to integrate the data, it is much
there are many data series in which more local infor-
easier—but more expensive—to go to a private
mation is needed. For example, users of the National
sector vendor.
Criminal Victimization Survey conducted by the
At a time when the web is there for the specific
Bureau of Justice Statistics have overwhelmingly stat-
purpose of retrieving information easily, freely, and
ed the need for state and county information. Similar
comprehensively, this approach is outdated. The
requests for local education and health data also have
time has come for an integration of data processing
been voiced. Most surveys from statistical agencies
and retrieval systems. This should be accomplished,
such as the National Center for Health Statistics and
even though the structure of the U.S. federal statisti-
the National Center for Education Statistics produce
cal system is highly decentralized.
data at the national level. For national policy needs,
The concept of a single system in the United
this makes sense. To serve the needs of states and
States, and probably most countries, is misleading.
local communities, however, national data does little
In reality, what you have is a confederation of agen-
good. The statistical agencies surely understand local
cies reporting to different jurisdictions that are inde-
needs, and this lack of local information is not based
pendent of each other. In the United States, there is
on the agencies’ lack of desire to produce it. Rather,
limited administrative record data sharing and, with
we are back to the issue of influence and the need for
separate Internet sites, little integration of tabulat-
resources. Where in Congress are the champions for
ed data sets. Each agency has its own budget, and
statistics when we need them? I submit that, for the
except for the purchasing of surveys from the U.S.
most part, they’re gone.
Census Bureau, little in the way of financial interac-
tion. This lack of centralization affects the agencies’
Staffing
influence with Congress and the funding for their
Over the next few years, many of the senior staff mem-
programs. (This is not the case during the decennial
bers of statistical agencies will reach retirement age. At
census cycle, when the apportionment of congres-
the same time, it is difficult for agencies to hire new
sional seats can affect a representative. Other data
personnel and hold on to talented statisticians and
series, such as employment and inflation, also are
economists. The private sector offers both higher sala-
closely reviewed.) Would a centralized, single agency
ries and the opportunity to diversify. Indeed, the prob-
help solve this? Put another way, would an agency
lem of “stove-piping” within statistical agencies, where
large enough to be recognized by Congress and the
talented people are expected to stay in one place for an
current administration as being critical to the overall
overly extended period of time, is counter-productive.
health of the nation have a better opportunity to
There is a need to develop a system whereby people can
receive the needed resources?
move not only within an agency, but also across agen-
Confidentiality
cies. Such a system of diverse training will be required
so personnel can develop the skills needed to address
To perhaps overstate the case, the days of taking cen-
the concerns that have been mentioned here.
suses and surveys may soon be coming to an end.
The challenges I have reviewed are only the
We may be at the crossroads of relying on admin-
beginning. To properly measure the effects of the
istrative records. Using administrative records data
current, and probably future, economic crises in
brings up confidentiality issues on the part of agen-
the United States, timely and relevant data are
cies. Yet, these data may become the basis for mea-
needed for those who have to make informed deci-
suring health, education, employment, expenditure,
sions affecting all Americans. n
transportation, energy use, and many other areas.
Using administrative records data will call for public/
private sector coordinated analyses and the allocation
Make the most of your ASA membership
of talent and research dollars. If the use of adminis- Visit the ASA Members Only site:
trative data becomes the norm, it is not too outré to
www.amstat.org/membersonly
see a time when no data will be real—model-based
estimates will be used to protect identities.
Partner discounts • Member forums • Enews archive
22 AmstAt News NOVEMBER 2009
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76