only about 0.02% of the total budget authority of
Principal Federal Statistical Agencies
about $2.5 trillion for the entire federal government. Bureau of Economic Analysis (U.S. Department of Commerce)
And the dedicated civil servants at the statistical agen-
Bureau of Justice Statistics (U.S. Department of Justice)
cies get the job done—key indicators come out on
schedule, data collection proceeds for a wide array of
Bureau of Labor Statistics (U.S. Department of Labor)
censuses and surveys, much important methodologi- Bureau of Transportation Statistics
cal research is carried out, and significant innovations (U.S. Department of Transportation)
are made.
U.S. Census Bureau (U.S. Department of Commerce)
What Is the Problem?
Economic Research Service (U.S. Department of Agriculture)
Yet, all is not well. The budget authority for the 14
Energy Information Administration (U.S. Department of Energy)
principal agencies (excluding the 2000 and 2010 cen-
National Agricultural Statistics Service
suses) has remained almost flat in real terms over the
(U.S. Department of Agriculture)
last 10 years. Most agencies have had to carry out their
responsibilities over the past decade with the same or
National Center for Education Statistics
fewer staff, even as their responsibilities have grown
(U.S. Department of Education)
along with the size and complexity of the popula-
National Center for Health Statistics
tion and economy (see Appendix A in Principles and
(U.S. Department of Health and Human Services)
Practices for a Federal Statistical Agency, 4th ed.).
Office of Environmental Information
Adding to staffing problems is a growing wave
(U.S. Environmental Protection Agency)
of senior-level retirements coupled with hurdles to
recruitment, such as the inability to hire noncitizens.
Office of Research, Evaluation, and Statistics
Consequently, despite best efforts, important data
(U.S. Social Security Administration)
series have been compromised in their relevance and
Science Resources Statistics Division
usefulness. Andrew Reamer’s column in the March (National Science Foundation)
issue of Amstat News provides examples—and others
Statistics of Income Division (U.S. Treasury Department)
could be added—of series that have been reduced in
sample size, scope, or periodicity or for which the
underlying design has not been reviewed or updated
in 10 or 20 years, or even longer. Coordination of
of objective, high-quality information for public
data series across agencies on such topics as income
policy analysis, research, and decisionmaking.
and health insurance coverage is not as thorough-
going as it could be; methodological research on
Another Part of the Solution—Goal-
common problems, such as increasing rates of unit
Oriented Research and Development
and item nonresponse in key surveys, is not as far
advanced as it could be, and innovation in concepts,
More funding is not the whole answer. How agencies
measures, and methods has often lagged behind
use their current funding, let alone funding increases,
social, economic, and technological change.
also needs to be smarter, as do the efforts of constitu-
encies to garner support for statistical agencies with
Part of the Solution—More Money
Congress. In particular, for the statistical system as a
The problems for the statistical system are well
whole, too little funding and staff are devoted to sus-
known by the agencies, which, with the Statistical
tained R&D within and across agencies, which is essen-
and Science Policy Office in OMB, are striv-
tial for keeping data series as up to date as possible in
ing hard—and doing a remarkable job in many
terms of relevance, quality, timeliness, usability, and
instances—to make bricks without straw. While
value for the dollars invested.
money may not be everything, it is undoubtedly
Of course, many agencies engage in signifi-
true that the statistical system needs significantly
cant R&D efforts, but from the perspective of the
more funding than it currently receives if it is to
Committee on National Statistics, too many data
meet the information needs of government, busi-
programs are on autopilot and, consequently, lag
ness, academia, and the public at large.
behind in their efficiency and effectiveness. In addi-
Realistically, the chances of sizeable increases in
tion, too many R&D efforts are scattershot and not
statistical agency funding in the current economic
focused on identifying the most important threats
climate are not high compared with other national
to data quality, relevance, and timeliness and the
needs. Yet, the positive statements made by the
best methods to surmount them. Steps that would
new administration about the importance of scien-
increase the benefit-cost ratio from statistical agency
tific evidence and the role of government give rise
R&D include the following:
to hope that statistical agency appropriations will
• Allocating a meaningful fraction of the budget
grow in recognition of the fundamental importance
for major continuing data series to R&D
MAY 2009 AMSTAT NEWS 29
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 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84