The Bureau of Labor Statistics of the U.S. Department of Labor is the principal Federal agency responsible for measuring labor market activity, working conditions, and price changes in the economy.
What is the effect of random variation
in State unemployment rates?
State and local users of the data may tend
to assume that the rates have low levels
of dispersion ; however, a closer analysis reveals
large variances attributed to sample size
EDWARD W. HILL
The reported monthly unemployment rate from the Current
Population Survey (cps) is the best point estimate of labor
market activity available by State and local labor market
areas . Because of its timeliness, wide coverage, and com-
prehensiveness, it is used by governments, planners, corpo-
rations, and the media. However, statements are often made
about fluctuations in the unemployment rate which are un-
warranted due to the variance of the data series .
The inverse of the unemployment rate is commonly used
as a proxy for gross regional product . It is also used intrare-
gionally, as a coincident indicator of the local business
cycle. InterregionalIy, it is used as a sign of the relative
strength of local economies. The unemployment rate is also
an important instrument in public policy decisions. This is
especially true at the State and local levels where announce-
ments in the rate can trigger political activity . The annual
rate is used by the Federal Government to redistribute funds
to the States . In many States, the rate is used as part of
formulae to redistribute funds from State to local govern-
ments. It is also used to extend or contract the length of time
people are eligible for unemployment benefits .
Most of these uses of the unemployment rate for States
and localities assume that it has low levels of dispersion and
that month-to-month movements in the rate are meaningful .
Because users usually do not pay attention to error attributed
Edward W. Hill is Research Director of the Economic Development Pro-
gram . College of Urban Affairs . Cleveland State University .
to random variation in sampling, they may be using the
unemployment rate to make inferences, decisions, resource
allocations, or policy statements which