(Music plays)
John Bailer: I'd like to welcome you today's Stats and Short Stories
episode. Stats and short stories is a partnership between Miami University
and the American Statistical Association. Today's guest is John Thompson,
director of the Census Bureau. We're very excited to have him here. I'm
John Bailer, I'm Chair of the Department of Statistics at Miami University
and I'm joined by my colleague, Richard Campbell, Chair of the Department
of Media, Journalism and Film. We're delighted to be speaking with John on
this short episode today. Welcome John!
John Thompson: Glad to be here.
Bailer: You know, one of the things that we're really curious about, and
this is to hear a little bit more about our data, that the Census Bureau
collects, not necessarily just through the census but through some of the
other surveys as well, that that you do, used to make decisions both in the
federal government and more broadly in industry?
Thompson: The Census Bureau collects a wide variety of data and provides it
as information. So, starting with the decennial census, it has some primary
purposes in re-apportioning the Congress every ten years, redrawing
congressional districts and local legislative districts, and also it
provides information to the agencies that look at civil rights enforcement.
The American Community Survey, which is very closely related to the census,
is used to allocate over four hundred billion dollars of federal funding
annually, and is also used by local governments and businesses to make an
informed decisions. Then, turning to our demographic area, we have a
program that we call the "small area estimates of income and poverty" and
that produces estimates on an annual basis that are used to allocate block
grants. We produce a series of the estimates called "small area estimates"
of health insurance and they are used by the Centers for Disease Control
and Prevention to look at the availability of proper insurance for cancer
prevention or a cancer cure. We produce an annual series of population
estimates which come out on annual basis and these are, these support a lot
of municipal grant needs. Turning to our economic side, we produce thirteen
key principal economic indicators and these are used to chronicle the
economy. These can be either on the monthly basis or a quarterly basis.
They also serve as a real tool for investments because you can really see
the markets move after these indicators are released. And finally we
produce information for the Bureau of Economic Analysis. The Bureau of
Economic Analysis produces estimates of gross domestic product and we give
them that eighty percent of the information that supports that calculation
or estimation and that would include information on retail sales, on
foreign imports and on services. So it's really gratifying to be working an
agency which has this broad portfolio of data production and data uses.
Richard Campbell: How do you, how do you let people know about what data is
available? How do you communicate that to businesses and to the public? Or
are do, are they just expected to know, go to the census, and you'll see,
what, you know, these…these different, where these different studies
are?
Thompson: We actually have an entire organization within the Census Bureau
and that does communications.
Campbell: Uh hmm.
Thompson: And a big part of what they do, is reaching out to various
stakeholders in our products and making sure, one, they are aware of them,
two, making sure that if they need answers to certain questions, that we
have subject matter experts available to them, and you know, and helping
them use the data too.
Bailer: This is, this is great. I'm going to ask you that to follow up on a
quick technical point that you raised. You said small area estimation.
Thompson: Yes.
Bailer: Can you explain, just give a quick explanation of that, for people
who have never heard of that before?
Speaker 2: Yeah, so quick explanation. Let me try to do this.
(Multiple people laughing)
Bailer: Sorry!
Thompson: Well, no, you know, you are a statistician, you would appreciate
this. So when you do sample surveys, you can only produce direct estimates
from a sample survey when you have enough sample to do that. So that's
usually for larger areas. So, small area estimates are where we use
statistical model to produce local area estimates of poverty and health
insurance. I don't know if that really answers the question.
Bailer: That's good, so...
Thompson: But it's really taking statistical modeling and using that in
lieu or in a supplement to direct data collection.
Bailer: Very good! Perfect! Outstanding! Well that's been great. It's been
our pleasure to have John Thompson join us on Stats and Short Stories.
Stats and Stories is a partnership between Miami University's Departments
of Statistics and Media, Journalism and Film, and the American Statistical
Association. Stay tuned and keep following us on Twitter or iTunes. We'd
like to share your thoughts on our program. Send your e-mail to stats and
stories at Miami oh.edu and be sure to listen for future episodes where we
discuss the statistics behind the stories and the stories behind the
statistics.
Click to close the script.