[DDI-ADG] time series example
Sandra.A.Cannon at frb.gov
Sandra.A.Cannon at frb.gov
Tue Sep 6 12:58:44 EDT 2005
Kate and company, (with apologies for having to abandon the call
unceremoniously)
The downside to using a spreadsheet from FRED is that they are a secondary
data source so they have already done some formatting to the data they
report. (To be pedantic, my staff collects it from the source and they get
it from us so it's actually our metadata they are reporting. Most data
providers don't really provide metadata in such a nice, accessible format.)
Maybe that isn't a downside but if you want to see how the actual issuing
institutions organize their data to see how they think about various pieces
and what they actually report, then a spreadsheet from FRED isn't the best
example.
Here are a few that may work including some with a geographical component:
Existing home sales from the National Association of Realtors:
http://www.onerealtorplace.com/Research.nsf/files/REL0507EHS.XLS/$FILE/REL0507EHS.XLS
Natural Gas Storage from the Energy Information Administration:
http://tonto.eia.doe.gov/oog/info/ngs/ngshistory.xls
Quarterly Services Survey from the Census Bureau:
http://www.census.gov/indicator/qss/all_2005Q1.xls
These are more complicated spreadsheets than what you get from FRED but are
the actual ones we use to put the data into the database which FRED then
mines.
/san/
-------------------------------------------------
San Cannon
Chief, Economic Information Management
Federal Reserve Board
Washington DC 20551
(202) 452-3710
scannon at frb.gov
Katherine
McNeill-Harman
<mcneillh at mit.edu To
> "DDI-ADG" <ddi-adg at icpsr.umich.edu>
Sent by: cc
ddi-adg-bounces at i
cpsr.umich.edu Subject
[DDI-ADG] time series example
09/06/2005 12:43
PM
Looked around and have a couple of potential examples of time-series data:
1) Raw data file (data separate from metadata in codebook)
(In ICPSR, someone suggested World Bank, but many of those seemed in odd
formats, so I came across the following):
Study No. 4058, Time Series for the Births and Deaths of Newspapers in
Baltimore, Boston, Buffalo, New York City, Philadelphia, and Washington,
DC, 1690-1994: http://webapp.icpsr.umich.edu/cocoon/ICPSR-STUDY/04058.xml
Data dictionary on p. 70 describes year as the first variable in all
records.
or
Study No. 6792, Uniform Crime Reports: Monthly Weapon-Specific Crime and
Arrest Time Series, 1975-1993 [National, State, and 12-City Data]:
http://webapp.icpsr.umich.edu/cocoon/ICPSR-STUDY/06792.xml
Might be a good candidate as it's relatively complex, with separate
national/state/city files and data is collected monthly (p. 28 of codebook
says 1st variable is year, second is month, then followed by an
alphanumeric combination of the two). Also may be a good candidate for
aggregate data.
2) Spreadsheet
I thought it'd be good to maybe also discuss an example of a time series
originally conceived/presented as a spreadsheet (rather than data
file/codebook combo). We have various ones in our proprietary database,
but I wanted to find one publicly-available. So I started at the Federal
Reserve (San, maybe you'll have a better suggestion?):
I browsed through FRED, their online data system, and navigated to a
version of the Consumer Price Index series (although there were multiple
other examples we could use)
http://research.stlouisfed.org/fred2/series/CPIAUCNS/downloaddata
You'll see that when you open up the file, there's general metadata at the
top, and the time series (with a single date and single value) begins a few
lines below.
or, a similar example for treasury bill interest rates:
http://research.stlouisfed.org/fred2/series/DGS3MO/downloaddata
Let me know what you think, any obstacles you see to using any of these as
examples. Again, I'd recommend passing on one in each of these categories
b/they're slightly different in nature.
Kate
___________________________________________
Katherine McNeill-Harman
Data Services Librarian
Dewey Library for Management and Social Sciences
Massachusetts Institute of Technology
77 Massachusetts Avenue, E53-100
Cambridge, MA 02139
mcneillh at mit.edu
617-253-0787
_______________________________________________
DDI-ADG mailing list
DDI-ADG at icpsr.umich.edu
http://www.icpsr.umich.edu/mailman/listinfo/ddi-adg
More information about the DDI-ADG
mailing list