Heavy Lifting - thoughts and web finds by an economist
     I also contribute to Division of Labour Load HL's Front Page
Monday, January 31, 2005

How much data is too much data?

A project between Robert Sonora and myself is on the verge of expansion. How much of an expansion? Here is the summary of data describing one year (we will eventually use four or five different years):

Variable | Obs Mean Std. Dev. Min Max
-------------+--------------------------------------------------------
year | 637812 1990 0 1990 1990
ecode | 0
exporter | 0
icode | 0
importer | 0
-------------+--------------------------------------------------------
sitc4 | 0
unit | 0
dot | 466421 1.219941 .4142067 1 2
value | 637812 19667.3 387015.6 0 2.12e+08
quantity | 450819 767928.6 6.00e+07 .007 1.57e+10

I won't let the cat out of bag, so to speak, but 637,812 observations in one year? We might be able to cull this down to a couple hundred thousand per year, but even then I think we will have plenty of degrees of freedom.

Comments: Post a Comment



Purchase




Le Chai - galerie du vin



Support



Popularity

Posts that contain Craig Depken per day for the last 90 days.



Contacts

Heavy Lifting's Main Page
Email Me
Atom Feed

WWW
Heavy Lifting




Great Links

Money I Found Today

Heavy Lifting - Firehose style (56k warning)



Recent Posts

- How much data is too much data?




Archives


home


Visitors
Site Meter Blogroll Me!



Credits

Modified maystar design
powered by blogger