Tobit model #447

Closed
wants to merge 26 commits into
from

Conversation

Projects
None yet
2 participants
@jseabold
Owner

jseabold commented Aug 27, 2012

TODO:

  • Still needs marginal effects.

jseabold added some commits Dec 6, 2011

@josef-pkt

This comment has been minimized.

Show comment Hide comment
@josef-pkt

josef-pkt Sep 19, 2012

Owner

we have to do something about the results files produced by stata
single column makes the files to large, too many lines

359,367 additions and files with 144 thousand lines ?

Owner

josef-pkt commented Sep 19, 2012

we have to do something about the results files produced by stata
single column makes the files to large, too many lines

359,367 additions and files with 144 thousand lines ?

@josef-pkt

This comment has been minimized.

Show comment Hide comment
@josef-pkt

josef-pkt Sep 19, 2012

Owner

the test files didn't get moved out of the scikits namespace/directories

Owner

josef-pkt commented Sep 19, 2012

the test files didn't get moved out of the scikits namespace/directories

@jseabold

This comment has been minimized.

Show comment Hide comment
@jseabold

jseabold Sep 20, 2012

Owner

Probably worth wiping them from git and redoing these.

Owner

jseabold commented Sep 20, 2012

Probably worth wiping them from git and redoing these.

@josef-pkt

This comment has been minimized.

Show comment Hide comment
@josef-pkt

josef-pkt Sep 20, 2012

Owner

I looked at the stata mkarray do file again. It would be relatively easy to make a line break only every k=4 or 5 lines, but haven't tried yet.
The alternative in cases like this with many nobs length arrays, would be to create csv files, but that's not automatic yet.

related: It took me a while to figure out that the big jump in loc count in ohloh this summer came from the tests of your tsa predict and ARIMA improvements. https://www.ohloh.net/p/statsmodels/analyses/latest/languages_summary
and comment ratio dropped to "with a decently commented source code "

Owner

josef-pkt commented Sep 20, 2012

I looked at the stata mkarray do file again. It would be relatively easy to make a line break only every k=4 or 5 lines, but haven't tried yet.
The alternative in cases like this with many nobs length arrays, would be to create csv files, but that's not automatic yet.

related: It took me a while to figure out that the big jump in loc count in ohloh this summer came from the tests of your tsa predict and ARIMA improvements. https://www.ohloh.net/p/statsmodels/analyses/latest/languages_summary
and comment ratio dropped to "with a decently commented source code "

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment