[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

From |
"Scott Merryman" <smerryman@kc.rr.com> |

To |
<statalist@hsphsun2.harvard.edu> |

Subject |
st: RE: Postfile Question [Stata 8.2] |

Date |
Sun, 8 May 2005 19:22:04 -0500 |

How about not using a tempfile and -postfile- and -postclose- for each iteration. For example: sysuse auto, clear forv i = 29(-1)25 { postfile hold integration_points b_cons b_price using results`i', replace disp "number of integration points " `i' qui gllamm fore price , i(rep) nip(`i') post hold (`i') (_b[_cons]) (_b[price]) postclose hold } Then you to use Roger Newson's -dsconcat- to append to individual files together. Scott > -----Original Message----- > From: owner-statalist@hsphsun2.harvard.edu [mailto:owner- > statalist@hsphsun2.harvard.edu] On Behalf Of Bryan W. Griffin > Sent: Friday, May 06, 2005 7:38 AM > To: statalist@hsphsun2.harvard.edu > Subject: st: Postfile Question [Stata 8.2] > > I'm using Stata 8.2. > > I created a do file to re-estimate a model several times, and after each > run I want estimates to be posted to the tempfile which I named model_1. I > thought that by specifying "every(1)" in the "postfile" part of the > command > that estimates would be posted to model_1 after the model is estimated > each > time. Last night I go to bed after running this do file for 8 hours > thinking that it was half complete, and this morning I find that the > computer rebooted for some reason. The estimates from the models > completed, > however, were not in the file model_1 -- it was blank. > > How do I get postfile to store estimates after each pass so I won't lose > estimates again should the computer reboot? Commands used are listed > below. > > > > > tempname abort > tempfile model_1 > > postfile `abort' quad_point /// > b0_cons b1_sex b2_option2 /// > se0_cons se1_sex se2_option2 /// > using "C:\sample file\model_1", every(1) > > forvalues i = 29(-1)20 { > > display `i' > gllamm resp sex option2 option3, i(id) fam(bin) link(logit) adapt nip(`i') > allc > > post `abort' (`i') /// > (_b[resp:_cons]) (_b[resp:sex]) (_b[resp:option2]) /// > (_se[resp:_cons]) (_se[sex]) (_se[option2]) > > } > > postclose `abort' * * For searches and help try: * http://www.stata.com/support/faqs/res/findit.html * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

**References**:**st: Postfile Question [Stata 8.2]***From:*"Bryan W. Griffin" <bwgriffin@GeorgiaSouthern.edu>

- Prev by Date:
**st: simulated maximum likelihood estimation** - Next by Date:
**st: RE: simulated maximum likelihood estimation** - Previous by thread:
**st: Postfile Question [Stata 8.2]** - Next by thread:
**st: Population Attributable Fraction (PAF) estimation** - Index(es):

© Copyright 1996–2015 StataCorp LP | Terms of use | Privacy | Contact us | What's new | Site index |