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

From |
"Ben Jann" <ben.jann@gmail.com> |

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

Subject |
st: Update to -estout- available from SSC |

Date |
Fri, 28 Sep 2007 21:07:03 +0200 |

Thanks to Kit Baum, an update to the -estout- package is available from the SSC archive. -estout- provides tools to produce regression tables. To install the update, type . ssc install estout, replace or use the -adoupdate- command. Main changes: o -esttab- has a new -onecell- option to combine point estimates and t-statistics (or standard errors, etc.) in a single table cell. This option is especially useful in RTF (Word) or HTML mode (a line break is inserted between the combined statistics in these modes). o -estout- can now handle e()-matrices with multiple rows. This is useful, e.g., if you want to tabulate bias corrected bootstrap confidence intervals, which are returned in a two row matrix called e(ci_bc). The syntax to address a specific row is name_#, where # is the row number. For example, type -cells(ci_bc_1 ci_bc_2)- to tabulate the BC bootstrap intervals. This functionality is only active if no e(name_#) matrix exists in the estimation set. o -estout- now has a -labcol2()- option to add a second column containing labels in the left stub of the table. This is useful, for example, to insert a column containing information on the hypothesized directions of the effetcs. o -estout- now has a -topfile()- and a -bottomfile()- option to add text from files on disk to the top and bottom of the table. o The "." character can now be used in -estout-'s -cells()- option to insert "null" elements (empty cells). o The "&" character can now be used in -estout-'s -cells()- option to combine elements in a single cell. There is a new -incelldelimiter()- option to specify the string to be printed between the combined elements. o Display formats in -estout- and -esttab-: "%g" or "g" can now be used in place of "%9.0g", "a" can be used in place of "a3" o -estadd- now has more flexible syntax with respect to adding matrices and scalars: -estadd r(name)- now adds in e(name) the contents of r(name) to the estimation set, where r(name) may be a scalar or a matrix. -estadd matrix name = ...- now accepts matrix expressions. -estadd matrix matname- now adds a copy of matrix 'matname' in e(matname); -estadd matrix r(matname)- adds a copy of matrix r(matname) in e(matname) -estadd scalar scalarname- now adds the value of scalar 'scalarname' in e(scalarname); -estadd scalar r(scalarname)- adds the value of r(scalarname) in e(scalarname) Significant changes have been made to the core of estout.ado. Although I did quite a bit of testing, I hope did not break anything. I'd be happy if you let me know if you encounter any odd behavior. ben * * 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/

- Prev by Date:
**st: Update to -kdens- available from SSC** - Next by Date:
**st: RE: RE: Does my statistic for "net proportion of subjects with improved prediction" already exist?** - Previous by thread:
**st: Update to -estout- available from SSC** - Next by thread:
**st: Update to -adolist- available from SSC** - Index(es):

© Copyright 1996–2017 StataCorp LLC | Terms of use | Privacy | Contact us | What's new | Site index |