By the way, examples for tabulating a matrix using -esttab- or
-estout- can be found at
http://repec.org/bocode/e/estout/advanced.html#advanced905
ben
On Fri, Jan 9, 2009 at 9:48 AM, Ben Jann <[email protected]> wrote:
> Thanks to Kit Baum, an update to the -estout- package on SSC is
> available. To install the update, type
>
> . ssc install estout, replace
>
> or use the -adoupdate- command. The estout website at
> http://repec.org/bocode/e/estout has also been updated.
>
> Changes:
>
> o The package contains a new command called -estpost-. -estpost- is a
> tool to prepare results from commands such as, e.g., -summarize-,
> -tabulate-, or -correlate- for tabulation by -esttab- or -estout-. For
> example, to produce a table of summary statistics, you could type
>
> . estpost summarize <varlist>
> . estout, cells("mean sd min max")
>
> See the examples at http://repec.org/bocode/e/estout/estpost.html
>
> o -estout- can now tabulate a matrix. For example, type
>
> . esttab matrix(<name>)
>
> where <name> is the name of a Stata matrix. -esttab r(<name>)- or
> -esttab e(<name>)-, where <name> is the name of a matrix stored in r()
> or e(), is also possible. See the Syntax section in -help estout- for
> details (http://repec.org/bocode/e/estout/hlp_estout.html#syn).
>
> o -estout- can now tabulate estimation sets that do not contain e(b)
> or e(V). For example, results from -factor- can now be tabulated (see
> the example at http://repec.org/bocode/e/estout/advanced.html#advanced404).
> The name space of tabulated coefficients is no longer restricted by
> e(b).
>
> o Mutiple values may now be specified in -estout-'s -modelwidth()-
> option to set the widths of the table columns individually.
>
> o -estout- has a new -rename()- option to rename coefficients before
> matching models. This is useful to merge different coefficients across
> models (i.e. to print them in the same row; see the example at
> http://repec.org/bocode/e/estout/advanced.html#advanced008).
>
> o The rows of matrices in e() can now be addressed within -estout-'s
> -cells()- option as <name>[#], <name>[<rowname>], or
> <name>["<rowname>"] where <name> is the name of the e() matrix, # is
> the row number, and <rowname> is the name of the matrix row. (The old
> syntax, <name>_#, is discontinued.) For example, you could type
> -cells(ci_bc[1] ci_bc[2])- or -cells(ci_bc[ll] ci_bc[ul])- to tabulate
> the lower and upper bounds of the bias-corrected confidence intervals
> after -bootstrap-. Furthermore, there is a new -transpose- suboption
> to address columns rather than rows.
>
> o The syntax of and how -estadd prchange- returns its results
> changed. See the section on -prchange- in -help estadd-
> (http://repec.org/bocode/e/estout/hlp_estadd.html#prchange). Also see
> http://repec.org/bocode/e/estout/spost.html#spost202 for examples on
> how to use -estadd prchange-.
>
> o -estout- now saves a copy of the tabulated results in r(). For
> example, the tabulated coefficients are returned in matrix r(coefs).
> See the Saved results section in -help estout-
> (http://repec.org/bocode/e/estout/hlp_estout.html#ret).
>
> For further details on changes see http://repec.org/bocode/e/estout/history.html
>
> Best,
> ben
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
>
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
