Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: Creating Descriptive Statistics With Estpost & Tabstat
From
Austin Nichols <[email protected]>
To
"[email protected]" <[email protected]>
Subject
st: Creating Descriptive Statistics With Estpost & Tabstat
Date
Wed, 3 Nov 2010 22:11:48 -0400
Matthew Krauchunas <[email protected]> :
Reframing in terms of a dataset anyone can use, you want to transpose this:
sysuse auto, clear
g year=rep78+2000
tabstat turn trunk, statistics(mean sd) by(year)
which can be done using -tabstatmat- (SSC) as you allude to, or using
-estout- (SSC) like so:
clear all
sysuse auto
g year=rep78+2000
qui levelsof year, loc(levs)
qui foreach v of loc levs {
estpost summ turn trunk if year==`v'
est sto CY`v'
}
esttab *, cell(mean sd(par)) mti
esttab *, cell(mean sd(par)) mti collabels(none) nonum noobs
tabstat turn trunk, statistics(mean sd) by(year)
and note that the -estout- solution can also be written out to a file easily.
OTOH, the -tabstatmat- solution feeds into -xml_tab- (SSC) nicely...
useful if you are an Excel user.
On Wed, Nov 3, 2010 at 8:30 PM, Matthew Krauchunas
<[email protected]> wrote:
> Hello,
>
> I am trying to create a table of means and standard deviations (in
> parentheses) similar to this format:
>
> Variable_Name 2002 2003 2004
> ---------------------------------------------------------
> rn_hprd .271 .265 .258
> (.157) (.159) (.159)
> -----------------------------------------------------------
> lvn_hprd .60 .62 .64
> (.180) (.181) (.186)
> -----------------------------------------------------------
>
> I have tried tabstat, but the years are the rows instead of the columns:
> . tabstat rn_hprd_adj lvn_hprd_adj, statistics( mean sd) by(year)
> columns(variables)
>
> year | rn_~_adj lvn~_adj
> ---------+--------------------
> 2002 | .2761311 .6059625
> | .1649422 .1979371
> ---------+--------------------
> 2003 | .2721822 .6346036
> | .168225 .2034016
> ---------+--------------------
> 2004 | .264628 .654483
> | .1695155 .21293
> ---------+--------------------
> 2006 | .2752124 .7032399
> | .1779005 .2163748
> ---------+--------------------
> 2007 | .276638 .739869
> | .1788564 .2327166
> ---------+--------------------
> Total | .2729584 .6676316
> | .1719123 .2182212
> ------------------------------
>
> I have also tried a combination of estpost & tabstat which appears to
> be a nice format, but again the same problem:
> estpost tabstat rn_hprd_adj lvn_hprd_adj, statistics( mean sd)
> by(year) columns(variables)
>
> year | e(rn_hp~) e(lvn_h~)
> -------------+----------------------
> 2002 |
> mean | .2761311 .6059625
> sd | .1649422 .1979371
> -------------+----------------------
> 2003 |
> mean | .2721822 .6346036
> sd | .168225 .2034016
> -------------+----------------------
> 2004 |
> mean | .264628 .654483
> sd | .1695155 .21293
> -------------+----------------------
> 2006 |
> mean | .2752124 .7032399
> sd | .1779005 .2163748
> -------------+----------------------
> 2007 |
> mean | .276638 .739869
> sd | .1788564 .2327166
> -------------+----------------------
> Total |
> mean | .2729584 .6676316
> sd | .1719123 .2182212
>
> I saw a potential solution to Mr. Nick Cox by transposing a matrix
> (http://www.stata.com/statalist/archive/2006-08/msg00335.html), but I
> cannot quite figure it out.
>
> Does anyone have any suggestions on how to create this type of table?
*
* 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/