st: Same N when using matrix for ttests

[Matthew Krauchunas <krauchunasms@mymail.vcu.edu>]

Hello,

I am running a series of ttests to compare my sample to excluded
observations.  I have adapted Ben Jann's code that I found on
Statalist, but I am having a problem in that the same N is being
produced for each variable even though I know the Ns are different.
Here is the code I am using and the result:

* perform t-tests on dependent variables and acuindex.
* next set of code from Ben Jann off of Statalist.org
http://www.stata.com/statalist/archive/2008-09/msg00385.html
capt prog drop myttests
program myttests, eclass
    version 8
    syntax varlist [if] [in], by(varname) [ * ]
    marksample touse
    markout `touse' `by'
    tempname Sample_Mean Excluded_Mean Sample_N Excluded_N
Sample_StDev Excluded_StDev t_statistic P_Values
    foreach var of local varlist {
        qui ttest `var' if `touse', by(`by') `options'
        mat `Sample_Mean' = nullmat(`Sample_Mean'), r(mu_1)
        mat `Excluded_Mean' = nullmat(`Excluded_Mean'), r(mu_2)
        mat `Sample_N'    = nullmat(`Sample_N'), r(N_1)
		mat `Excluded_N'    = nullmat(`Excluded_N'   ), r(N_2)
		mat `Sample_StDev'    = nullmat(`Sample_StDev'   ), r(sd_1)
		mat `Excluded_StDev'    = nullmat(`Excluded_StDev'   ), r(sd_2)
		mat `t_statistic' = nullmat(`t_statistic'), r(t)
        mat `P_Values'  = nullmat(`P_Values' ), r(p)
	    }
    foreach mat in Sample_Mean Excluded_Mean Sample_N Excluded_N
Sample_StDev Excluded_StDev t_statistic P_Values {
        mat coln ``mat'' = `varlist'
    }
    tempname b V
    mat `b' = `Sample_Mean'*0
    mat `V' = `b''*`b'
    eret post `b' `V'
    eret local cmd "myttests"
    foreach mat in Sample_Mean Excluded_Mean Sample_N Excluded_N
Sample_StDev Excluded_StDev t_statistic P_Values {
        eret mat `mat' = ``mat''
				    }
end
* dependent variables and variables used in their calculations.
* independent variables:  organizational characteristics *
myttests  beds, by(dropped_observations)
ereturn list
esttab, nomtitle nonumbers noobs cells("Sample_N Sample_Mean
Sample_StDev Excluded_N Excluded_Mean Excluded_StDev t_statistic
P_Values")

Here is the result and the N for all variables is 8,162:

--------------------------------------------------------------------------------------------------------------------
                 Sample_N  Sample_Mean Sample_StDev   Excluded_N
Excluded_M~n Excluded_S~v  t_statistic     P_Values
--------------------------------------------------------------------------------------------------------------------
beds                 3282     98.72121     44.74487         4880
94.95512     52.69485     3.359993      .000783
slack                3282     .0975765     .4532256         4880
.0087492     1.090031     4.418613     .0000101
mcal_revenue         3282     .6074439     .1988794         4880
.4182913     .2839123      33.0953     1.7e-225
dependenc~15         3282     .4146383     .1492982         4880
.2812511     .1981935     32.80157     8.8e-222
dependenc~25         3282      .411041     .1445903         4880
.2812352     .1952051     32.55888     9.9e-219
--------------------------------------------------------------------------------------------------------------------

However, the N is 9,476 when I run beds alone:

                 Sample_N  Sample_Mean Sample_StDev   Excluded_N
Excluded_M~n Excluded_S~v  t_statistic     P_Values
--------------------------------------------------------------------------------------------------------------------
beds                 3282     98.72121     44.74487         6194
88.95802     70.55003     7.197858     6.58e-13
--------------------------------------------------------------------------------------------------------------------


Does anyone have any suggestions on how to run the ttests and account
for the different Ns?

Thank you,
Matt
*
*   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/