Your command is weird in that you seem to be asking for the mean of the
variables while using -ttest- which is designed to check whether the means
are statistically different from each other. If the mean of the two vars was
all you ever wanted, you could just bootstrap the -summarize- command and
get the same result with less fuss...
*********
webuse fuel , clear
ttest mpg1==mpg2, unpaired unequal
bootstrap r(mu_1) r(mu_2), reps(50) : ttest mpg1==mpg2, unpaired unequal
bootstrap r(mean), reps(50) : su mpg1
bootstrap r(mean), reps(50) : su mpg2
*********
I would have expected you to bootstrap the p value that -ttest- returns in
r(p_u), r(p_l) and r(p), depending on the Ha. So the z statistic and
associated p-value tell you whether the mean is significantly different from
zero, and I am pretty sure that is not why you fired up -ttest- in the first
place...
HTH
Martin
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Carlo Lazzaro
Sent: Saturday, September 06, 2008 6:10 PM
To: [email protected]
Subject: st: z statistics in bootstrap output
Dear Statalisters,
following some seemingly unfruitful research on Statalist Archives, Stata
9.2/SE manual and Google, I would kindly ask you for a clarification and the
related formula concerning the meaning of z in bootstrap output (please, see
below).
Thanks a lot for your kindness and for your time.
Kind Regards,
Carlo
-----------------------------------------------------------------------
Bootstrap results Number of obs =
100
Replications =
10
command: ttest A_C == B_C, unpaired unequal
_bs_1: r(mu_1)
_bs_2: r(mu_2)
----------------------------------------------------------------------------
--
| Observed Bootstrap Normal-based
| Coef. Std. Err. z P>|z| [95% Conf.
Interval]
-------------+--------------------------------------------------------------
--
_bs_1 | 47.30786 2.200492 21.50 0.000 42.99497
51.62074
_bs_2 | 76.26435 3.772698 20.21 0.000 68.86999
83.6587
----------------------------------------------------------------------------
--
*
* 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/
