Hi all,
When I use ttest to test pre- vs. post-treatment means, I get one value
for t.
When I use lincom with the respondent_id as the psu, I get a different
value.
Is the ttest command preferred, and if so, what is the difference in the
two tests?
. ttest communication, by(survey_num)
Two-sample t test with equal variances
------------------------------------------------------------------------
------
Group | Obs Mean Std. Err. Std. Dev. [95% Conf.
Interval]
---------+--------------------------------------------------------------
------
pre- | 40 3.425 .1272868 .8050322 3.167538
3.682462
post- | 40 3.675 .0728319 .4606294 3.527684
3.822316
---------+--------------------------------------------------------------
------
combined | 80 3.55 .0742046 .6637065 3.402299
3.697701
---------+--------------------------------------------------------------
------
diff | -.25 .1466506 -.541959
.041959
------------------------------------------------------------------------
------
Degrees of freedom: 78
Ho: mean(pre-) - mean(post-) = diff = 0
Ha: diff < 0 Ha: diff != 0 Ha: diff > 0
t = -1.7047 t = -1.7047 t =
-1.7047
P < t = 0.0461 P > |t| = 0.0922 P > t =
0.9539
. svymean communication, by(survey_num)
Survey mean estimation
pweight: <none> Number of obs =
80
Strata: <one> Number of strata =
1
PSU: respondent_id Number of PSUs =
40
Population size =
80
------------------------------------------------------------------------
------
Mean Subpop. | Estimate Std. Err. [95% Conf. Interval]
Deff
---------------+--------------------------------------------------------
------
communication |
pre- | 3.425 .1272868 3.167538 3.682462
1.012821
post- | 3.675 .0728319 3.527684 3.822316
1.012821
------------------------------------------------------------------------
------
. lincom [communication]pre - [communication]post
( 1) [communication]pre- - [communication]post- = 0
------------------------------------------------------------------------
------
Mean | Estimate Std. Err. t P>|t| [95% Conf.
Interval]
-------------+----------------------------------------------------------
------
(1) | -.25 .1187542 -2.11 0.042 -.4902031
-.0097969
------------------------------------------------------------------------
------
Thanks,
David Richmond
*
* 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/
