Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: testing group means


From   Claude Francoeur <[email protected]>
To   [email protected]
Subject   st: testing group means
Date   Sun, 07 Jan 2007 10:56:16 -0500

I am testing if 4 group means are different from zero.  Stata is using the 
std dev of each group to perform the t tests. This causes that the "Power & 
Pipelines" group mean is not diffrent from 0 with a mean of -0.0099, but the 
REIT group is, with a mean of -0.0044.  I would prefer to use the overall 
std dev. to make the t tests. How do I tell Stata to use the overall SD?

Thanks.

by trust_type, sort : ttest meanmonthlyar == 0



-> trust_type = Power & Pipelines



One-sample t test

------------------------------------------------------------------------------

Variable |     Obs        Mean    Std. Err.   Std. Dev.   [95% Conf. 
Interval]

---------+--------------------------------------------------------------------

meanmo~r |      18   -.0099333    .0063121      .02678   -.0232507 
.003384

------------------------------------------------------------------------------

    mean = mean(meanmonthlyar)                                    t 
  -1.5737

Ho: mean = 0                                     degrees of freedom = 
17



    Ha: mean < 0                 Ha: mean != 0                 Ha: mean > 0

 Pr(T < t) = 0.0670         Pr(|T| > |t|) = 0.1340          Pr(T > t) = 
0.9330



-----------------------------------------------------------------------------------------------------------------------------



-> trust_type = REIT



One-sample t test

------------------------------------------------------------------------------

Variable |     Obs        Mean    Std. Err.   Std. Dev.   [95% Conf. 
Interval]

---------+--------------------------------------------------------------------

meanmo~r |      25    -.004356    .0021169    .0105847   -.0087252 
.0000131

------------------------------------------------------------------------------

    mean = mean(meanmonthlyar)                                    t 
  -2.0577

Ho: mean = 0                                     degrees of freedom = 
24



    Ha: mean < 0                 Ha: mean != 0                 Ha: mean > 0

 Pr(T < t) = 0.0253         Pr(|T| > |t|) = 0.0506          Pr(T > t) = 
0.9747

-----------------------------------------------------------------------------------------------------------------------------



-> trust_type = Business Trust



One-sample t test

------------------------------------------------------------------------------

Variable |     Obs        Mean    Std. Err.   Std. Dev.   [95% Conf. 
Interval]

---------+--------------------------------------------------------------------

meanmo~r |      95    .0040821    .0055586    .0541783   -.0069546 
.0151188

------------------------------------------------------------------------------

    mean = mean(meanmonthlyar)                                    t = 
0.7344

Ho: mean = 0                                     degrees of freedom = 
94



    Ha: mean < 0                 Ha: mean != 0                 Ha: mean > 0

 Pr(T < t) = 0.7677         Pr(|T| > |t|) = 0.4645          Pr(T > t) = 
0.2323



-----------------------------------------------------------------------------------------------------------------------------



-> trust_type = Energy Trust



One-sample t test

------------------------------------------------------------------------------

Variable |     Obs        Mean    Std. Err.   Std. Dev.   [95% Conf. 
Interval]

---------+--------------------------------------------------------------------

meanmo~r |      33    .0057545     .005595    .0321408   -.0056421 
.0171512

------------------------------------------------------------------------------

    mean = mean(meanmonthlyar)                                    t = 
1.0285

Ho: mean = 0                                     degrees of freedom = 
32



    Ha: mean < 0                 Ha: mean != 0                 Ha: mean > 0

 Pr(T < t) = 0.8443         Pr(|T| > |t|) = 0.3114          Pr(T > t) = 
0.1557



-----------------------------------------------------------------------------------------------------------------------------

*
*   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/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index