ANOVA standard deviations

[Wendy Jane]

Hi,

I was wondering if there is any way to output weighted standard deviations for ANOVAs in stata?
For example:

webuse manuf
anova yield method c.temperature

I can output the weighted means for yield by method using

margins method

But I dont know how to output the weighted means?

Additionally if I was not controlling for temperature I could use:

oneway yield method, tabulate

to get the weighted standard deviations

Is there another command that could do this for ANOVAs that control for another variable (in this case c.temperature)?


Thank you very much for any help!

[Carlo Lazzaro]

Wendy:
is what follows that you're looking for?

. webuse manuf
. anova yield method c.temperature

                         Number of obs =         36    R-squared     =  0.1980
                         Root MSE      =    2.98544    Adj R-squared =  0.1494

                  Source | Partial SS         df         MS        F    Prob>F
             ------------+----------------------------------------------------
                   Model |     72.625          2     36.3125      4.07  0.0262
                         |
                  method |      42.25          1       42.25      4.74  0.0367
             temperature |     30.375          1      30.375      3.41  0.0739
                         |
                Residual |    294.125         33   8.9128788  
             ------------+----------------------------------------------------
                   Total |     366.75         35   10.478571  

. margins method

Predictive margins                                          Number of obs = 36

Expression: Linear prediction, predict()

------------------------------------------------------------------------------
             |            Delta-method
             |     Margin   std. err.      t    P>|t|     [95% conf. interval]
-------------+----------------------------------------------------------------
      method |
       Stir  |        6.5    .703676     9.24   0.000      5.06836     7.93164
       Fold  |   8.666667    .703676    12.32   0.000     7.235027    10.09831
------------------------------------------------------------------------------

. bysort method: sum yield

------------------------------------------------------------------------------------------------------------------------------------------
-> method = Stir

    Variable |        Obs        Mean    Std. dev.       Min        Max
-------------+---------------------------------------------------------
       yield |         18         6.5    2.995094          2         13

------------------------------------------------------------------------------------------------------------------------------------------
-> method = Fold

    Variable |        Obs        Mean    Std. dev.       Min        Max
-------------+---------------------------------------------------------
       yield |         18    8.666667    3.180825          3         14


.

[Wendy Jane]

No unfortunately. As far as I know the bysort command doesn't give adjusted means/standard deviations:

. webuse autom
(1978 automobile data)

. anova price foreign c.weight

                         Number of obs =         74    R-squared     =  0.4989
                         Root MSE      =    2117.02    Adj R-squared =  0.4848

                  Source | Partial SS         df         MS        F    Prob>F
              -----------+----------------------------------------------------
                   Model |  3.169e+08          2   1.584e+08     35.35  0.0000
                         |
                 foreign |  1.326e+08          1   1.326e+08     29.59  0.0000
                  weight |  3.154e+08          1   3.154e+08     70.36  0.0000
                         |
                Residual |  3.182e+08         71   4481776.4  
              -----------+----------------------------------------------------
                   Total |  6.351e+08         73     8699526  

. margins foreign

Predictive margins                                          Number of obs = 74

Expression: Linear prediction, predict()

------------------------------------------------------------------------------
             |            Delta-method
             |     Margin   std. err.      t    P>|t|     [95% conf. interval]
-------------+----------------------------------------------------------------
     foreign |
   Domestic  |   5083.986   316.3435    16.07   0.000     4453.215    5714.757
    Foreign  |   8720.987   530.3685    16.44   0.000     7663.463    9778.512
------------------------------------------------------------------------------

. bysort foreign: sum price

---------------------------------------------------------------------------------------------------------------------------------
-> foreign = Domestic

    Variable |        Obs        Mean    Std. dev.       Min        Max
-------------+---------------------------------------------------------
       price |         52    6072.423    3097.104       3291      15906

---------------------------------------------------------------------------------------------------------------------------------
-> foreign = Foreign

    Variable |        Obs        Mean    Std. dev.       Min        Max
-------------+---------------------------------------------------------
       price |         22    6384.682    2621.915       3748      12990