Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

# Re: st: Anova and pwcompare and not estimable

 From Martyn Sherriff To statalist@hsphsun2.harvard.edu Subject Re: st: Anova and pwcompare and not estimable Date Tue, 10 Jan 2012 10:04:13 +0000

```I agree, it does look a little odd. I cannot think of an explanation
at the moment. Sorry.
Martyn

On 9 January 2012 22:04, Garry Anderson <g.anderson@unimelb.edu.au> wrote:
> Dear Statalist and Martyn,
>
> Thank you for referring me to the excellent discussion.
>
> I have used -pwcompare calib#shape, asbalanced emptycells(reweight)- and obtained the following.
>
> I would have expected two different standard errors for the two types of comparison (within calib, and between calib). The -anova- defines which error term to use for each factor and I would have thought this carries over to comparisons of means.
>
>
> set more of
> use http://www.stata-press.com/data/r12/t77
> gen sub1to6 = subject
> replace sub1to6=sub1to6 + 3 if calib==2
> anova score calib / sub1to6|calib shape calib#shape,repeated(shape)
>
> pwcompare calib#shape, asbalanced emptycells(reweight)
>
> Pairwise comparisons of marginal linear predictions
>
> Margins      : asbalanced
> Empty cells  : reweight
>
> -----------------------------------------------------------------
>                |   Contrast   Std. Err.     [95% Conf. Interval]
> ----------------+------------------------------------------------
>    calib#shape |
> (1 2) vs (1 1)  |         -1   .9077853     -2.977894    .9778942
> (1 3) vs (1 1)  |          3   .9077853      1.022106    4.977894
> (1 4) vs (1 1)  |   .6666667   .9077853     -1.311227    2.644561
> (2 1) vs (1 1)  |          3   .9077853      1.022106    4.977894
> (2 2) vs (1 1)  |   1.333333   .9077853     -.6445608    3.311227
> (2 3) vs (1 1)  |   4.666667   .9077853      2.688773    6.644561
> (2 4) vs (1 1)  |   5.333333   .9077853      3.355439    7.311227
> (1 3) vs (1 2)  |          4   .9077853      2.022106    5.977894
> (1 4) vs (1 2)  |   1.666667   .9077853     -.3112275    3.644561
> (2 1) vs (1 2)  |          4   .9077853      2.022106    5.977894
> (2 2) vs (1 2)  |   2.333333   .9077853      .3554392    4.311227
> (2 3) vs (1 2)  |   5.666667   .9077853      3.688773    7.644561
> (2 4) vs (1 2)  |   6.333333   .9077853      4.355439    8.311227
> (1 4) vs (1 3)  |  -2.333333   .9077853     -4.311227   -.3554392
> (2 1) vs (1 3)  |   2.66e-15   .9077853     -1.977894    1.977894
> (2 2) vs (1 3)  |  -1.666667   .9077853     -3.644561    .3112275
> (2 3) vs (1 3)  |   1.666667   .9077853     -.3112275    3.644561
> (2 4) vs (1 3)  |   2.333333   .9077853      .3554392    4.311227
> (2 1) vs (1 4)  |   2.333333   .9077853      .3554392    4.311227
> (2 2) vs (1 4)  |   .6666667   .9077853     -1.311227    2.644561
> (2 3) vs (1 4)  |          4   .9077853      2.022106    5.977894
> (2 4) vs (1 4)  |   4.666667   .9077853      2.688773    6.644561
> (2 2) vs (2 1)  |  -1.666667   .9077853     -3.644561    .3112275
> (2 3) vs (2 1)  |   1.666667   .9077853     -.3112275    3.644561
> (2 4) vs (2 1)  |   2.333333   .9077853      .3554392    4.311227
> (2 3) vs (2 2)  |   3.333333   .9077853      1.355439    5.311227
> (2 4) vs (2 2)  |          4   .9077853      2.022106    5.977894
> (2 4) vs (2 3)  |   .6666667   .9077853     -1.311227    2.644561
> -----------------------------------------------------------------
>
> .
>
> Kind regards, Garry
>
>
>
>
>
>
>
>
>
> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Martyn Sherriff
> Sent: Monday, 9 January 2012 10:08 PM
> To: statalist@hsphsun2.harvard.edu
> Subject: Re: st: Anova and pwcompare and not estimable
>
> pwcompare calib#shape, asbalanced emptycells(reweight)
>
> There is an excellent discussion of this at http://www.ats.ucla.edu/stat/stata/faq/margins_nested1.htm
>
> Cheers,
> Martyn
>
> On 9 January 2012 08:52, Garry Anderson <g.anderson@unimelb.edu.au> wrote:
>> pwcompare calib#shape
> *
> *   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/

*
*   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/
```