Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: BatPlot options and Creating a Matrix
From
Nick Cox <[email protected]>
To
[email protected]
Subject
Re: st: BatPlot options and Creating a Matrix
Date
Fri, 5 Aug 2011 20:55:44 +0100
-concord- just calls standard -twoway- commands and options for its
graphics. All the graphics syntax that is not explained by the help
is thus covered by the graphics manual.
Nick
On Fri, Aug 5, 2011 at 7:39 PM, Diego Bellavia <[email protected]> wrote:
> concord works like a charm, thank you very much (BTW, I would like to manipulate
> a little bit more the B-A plots I get with the loa options, is there any help
> online where I could look at ?)
>
>
> statsby looked promising but I am now studying how to report everything with the
> "matrix" command, it seems more difficult to understand but also extremely
> powerful.
>
>
> Thank you so much for the brief but effective reply !
>
> ----- Messaggio originale -----
> Da: Nick Cox <[email protected]>
>
> On the second question, check out -statsby-.
>
> On the first, see also -concord- (-findit concord- for locations).
>
> Nick
>
> On 4 Aug 2011, at 12:44, Diego Bellavia <[email protected]> wrote:
>> I am struggling with batplot (quiet successfully I must say) and I have a
>>couple
>> of questions regarding the use of this command:
>>
>>
>> 1) Is there any way to modify the Y axis label options so that the "dashed"
>> green line would be centered to 0 value on Y axis and the limits of agreements
>> would be symmetric around the zero then ? Using the ylab options I can change
>> the label but not the position of the graph...
>>
>> 2) The "grey" area defined by the B-A plot (using the notrend option) defines
>> 95% limits of agreeement, am I correct ?
>>
>>
>> 3) My Mentor here asked me to compute the "Bias" for the inter-observer
>> agreement in the same dataset of measures. I am assuming this is the simple
>> coefficient of variation (obtained as 100 * SDdiff / Mean-diff) am I correct ?
>>
>>
>>
>> I have also another question, totally unrelated to B-A plots:
>>
>> I have to run several simple regression models and would like to automatically
>> group results
*
* 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/