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: Stata 13 wishlist
From
William Buchanan <[email protected]>
To
"[email protected]" <[email protected]>
Subject
Re: st: Stata 13 wishlist
Date
Thu, 3 Jan 2013 08:04:42 -0800
I just remembered a few things that I've been wondering about for a while:
1. Adding a suppression option to graph commands for labels. For example, I often need to generate bar graphs with bar heights labeled but think it'd be nice if I could selectively suppress 0 values; the graphs aren't my choice, but this is one way I think I could make the graphs even cleaner.
2. Additional control over placement of individual value labels. When graphing frequencies of categorical values, it'd be nice if there were a way to use something like jittering to displace value labels when they completely or partially overlap to improve clarity.
3. I mentioned it previously, but I think adding some good documentation on Stata's graphics engine could easily solve many of the issues, since there would probably be more than a few people interested in developing their own graphs and/or adding features to existing graphic classes.
Sent from my iPhone
On Jan 3, 2013, at 6:20, Stas Kolenikov <[email protected]> wrote:
> Stata is freaking powerful in instrumental variable models, a far cry
> for any mainstream latent variable package. With a little twist and a
> couple dozen lines of code, you have a whole new arsenal of techniques
> fully supported by GMM, which in turn treats anything that has a
> quadratic objective function. So I am sure that with some -gmm-
> witchcraft, the analogue of Mplus' WLSMV can be coded in Stata. If
> that's the diagonally weighted least squares (I've never been very
> good at idiosyncratic Mplus abbreviations), then it is -gmm,
> wmatrix(robust, independent)- when the covariance entries are given to
> -gmm- as moments... and then -gmm- would offer more, like -cluster-
> corrections and iterated GMM, to mention a couple. As far as I
> understand, Stata's -sem, method(adf)- is implemented internally via a
> -gmm- call. Moreover, a lot of ordinal response functionality can come
> from the wonderful David Roodman's -cmp-. So if you are desperate to
> do ordinal SEM in Stata, you'll find ways :).
>
> On Wed, Jan 2, 2013 at 10:29 AM, John Antonakis <[email protected]> wrote:
>> Hi Billy:
>>
>> Right...here is the post:
>>
>> http://www.stata.com/statalist/archive/2012-08/msg01453.html
>>
>> Still, ADF doesn't have all the advantages that what WLSMV (i.e., Muthén's
>> robust WLS) does.
>>
>> Best,
>>
>> J.
>>
>> __________________________________________
>>
>> Prof. John Antonakis
>> Faculty of Business and Economics
>> Department of Organizational Behavior
>> University of Lausanne
>> Internef #618
>> CH-1015 Lausanne-Dorigny
>> Switzerland
>> Tel ++41 (0)21 692-3438
>> Fax ++41 (0)21 692-3305
>> http://www.hec.unil.ch/people/jantonakis
>>
>> Associate Editor
>> The Leadership Quarterly
>> __________________________________________
>>
>> On 02.01.2013 17:21, William Buchanan wrote:
>>>
>>> It's been requested several times previously, but including some capacity
>>> to control the transparency in graphs (e.g., an option for alpha blending).
>>> Adding some documentation to help end-users develop new graph commands more
>>> easily would also be incredibly helpful (Sergey R. presented on this topic
>>> and the Beamer slides can be found easily via google).
>>>
>>> Re: John,
>>> I'm not in the best Internet browsing situation at the moment, but I had
>>> read a post where either Cameron McIntosh or Stas Kolenikov suggested that
>>> the ADF estimator is equivalent to the WLS estimator in Mplus.
>>>
>>> If nothing else I think speeding up some of the -xt- commands would be
>>> pretty awesome (e.g., xtmelogit, xtmepoisson, etc...). Another previously
>>> mentioned suggestion was to help make it easier for users to integrate Stata
>>> with other scripting and/or programming languages (i.e., python).
>>>
>>> Since the documentation is prepared in LaTeX, maybe an electronic copy in
>>> a format other than PDF would be helpful as well.
>>>
>>> Just my $ 0.02,
>>> Billy
>>>
>>> Sent from my iPhone
>>>
>>> On Jan 2, 2013, at 7:53, Nick Cox <[email protected]> wrote:
>>>
>>>> Postings on this point seem to be overlooking the Graph Recorder.
>>>>
>>>> Nick
>>>>
>>>> On Wed, Jan 2, 2013 at 3:44 PM, John Antonakis <[email protected]>
>>>> wrote:
>>>>>
>>>>> I second that suggestion:
>>>>>
>>>>> "to show commands and syntaxes in the results window". Oftentimes, it is
>>>>> hard to figure out the syntax when making minor edits to a graph....it
>>>>> would
>>>>> be so helpful if we could see the syntax that makes the change.
>>>>
>>>> *
>>>> * For searches and help try:
>>>> * http://www.stata.com/help.cgi?search
>>>> * http://www.stata.com/support/faqs/resources/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/faqs/resources/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/faqs/resources/statalist-faq/
>> * http://www.ats.ucla.edu/stat/stata/
>
>
>
> --
> -- Stas Kolenikov, PhD, PStat (SSC) :: http://stas.kolenikov.name
> -- Senior Survey Statistician, Abt SRBI :: work email kolenikovs at
> srbi dot com
> -- Opinions stated in this email are mine only, and do not reflect the
> position of my employer
>
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/faqs/resources/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/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/