Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: gra command


From   Nick Cox <njcoxstata@gmail.com>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   Re: st: gra command
Date   Tue, 25 Jun 2013 22:27:46 +0100

Indeed, but I also explained that it uses version control, so it still
works. The only thing out-of-date  about -cusum6-  is that its graphs
cannot be edited in versions of Stata from 8 on.

What is out-of-date is the graphics advice in the document you
downloaded from Royal Holloway, London and I gave some advice on how
to plot results from this method.
Nick
njcoxstata@gmail.com


On 25 June 2013 22:22, Guelmbaye Ngarsandjé <guelmbaye@hotmail.com> wrote:
> Hi Nick,
> You said "cusum6 is an old program" that's why I ask if there is a new one. As I said, I am working on time series data and want to label my X axis so I could identify (with th cusum6 command) break point; but, I can't edit myself. I would like to know if there is a command telling stata to put all my time-periods (quarter) on the X axis.
>
> Thanks
>
> PS: I am using stata 12 with update from March20th, 2013.
>
> ----------------------------------------
>> Date: Tue, 25 Jun 2013 22:15:34 +0100
>> Subject: Re: st: gra command
>> From: njcoxstata@gmail.com
>> To: statalist@hsphsun2.harvard.edu
>>
>> I fail to see how this question follows from my post, but
>>
>> 1. The official Stata command -cusum- is absolutely nothing to do with
>> -cusum6- (SSC).
>>
>> 2. As -cusum6- (SSC) still works, there is no obvious need for it to
>> be replaced with anything.
>>
>> If that doesn't answer your question, please state what you want to do
>> and someone may be able to help.
>>
>> Nick
>> njcoxstata@gmail.com
>>
>>
>> On 25 June 2013 22:06, Guelmbaye Ngarsandjé <guelmbaye@hotmail.com> wrote:
>>> Hi Nick,
>>>
>>> What is the new command cusum for time series data then? The cusum commmand does not work saying data are out of range.
>>> ----------------------------------------
>>>> Date: Tue, 25 Jun 2013 21:55:34 +0100
>>>> Subject: Re: st: gra command
>>>> From: njcoxstata@gmail.com
>>>> To: statalist@hsphsun2.harvard.edu
>>>>
>>>> Anders is giving excellent advice.
>>>>
>>>> Being new to Stata Guelmbaye is, however, confusing quite different sources.
>>>>
>>>> 1. -cusum6- (SSC, Kit Baum, as you are asked to explain) is an old
>>>> program but it sets -version 6- at the beginning of the program so its
>>>> graphs should work fine, although as noted they cannot be edited with
>>>> modern Stata's Graph Editor.
>>>>
>>>> 2. The problem that Guelmbaye is reporting comes from reliance not on
>>>> -cusum6- but on a document
>>>> http://personal.rhul.ac.uk/uhte/006/ec5040/Cusum%20test.pdf which is
>>>> (a) quite independent of -cusum6- and (b) out-of-date.
>>>>
>>>> Something like
>>>>
>>>> (version 7 and older)
>>>> graph cusum lower upper year, s([year]) c(.mm) xlab(1965,1975,1985,1995) ylab
>>>>
>>>> would probably go better as
>>>>
>>>> (version 8 and later)
>>>> scatter cusum year || line lower upper year
>>>>
>>>> with -ylabel()- and -xlabel()- added to taste.
>>>>
>>>> Nick
>>>> njcoxstata@gmail.com
>>>>
>>>> Anders Alexandersson
>>>>
>>>>> Then build up the graph from the beginning with the current graph command.
>>>>> Also, did you read
>>>>> http://www.stata.com/statalist/archive/2012-04/msg00231.html ?
>>>>
>>>> Guelmbaye Ngarsandjé
>>>>
>>>>>> Thanks. This works well though I can't edit it!
>>>>
>>>> Anders Alexandersson
>>>>
>>>>>>> Change -gra- to -gr7- if you want to use the old Stata 7 graph command.
>>>>>>> As I wrote, see http://www.ats.ucla.edu/stat/stata/faq/graphics78.htm .
>>>>>>>
>>>>>>> For the other graph problems, I suggest you instead use the current
>>>>>>> graph command.
>>>>>>> See http://www.stata.com/statalist/archive/2012-04/msg00231.html
>>>>
>>>> Guelmbaye Ngarsandjé
>>>>
>>>>>>>> Thanks Anders. I changed "gra" to "graph" and I got "gpopgraph_g.new petindex, s([year]) xlab ylab: class member function not found" message. To say it frankly, it's my first time using stata and I have stata12; therefore it's hard for me to know what has changed and from where. How about the other problems I long for answers?
>>>>
>>>> Anders Alexandersson
>>>>
>>>>>>>>> The -gra- command is the Stata 7 (and older) graph command.
>>>>>>>>> See http://www.ats.ucla.edu/stat/stata/faq/graphics78.htm
>>>>
>>>> Guelmbaye Ngarsandjé
>>>>
>>>>>>>>>> I have been looking to check the strutural break in my data and found
>>>>>>>>>> that cusum6 helps do it. However, the file I found has some commands
>>>>>>>>>> that don’t work when I type them. For example using greenedat.dta from
>>>>>>>>>> P.136 provided by the file is the command:
>>>>>>>>>>
>>>>>>>>>> “gra gpop petindex, s([year]) xlab ylab” which gives the following
>>>>>>>>>> message : “Unrecognized command: gra”
>>>>>>>>>>
>>>>>>>>>> The support file can be found at:
>>>>>>>>>> http://personal.rhul.ac.uk/uhte/006/ec5040/Cusum%20test.pdf
>>>>>>>>>>
>>>>>>>>>> What am I doing wrong? In the mean time I want my X axis to be fully
>>>>>>>>>> labelled by the periods but when trying to edit the cusum graphs I
>>>>>>>>>> receive “This is not a “live” graph and therefore cannot be edited.”
>>>>>>>>>> How to obtain my periods labelled at 45 degrees on the X axis?
>>>>
>>>> *
>>>> * 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/
> *
> *   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index