Bookmark and Share

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: How to graph several mean trajectories and combine them in a single graph


From   "Han-Jung Ko (Koko)" <kohan@onid.oregonstate.edu>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: How to graph several mean trajectories and combine them in a single graph
Date   Tue, 25 Feb 2014 16:19:25 -0600

Thank you both for the help.

I did try your suggestions and did more research. I am able to now
graph the dots of means of my variables of interest by wave in a
single graph (i.e., means of pr_ and pl_). Here is my command:

egen pl_m = mean(pl_), by (wave)
egen pr_m = mean(pr_), by(wave)
graph twoway dot pl_m pr_m wave

However, when I tried to connect the dots using the following command:
graph twoway connected pl_m pr_m wave

it not only connects the dots but also draw a line from wave 1 dot to
wave 5 dot for pr_ and pl_. Do you know how I can do to have only the
dots connected for pl_ and pr_ separately but not a straight line from
wave 1 to wave 5 datapoints?

Hope the question is clear. I am sorry that I am not a native speaker.

Sincerely,
Han-Jung Ko

Han-Jung Ko, M.S.
Doctoral Candidate
Human Development and Family Studies
School of Social and Behavioral Health Sciences
Oregon State University
kohan@onid.orst.edu


On Tue, Feb 25, 2014 at 1:53 PM, Nick Cox <njcoxstata@gmail.com> wrote:
> -profileplot- does require a -by()- option but feeding it a variable
> that is constant suppresses subdivision when you don't want it.
>
> Nick
> njcoxstata@gmail.com
>
> On 25 February 2014 18:55, Han-Jung Ko (Koko)
> <kohan@onid.oregonstate.edu> wrote:
>> Thank you. I am not certain. The profileplot command seems requiring
>> by() specification. I may try to see whether graph command could work
>> for graphing means across individuals for certain variables overtime
>> and combine them...
>
>  On Tue, Feb 25, 2014 at 11:57 AM, Nick Cox <njcoxstata@gmail.com> wrote:
>
>>> Sorry, but I can't advise further given "did not work". What was wrong
>>> from your point of view?
>
>>> On 25 February 2014 17:49, Han-Jung Ko (Koko)
>>> <kohan@onid.oregonstate.edu> wrote:
>>>> Thank you, Nick. I tried your suggestion and it did not work though.
>>>> I will try to ask in the FAQ in the link you sent me.
>
>>>> On Tue, Feb 25, 2014 at 3:31 AM, Nick Cox <njcoxstata@gmail.com> wrote:
>>>>> -profileplot- is a user-written program by Philip Ender and from
>>>>> http://www.ats.ucla.edu/stat/stata/ado/analysis
>>>>> as you are asked to explain in the FAQ.
>>>>>
>>>>> If I understand you correctly, you can easily fool -profileplot- into
>>>>> lumping all observations together by
>>>>>
>>>>> gen everyone = 1
>>>>>
>>>>> profileplot ..., by(everyone)
>>>>>
>>>>> although you will probably want to fix legend.
>>>>>
>>>>> Nick
>>>>> njcoxstata@gmail.com
>>>>>
>>>>> On 24 February 2014 20:44, Han-Jung Ko
>>>>>
>>>>>> I am trying to graph several mean trajectories and combine them in a
>>>>>> single graph. By using profileplot command, it is possible to graph
>>>>>> them side-by-side but not in a single graph.
>>>>>> For example,
>>>>>> . profileplot pl_1 pl_2 pl_3 pl_4 pl_5, by(sex) name(graph_pl, replace)
>>>>>> . profileplot pg_1 pg_2 pg_3 pg_4 pg_5, by(sex) name(graph_pg, replace)
>>>>>> . graph combine graph_pl graph_pg
>>>>>>
>>>>>> However, using profileplot command also requires the option by(). I
>>>>>> wonder how I could graph the meantrajectories for all participants
>>>>>> (not by gender) and combine the total of six trajectories together?
> *
> *   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index