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: dot chart with ci


From   Richard Moverare <richard.moverare@gmail.com>
To   statalist <statalist@hsphsun2.harvard.edu>
Subject   Re: st: dot chart with ci
Date   Thu, 9 May 2013 15:48:01 +0200

Hi again,

nevermind my earlier question, I found a solution. I case anyone is
interested, this is what used:

twoway (scatter group est1) (rcap est1_u est1_l group, horizontal) ///
(scatter group est2) (rcap est2_u est2_l group, horizontal), ///
ylabel(1/13, valuelabel angle(0)) ytitle("")

where est1 and est2 are the two estimates, and est1_l and est1_u are
the lower and upper bounds (same for est2). And group is my grouping
variable. I use the value labels for that variable as well (after
using sencode to change it from string to numeric)

All the best, Rick


2013/5/9 Richard Moverare <richard.moverare@gmail.com>:
> Thank you for your prompt reply, Nick. I thave seen that thread. I
> might be missing something, I am able to create one estimate with ci
> per category of my grouping variable (I think that is what is
> presented in the thread you refer to), but I want two estimates per
> category, e.g.
>
> sysuse auto, clear
> graph dot (mean) length weight, over(rep78)
>
>
>
> But with ci for the two variables. I am sorry if that is obvious from
> the thread you refer to, but I don't see that.
>
> Any help would be greatly appreciated.
>
> All the best, Rick
>
>
>
> 2013/5/9 Nick Cox <njcoxstata@gmail.com>:
>> See the concurrent thread started by Ronnie B.
>> Nick
>> njcoxstata@gmail.com
>>
>>
>> On 9 May 2013 12:31, Richard Moverare <richard.moverare@gmail.com> wrote:
>>> Dear Statalist,
>>>
>>> I would like to creat a dot chart with confidence intervals attached
>>> to the dots. I have variables for the estimates and their lower and
>>> upper bound. I have two estimates for each group of a group variable.
>>> So something like
>>>
>>> sysuse auto, clear
>>> graph dot (mean) length weight, over(rep78)
>>>
>>> But as mentioned I would like to add the confidence intervals. I guess
>>> I should use twoway scatter with rcap, but I don't get the result I
>>> want. Any help would be greatly appreciated.
>>>
>>> All the best,
>>> Rick
>>> *
>>> *   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