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 export Mann-Whitney U Test output in rich text format


From   Nick Cox <[email protected]>
To   [email protected]
Subject   Re: st: How to export Mann-Whitney U Test output in rich text format
Date   Sat, 1 Sep 2012 14:52:33 +0100

0. Read the chapters on [U] on programming until you understand enough
to get your program working correctly.

1. Your program will allow syntax like the r-class command, but will
be declared as e-class.

2. Your program will run the r-class command.

3. Your program will pick up the r-class results you want and return
them as e-class results.

Here is a toy example:

program mymean, eclass
                version 9
	syntax varname(numeric) [if] [in]
	marksample touse
	qui count if `touse'
	su `varlist' if `touse', meanonly
	ereturn scalar mean = r(mean)
end

If you have never programmed in Stata before, expect this to take
several hours.

Naturally, it might be easier to work out how to format results you
save otherwise within your word processing software (at a guess, MS
Word).

Nick

Nick

On Sat, Sep 1, 2012 at 2:23 PM, Caliph Omar Moumin
<[email protected]> wrote:
>
>  Dear Billy
>
> How can write my own eclass verssion? I ready need to export the results of ranksum command in rtf like regression results.
> Kind Regards,
> Caliph
> Email:  [email protected]
>
>
>
> ----- Original Message -----
> From: William Buchanan <[email protected]>
> To: "[email protected]" <[email protected]>
> Cc:
> Sent: Saturday, September 1, 2012 2:28 PM
> Subject: Re: st: How to export Mann-Whitney U Test output in rich text format
>
> You could always write "your own" eclass version of the program.  I've had to do this for folks before and I just ended up posting the results from -r()- into -e()- with the same name.  Then esttab/estout works fine.
>
> HTH,
> Billy
>
> Sent from my iPhone
>
> On Sep 1, 2012, at 5:09, Nick Cox <[email protected]> wrote:
>
>> -eststo- and -estpost- are user-written commands (SJ, SSC), as you are
>> asked to explain.
>>
>> You don't show the code you tried using -eststo- or -estpost- (or I
>> gather other commands) but as -ranksum- is not an estimation command,
>> I don't think you should expect your code to work. The difference
>> between e-class and r-class commands is crucial here.
>>
>> Others may have positive suggestions.
>>
>> Nick
>>
>> On Sat, Sep 1, 2012 at 12:35 PM, Caliph Omar Moumin
>> <[email protected]> wrote:
>>
>>> I am having a problem of how to export  Mann-Whitney U Test output into rich text format "rtf"
>>> I tried to combine command like "eststo" "estpost" and the other but it is not working.
>>> my command is listed below, what command shall i combine to export outputs including  obs;  rank sum;    expected; z and others statistics.
>>>
>>> If you know how could you please help me?
>>>
>>> forval i = 1/8 {
>>> display "*================================================*"
>>> display "`: label (tilstand4) `i''" _n
>>> display "*================================================*"
>>> bysort gender: ranksum LOS if  (tilstand4 == `i'), by(alcoholcons)
>>> }
>>>
>>>
>>>
>>>
>>> Two-sample Wilcoxon rank-sum (Mann-Whitney) test
>>> alcoholcons |      obs    rank sum    expected
>>> -------------+---------------------------------
>>>  nonalcohol |    5071    14440834    14695758
>>>    alcohol |      724    2353076    2098152
>>> -------------+---------------------------------
>>>    combined |    5795    16793910    16793910
>>>
>>> unadjusted variance  1.773e+09
>>> adjustment for ties  -2.667e+08
>>>                    ----------
>>> adjusted variance    1.507e+09
>>> Ho: LOS(alcoho~s==nonalcohol) = LOS(alcoho~s==alcohol)
>>>            z =  -6.568
>>>    Prob > |z| =  0.0000
>>>
>>>
>> *
>> *  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/
>
> *
> *  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/
>
>
> *
> *   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/
*
*   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/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index