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: New commands -dmout- and -pctrim-
From
Michael Barker <[email protected]>
To
[email protected]
Subject
Re: st: New commands -dmout- and -pctrim-
Date
Tue, 4 Feb 2014 16:17:25 -0500
Hi Amber,
You can use dmout if your outcome variables are 0/1. Then the mean of
that variable is equal to the proportion of the sample that is in that
group.
dmout produces results as if you used ttest. There is another command,
prtest, that is specifically for testing proportions. dmout does not
reproduce the results from prtest. But the results of those tests
should be similar, especially for large samples and proportions close
to 0.5.
Mike
On Tue, Feb 4, 2014 at 2:50 AM, Amber Prakash <[email protected]> wrote:
> Hi,
>
> Thanks for those user commands...they help immensely. I was wondering if
> there is a similar user command for comparing percentages or proportions
> over two groups allowing multiple comparisons in one go?
>
> Thanks again.
>
> On 04/02/2014, Amber Prakash <[email protected]> wrote:
>> Hi,
>>
>> Thanks for those user commands...they help immensely. I was wondering if
>> there is a similar user command for comparing percentages or proportions
>> over two groups allowing multiple comparisons in one go?
>>
>> Thanks again.
>>
>>
>> On 3 February 2014 20:46, Michael Barker <[email protected]> wrote:
>>
>>> Thanks to Kit Baum, two new commands are available on the SSC archive:
>>> -dmout- and -pctrim-
>>>
>>> DMOUT: module to create difference-in-means tables.
>>> dmout produces difference-in-means tables. Means of each variable in
>>> varlist are compared across the values of the by() variable. dmout is
>>> useful when comparing several variables across two groups, such as
>>> treatment and control groups in an RCT, or attriters and non-attriters
>>> in longitudinal data.
>>>
>>> PCTRIM: module to trim variables based on percentiles.
>>> pctrim trims outlying observations based on percentile bounds. pctrim
>>> can operate on a varlist. The user can create an indicator variable
>>> marking outliers or recode them. Recode options include mean, median,
>>> upper/lower bounds, or system missing.
>>>
>>> pctrim is similar to the recent SSC addition, -winsor2-, by Lian
>>> Yu-jun. Both commands allow users to trim or winsorize several
>>> variables at once. The main difference is in their treatment of
>>> missing values. -winsor2- operates on each variable independently. The
>>> default behavior for pctrim first identifies the analysis sample, with
>>> no missing data, then operates on that sample only. pctrim can operate
>>> on variables independently with the missok option. Both pctrim and
>>> winsor2 are related to the original -winsor- command, by Nicholas J.
>>> Cox.
>>> *
>>> * 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/
>>>
>>
>>
>>
>> --
>> Well it seems I've finally, Thought of everything
>> I want to love,I want to feel,Find peace
>> Find the real :)
>> Skype with me at: amber.sky78
>>
>
>
> --
> Well it seems I've finally, Thought of everything
> I want to love,I want to feel,Find peace
> Find the real :)
> Skype with me at: amber.sky78
> *
> * 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/