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 at the end of May, and its replacement, statalist.org is already up and running.


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

Re: st: significance of differences


From   Nick Cox <njcoxstata@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: significance of differences
Date   Fri, 1 Jun 2012 09:01:27 +0100

OK. I suggest that is usually still better to look at the entire
relationship between the two variables and not degrade one or look at
extreme quantile-based groups without looking at the others too.

Nick

On Fri, Jun 1, 2012 at 8:56 AM, "Fabian Schönenberger" <sch.f@gmx.ch> wrote:
> Many thanks. Works perfectly.
>
> Exactly, varquintile is a quintile-classed division of one factor; assigning for each observation 1 to 5.
> The ttest is conducted for other variables, but under the condition that the means of this variable for quintile 1 and quintile 5 of the quintile variable are considered.
>
> The reason is simple: I just want to find out, if my quintile-parameter leads to significant differences in other fundamental factors for companies.
>
> Many thanks, also for your previous feedbacks!
> Fabian
>
>
> -------- Original-Nachricht --------
>> Datum: Fri, 1 Jun 2012 07:48:01 +0100
>> Von: Nick Cox <njcoxstata@gmail.com>
>> An: statalist@hsphsun2.harvard.edu
>> Betreff: Re: st: significance of differences
>
>> I presume that -varquintile- is a quintile-classed division of one
>> variable, say x, and -var- is another variable, say y.
>>
>> Without knowing any details, I wonder if this is a particularly good
>> test to use.
>>
>> (I certainly hope that -varquintile- is _not_ a division of the same
>> variable, as printed significance levels surely won't apply, for
>> several good reasons.)
>>
>> That said, Stata will do what I think you want with
>>
>> ttest var if inlist(varquintile, 1, 5), by(varquintile)
>>
>> Note that
>>
>> ttest var if varquintile==1 == var if varquintile==5
>>
>> can't be legal because no Stata command allows more than one -if-
>> condition.
>>
>> Nick
>>
>> On Fri, Jun 1, 2012 at 7:26 AM, "Fabian Schönenberger" <sch.f@gmx.ch>
>> wrote:
>>
>> > I want to compare if the difference of a specific variable between the
>> first and fifth quintile is significant.
>> > I tried ttest with if; ttest var if varquintile==1 == var if
>> varquintile==5
>> > However, this does not work. Any suggestions?
>>
>> *
>> *   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/
>
> --
> NEU: FreePhone 3-fach-Flat mit kostenlosem Smartphone!
> Jetzt informieren: http://mobile.1und1.de/?ac=OM.PW.PW003K20328T7073a
> *
> *   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index