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: xtmixed postestimation: correlation between dependent and independent
From
megan rossi <[email protected]>
To
"[email protected]" <[email protected]>
Subject
Re: st: xtmixed postestimation: correlation between dependent and independent
Date
Sun, 17 Mar 2013 21:27:10 +1000
Not as such but the surgery results in an increase in both variables (serum markers) so I'd assume if they are correlated it would be more apparent at high concentrations ie. year 1 and 2
Sent from my iPhone
On 17/03/2013, at 1:35 PM, "David Hoaglin" <[email protected]> wrote:
> As I read the initial description, the data have a bivariate dependent
> variable (a and b) and no independent variable (other than time).
>
> Do the data show evidence that the surgery alters the correlation
> between a and b?
>
> David Hoaglin
>
> On Sat, Mar 16, 2013 at 10:57 PM, JVerkuilen (Gmail)
> <[email protected]> wrote:
>> On Sat, Mar 16, 2013 at 10:46 PM, megan rossi <[email protected]> wrote:
>>> Hi All
>>> With xtmixed is there a post estimate command that will give you the correlation coefficient between the dependent and independent variable? The intraclass correlation gives you the correlation between the dependent and the levels, but I am after the dependant and independent correlation.<<
>>
>> Essentially the strength of relationship is measured by the regression
>> coefficient. This asymmetry is part of what a regression does.
>
> *
> * 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/