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]

st: RE: Regress question group omitted


From   "Sarah Edgington" <[email protected]>
To   <[email protected]>
Subject   st: RE: Regress question group omitted
Date   Fri, 1 Jun 2012 12:25:33 -0700

Lars,
If charge time is always the same for all members of a given group you can't
include both chargetime and group in your regression because group and
chargetime are perfectly correlated.  One way to think about it is that
adding group to the regression doesn't add any new information.  You can
already determine what group an individual is in by looking at the value for
chargetime.

Hope that helps.

-Sarah


-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Lars Folkestad
Sent: Friday, June 01, 2012 8:38 AM
To: [email protected]
Subject: st: Regress question group omitted

Dear Statalist

I have a dataset containing two variables (continious) that record time in
seconds to an event. I also have a continious variabe (charge time) that is
group dependente and a grouping variable

First second charge group
16.      145.     8.          1
12.      157.      5.         2

And so forth

I want to compare time to first event between The two groups, but takeing
into account The differences in charge time.

So first a stats question and then a Stata question

1. Would it be correct to just substract The charge time variable from The
time to first event variable (both in sec) where the time to first event is
meassured and The charge time is fixed by group (its 8s for group 1 and 5s
for group 2). This so that The difference between groups found, are not due
to The difference in charge time but other factors. Or do i need a multible
linier regression model?

2) when doing a regression model using Stata 12 using

regress first chargetime i.group

In the results group is omitted why is this? 

Thank you
Lars
*
*   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