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: Creating categories of Continuous Variable
From
Richard Williams <[email protected]>
To
[email protected], [email protected]
Subject
Re: st: Creating categories of Continuous Variable
Date
Wed, 12 Mar 2014 20:15:06 -0500
You can check out the mkspline command. Besides the Stata docs, see
http://maartenbuis.nl/presentations/bonn09.pdf
http://www.stata.com/meeting/4nasug/RCsplines.pdf
http://www.ats.ucla.edu/stat/stata/faq/piecewise.htm
http://www.ats.ucla.edu/stat/stata/faq/nl_optimal_knots.htm
There are lots of other ways to deal with nonlinear relationships,
e.g. If you suspect a curvilinear relationship you may wish to add an x^2 term.
http://essedunet.nsd.uib.no/cms/topics/multilevel/ch1/5.html
At 05:11 PM 3/12/2014, Satyen Dubey wrote:
Dear All,
I am examining the effect of "Y" variable on certain firm financial risk
variables. I am using OLS model to do this. My model looks like following.
Firm Risk Variable = b+ "Y" + other variables
"Y" is a continuous variable and if theory holds should reduce firm risk.
Now i suspect that the effect of "Y" may not be the same for different
levels of "Y" e.g. for low values of "Y" the effect could be negative and
for high values (very extensive use) the effect could be positive.
To do this analyse I have created 5 dummy variables.
1) "Y" <= 20% use then 1 otherwise 0
2) 20% < "Y" <= 40% then 1 else 0
3) 40% < "Y" <= 60% then 1 else 0
4) 60% < "Y" <= 80% then 1 else 0
5) "Y" > 80% use then 1 otherwise 0
After examine the following model.
Firm Risk Variable = b+ "Y" *(1)+ "Y" *(2)+ "Y" *(3)+ "Y" *(4)+ "Y" *(5) +
other variables
My Questions is:
Is this correct way to do this?
Is there any other way i can examine this?
Thanks in advance.
-----
Thanks & Regards,
Satyen Dubey
--
View this message in context:
http://statalist.1588530.n2.nabble.com/Creating-categories-of-Continuous-Variable-tp7580491.html
Sent from the Statalist mailing list archive at Nabble.com.
*
* 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/
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: [email protected]
WWW: http://www.nd.edu/~rwilliam
*
* 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/