Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: When to use Log (1+x) Transformation?


From   "Song" <[email protected]>
To   <[email protected]>
Subject   Re: st: When to use Log (1+x) Transformation?
Date   Sun, 6 Apr 2008 14:20:01 -0500

Maarten,

I understand your point. I plan to estimate the following model by 3SLS (reg3).

ln(Revenue in each country) = a0 + a1*time window + controls.
ln(time window) = b0 + b1*(expected) Revenue in each country + controls.

Time window is difference in launching time (in days) of a product between the US and international launch. Both revenue and time window are skewed, so I wanted to use log transformation. The problem is that time window includes a lot of zeros, so I am not sure what is the best method. Can you suggest a good method? Do you still think glm and spline will work in this situation?

Thank you,
Reo.

----- Original Message ----- From: "Maarten buis" <[email protected]>
To: <[email protected]>
Sent: Sunday, April 06, 2008 1:01 PM
Subject: Re: st: When to use Log (1+x) Transformation?



--- Song wrote:
I need to use log transfomation for both my dependent variable
and independent variables.
I always get rebellious as soon as someone says the he or
she
"must" or "needs to" use some technique or do some
transformation. Statistics
does not force you do anything. The
only thing you must do is make sense.
Statistics books are full
of rules of thumb and tips that will often help
making sensible
decision. It these "rules" that people often mean
when they say
that they "must" do something. I have two problems with
that:


1) You are the only one who is responsible for your decisions.

You are hiding
from that responsibility by saying that you "must"

do something (at least as long as you do not tell why this is the

case).

2) Such rules help in general but often do not apply to your

specific research
project. The only one who can see that is you.

This is a general rant, and I hope you do not take this personally.

It is just
that this issue is bothering me for some time, and you

just made this remark at
a time that I had time to write it up.

Also, I am a non-native speaker, so it
may very well be that I read

too much in the word need in this context

-- Maarten
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands


visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434

+31 20 5986715

http://home.fsw.vu.nl/m.buis/
-----------------------------------------


___________________________________________________________
Yahoo! For Good helps you make a difference

http://uk.promotions.yahoo.com/forgood/

*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index