Statalist


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

Re: st: Log of nonpositive numbers


From   ucb_gal <ucb_gal@yahoo.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Log of nonpositive numbers
Date   Sat, 29 Mar 2008 13:57:22 -0700 (PDT)

Surprisingly, income and wealth are not that highly correlated.  And this is much of the thrust of my study (that using income as our proxy of financial resources is missing much of the picture -- see Oliver and Shapiro's book Black Wealth/White Wealth and Dalton Conley's book Being Black, Living in the Red for discussions of this as it relates to race).

Income can be negative if you consider income from investments, which can be losses.  

In my dataset (NLSY97), there are only a few zero incomes, but there are a considerable number of negative wealth values.

----- Original Message ----
From: Daniel Schneider <daniel.schneider@stanford.edu>
To: statalist@hsphsun2.harvard.edu
Sent: Saturday, March 29, 2008 1:58:41 AM
Subject: Re: st: Log of nonpositive numbers

Income should not be negative. Wealth is not income. The studies that 
use something like this mostly use INCOME not WEALTH.

The question here is why you are using both wealth and income. In many 
(but not all cases) income is included as a general control variable 
reflecting social status etc. In that case you would probably be fine by 
just using income and perhaps using log(income+1) for those few cases 
that have zero income. I bet income and wealth are highly correlated 
anyways.



ucb_gal wrote:
> Hi,
> 
> I've seen this question asked a few other times, but I'm still a little unclear on what the considerations are in thinking this through.
> 
> I'm running logistic regressions with the log of income and wealth as independent variables.  I've seen this done often enough that I didn't really think twice about it.  But then I realized that while I don't have a ton of cases with exact 0 values in either variable, I do have a number of cases with negative wealth.  And all of these show up as missing now.
> 
> Am I mistaken in thinking that I've seen studies that use the log of income as predictors??
> 
> Thanks!
> 
> 
> 
> 
>       ____________________________________________________________________________________
> Like movies? Here's a limited-time offer: Blockbuster Total Access for one month at no cost. 
> http://tc.deals.yahoo.com/tc/blockbuster/text4.com
> *
> *   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/





      ____________________________________________________________________________________
Never miss a thing.  Make Yahoo your home page. 
http://www.yahoo.com/r/hs
*
*   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index