Use -gen double varname = r(mean)- instead of -gen varname = r(mean)-. In my example the mean of price three deviates from zero in the fourteenth decimal place, which is as close to zero as you could hope to get in a normal computer program.
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting adress:
Buitenveldertselaan 3 (Metropolitan), room Z214
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
-----Original Message-----
From: [email protected] [mailto:[email protected]]On Behalf Of Raoul C Reulen
Sent: vrijdag 25 november 2005 10:30
To: [email protected]
Subject: st: RE: RE: variable mean and r(mean), why do they differ?
Thanks Maarten,
In my analysis it does make a difference. I have to calculate numerous
mean values, sum them to obtain one variable and then I have to multiply
this by a large factor before I can use it. Any suggestions? Thanks
again.
Raoul
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Maarten Buis
Sent: 25 November 2005 09:08
To: [email protected]
Subject: st: RE: variable mean and r(mean), why do they differ?
Raoul:
Your hunch seems to be correct:
sysuse auto, clear
sum price
gen price2 = price - r(mean)
gen double price3 = price - r(mean)
sum price2 price3
However note that the difference in the highest and lowest price is
aprox. 1,200 dollar and that price2 is different from zero in only the
fifth decimal place, so I would consider that zero for any practical
application.
HTH,
Maarten
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting adress:
Buitenveldertselaan 3 (Metropolitan), room Z214
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]]On Behalf Of Raoul C
> Reulen
> Sent: vrijdag 25 november 2005 9:43
> To: [email protected]
> Subject: st: variable mean and r(mean), why do they differ?
>
> If I want to save the mean of a variable into a new variable, I would
first:
> sum var1
> gen var2, r(mean)
> But if I subtract var1-var2, the outcome is almost, but not exactly
"0". How can make sure that both means are equal?
> I have tried .round, .int. , but that doesn't work. Do I have to
change the storage type? Thanks for the advice.
*
* 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/
*
* 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/
