[R] summary linear regression

[Gorka Merino]

>>Good morning,
>>
>>I am a PhD student in Barcelona working with R. My question is about the 
>>summary of linear regressions.
>>The output of that summary gives some statistical parameters of the 
>>regression. One of them is the R-squared. In the help menu i have read 
>>that the manner to calculate the R-squared is
>>
>>R^2 = 1 - Sum(R[i]^2) / Sum((y[i]- y*)^2), and  when the linear 
>>regression is forced to start at the point (0,0)  y* is 0.
>>
>>My question is if the R-squared obtained when the linear regression 
>>crosses the origin has the same meaning as when it does with an 
>>intercept. I'm faced to a theoretical model which brings some values for 
>>a variable that compared to the observed ones gives some R*squared of 
>>0.32 when the regression has an intercept and 0.7 when it is forced to 
>>cross the origin.
>>To sum up, it may be stated that the theoretical methodolgy followed 
>>explains the 70% of  of the observed variance?
>>
>>Thank you very much.
>>
>>Gorka Merino.

Gorka Merino	
Institut de Ciències del Mar, CMIMA-CSIC
Psg. Marítim de la Barceloneta 37-49
08003-BARCELONA (Spain)

Tel.: (34) 932 30 95 48
e-mail: gmerino at icm.csic.es

CMIMA:
Tel.: (34) 932 30 95 00
Fax:  (34) 932 30 95 55