[R] Partial R2 values calculated using different packages

[Yonghao]

Dear fellow R-users

I've always used Prof Harrell's rms package to calculate/visualize partial
R2 values from a standard regression analysis (below is a quick example on
how I've done so). Recently, I calcuated partial R2 values using the ppcor
and gRbase packages. As it turns out, ppcor and gRbase agree with each other
but the values generated from these packages tended to be greater than those
generated by the rms package.
 
Has anyone encountered a similar situation like mine?

Yonghao

++++++++++++++++++++++++++++++++++++
f <- ols(y ~ x1 + x2 + x3)
p <- plot(anova(f), what='partial R2')
p


--
View this message in context: http://r.789695.n4.nabble.com/Partial-R2-values-calculated-using-different-packages-tp4322671p4322671.html
Sent from the R help mailing list archive at Nabble.com.