r - `rms::ols()`: how to fit a model without intercept -


i'd use ols() (ordinary least squares) function rms package multivariate linear regression, not calculate intercept. using lm() syntax like:

model <- lm(formula = z ~ 0 + x + y, data = mydata) 

where 0 stops calculating intercept, , 2 coefficients returned, on x , other y. how do when using ols()? trying

model <- ols(formula = z ~ 0 + x + y, data = mydata) 

did not work, still returns intercept , coefficient each x , y.

here link csv file

it has 5 columns. example, can use first 3 columns:

model <- ols(formula = corren ~ inten_anti_ncp + inten_par_ncp, data = ccd) 

thanks!

rms::ols uses rms:::design instead of model.frame.default. design called default of intercept = 1, there no (obvious) way specify there no intercept. assume there reason this, can try changing ols using trace.


Comments

Popular posts from this blog

hibernate - How to load global settings frequently used in application in Java -

python 3.x - Mapping specific letters onto a list of words -

objective c - Ownership modifiers with manual reference counting -