I'm trying to extract 1/4 standardized regression coefficients using lm.beta, and hitting a snag. Usually I would just code model$coefficients[x]
, but I have always been pulling unstandardized coefficients before. For some reason, it does not appear to work on the standardized version. I am getting all kinds of weird results. Is there another way to do this? Sorry if this is a dumb question, but I am confused as to why this would be a problem. Below is the code chunk. It's just a standardized regression table, and I need one value.
top_dog=lm.beta(new_lreg)
CodePudding user response:
Fitting Regression And Getting Betas
You didn't provide data (I advise doing that next time) but I have used the iris
dataset native to R to show you how it can be done. First fit a regression:
#### Run Iris Regression ####
iris.lm <- lm(Petal.Length ~ Sepal.Width Sepal.Length,
data = iris)
Then save the betas as an object:
#### Save Betas as Object ####
beta.iris <- lm.beta::lm.beta(iris.lm)
Printing Beta Coefficients
You can call the coefficients this way:
#### Call Them ####
beta.iris$standardized.coefficients
Which will give you this printout:
(Intercept) Sepal.Width Sepal.Length
NA -0.3305168 0.8328950
If you want a specific coefficient you do so like this:
#### Select Which ####
beta.iris$standardized.coefficients[2]
Which will give you the Sepal.Width beta:
Sepal.Width
-0.3305168