Computes the standardized (regression) coefficients, also called beta coefficients or beta weights, to quantify the importance (the effect) of the predictors on the dependent variable in a multiple regression analysis where the variables are measured in different units.
scaled.coef(object, ...)
# S3 method for default
scaled.coef(object, scale.response = TRUE, complete = FALSE, ...)an object for which the extraction of model coefficients is meaningful.
further arguments passed to or from other methods.
logical indicating if the response variable should be standardized.
for the default (used for lm, etc) and aov methods: logical indicating if the full coefficient vector should be returned also in case of an over-determined system where some coefficients will be set to NA.
A named vector with the scaled coefficients.
The beta weights are the coefficient estimates resulting from a regression
analysis where the underlying data have been standardized so that the
variances of dependent and explanatory variables are equal to 1.
Therefore, standardized coefficients are unitless and refer to how many
standard deviations a dependent variable will change, per standard deviation
increase in the predictor variable.
See https://en.wikipedia.org/wiki/Standardized_coefficient or
QuantPsyc::lm.beta.
Based on QuantPsyc::lm.beta.
fit <- lm(fidelida ~ velocida + calidadp, hbat)
coef(fit)
#> (Intercept) velocida calidadp
#> 1.334685 7.973594 3.336468
scaled.coef(fit)
#> velocida calidadp
#> 0.6664119 0.5146444
fit2 <- lm(scale(fidelida) ~ scale(velocida) + scale(calidadp), hbat)
coef(fit2)
#> (Intercept) scale(velocida) scale(calidadp)
#> -4.566135e-16 6.664119e-01 5.146444e-01
fit3 <- lm(fidelida ~ scale(velocida) + scale(calidadp), hbat)
coef(fit3)
#> (Intercept) scale(velocida) scale(calidadp)
#> 58.100000 5.975153 4.614382
scaled.coef(fit, scale.response = FALSE)
#> (Intercept) velocida calidadp
#> 58.100000 5.975153 4.614382