Build regression model from a set of candidate predictor variables by removing predictors based on akaike information criterion, in a stepwise manner until there is no variable left to remove any more.

ols_stepaic_backward(model, ...)

# S3 method for default
ols_stepaic_backward(model, details = FALSE, ...)

# S3 method for ols_stepaic_backward
plot(x, ...)

Arguments

model

An object of class lm; the model should include all candidate predictor variables.

...

Other arguments.

details

Logical; if TRUE, will print the regression result at each step.

x

An object of class ols_stepaic_backward.

Value

ols_stepaic_backward returns an object of class "ols_stepaic_backward". An object of class "ols_stepaic_backward" is a list containing the following components:

steps

total number of steps

predictors

variables removed from the model

aics

akaike information criteria

ess

error sum of squares

rss

regression sum of squares

rsq

rsquare

arsq

adjusted rsquare

References

Venables, W. N. and Ripley, B. D. (2002) Modern Applied Statistics with S. Fourth edition. Springer.

See also

Other variable selection procedures: ols_step_all_possible, ols_step_backward, ols_step_best_subset, ols_step_forward, ols_stepaic_both, ols_stepaic_forward

Examples

# NOT RUN {
# stepwise backward regression
model <- lm(y ~ ., data = surgical)
ols_stepaic_backward(model)
# }
# NOT RUN { # stepwise backward regression plot model <- lm(y ~ ., data = surgical) k <- ols_stepaic_backward(model) plot(k) # }