methods-lm {ordr}

Functionality for linear model objects

Description

These methods extract data from, and attribute new data to, objects of class "lm", "glm", and "mlm" as returned by stats::lm() and stats::glm().

Usage

## S3 method for class 'lm'
as_tbl_ord(x)

## S3 method for class 'lm'
recover_rows(x)

## S3 method for class 'lm'
recover_cols(x)

## S3 method for class 'lm'
recover_coord(x)

## S3 method for class 'lm'
recover_aug_rows(x)

## S3 method for class 'lm'
recover_aug_cols(x)

## S3 method for class 'lm'
recover_aug_coord(x)

## S3 method for class 'glm'
recover_aug_rows(x)

## S3 method for class 'mlm'
recover_rows(x)

## S3 method for class 'mlm'
recover_cols(x)

## S3 method for class 'mlm'
recover_coord(x)

## S3 method for class 'mlm'
recover_aug_rows(x)

## S3 method for class 'mlm'
recover_aug_cols(x)

## S3 method for class 'mlm'
recover_aug_coord(x)

Arguments

x

An ordination object.

Value

The recovery generics ⁠recover_*()⁠ return core model components, distribution of inertia, supplementary elements, and intrinsic metadata; but they require methods for each model class to tell them what these components are.

The generic as_tbl_ord() returns its input wrapped in the 'tbl_ord' class. Its methods determine what model classes it is allowed to wrap. It then provides 'tbl_ord' methods with access to the recoverers and hence to the model components.

See Also

Other methods for idiosyncratic techniques: methods-kmeans

Other models from the stats package: methods-cancor, methods-cmds, methods-factanal, methods-kmeans, methods-prcomp, methods-princomp

Examples

# Motor Trend design and performance data
head(mtcars)
# regression analysis of performance measures on design specifications
mtcars_centered <- scale(mtcars, scale = FALSE)
mtcars_centered %>%
  as.data.frame() %>%
  lm(formula = mpg ~ wt + cyl) %>%
  print() -> mtcars_lm

# wrap as a 'tbl_ord' object
(mtcars_lm_ord <- as_tbl_ord(mtcars_lm))
# augment everything with names, predictors with observation stats
augment_ord(mtcars_lm_ord)
# calculate influences as the squares of weighted residuals
mutate_rows(augment_ord(mtcars_lm_ord), influence = wt.res^2)

# regression biplot with performance isolines
mtcars_lm_ord %>%
  augment_ord() %>%
  mutate_cols(center = attr(mtcars_centered, "scaled:center")[name]) %>%
  mutate_rows(influence = wt.res^2) %T>% print() %>%
  ggbiplot(aes(x = wt, y = cyl, intercept = `(Intercept)`)) +
  #theme_biplot() +
  geom_origin(marker = "circle", radius = unit(0.02, "snpc")) +
  geom_rows_point(aes(color = influence)) +
  geom_cols_vector() +
  geom_cols_isoline(aes(center = center), by = .5, hjust = -.1) +
  ggtitle(
    "Weight isolines with data colored by importance",
    "Regressing gas mileage onto weight and number of cylinders"
  )