methods-mca: Functionality for multiple correspondence analysis ('mca')...

methods-mcaR Documentation

Functionality for multiple correspondence analysis ('mca') objects

Description

These methods extract data from, and attribute new data to, objects of class "mca" from the MASS package.

Usage

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

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

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

## S3 method for class 'mca'
recover_inertia(x)

## S3 method for class 'mca'
recover_conference(x)

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

## S3 method for class 'mca'
recover_supp_rows(x)

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

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

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

Arguments

x

An ordination object.

Details

Multiple correspondence analysis (MCA) relies on a singular value decomposition of the indicator matrix X of a table of several categorical variables, scaled by its column totals. MASS::mca() returns the SVD factors UD and V as the row weights $fs, on which the inertia is conferred, and the column coordinates $cs. The row coordinates $rs are obtained as XV and accessible as supplementary elements.

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 singular value decomposition-based techniques: methods-cancor, methods-correspondence, methods-lda, methods-lra, methods-prcomp, methods-princomp, methods-svd

Other models from the MASS package: methods-correspondence, methods-lda

Examples

# table of admissions and rejections from UC Berkeley
class(UCBAdmissions)
ucb_admissions <- as.data.frame(UCBAdmissions)
ucb_admissions <-
  ucb_admissions[rep(seq(nrow(ucb_admissions)), ucb_admissions$Freq), -4L]
head(ucb_admissions)
# perform multiple correspondence analysis
ucb_admissions %>%
  MASS::mca() %>%
  as_tbl_ord() %>%
  # augment profiles with names, masses, distances, and inertias
  augment_ord() %>%
  print() -> admissions_mca

# recover row and column coordinates and row weights
head(get_rows(admissions_mca, elements = "score"))
get_cols(admissions_mca)
head(get_rows(admissions_mca))

# column-standard biplot of factor levels
admissions_mca %>%
  ggbiplot() +
  theme_bw() + theme_biplot() +
  geom_origin() +
  #geom_rows_point(stat = "unique") +
  geom_cols_point(aes(color = factor, shape = factor)) +
  geom_cols_text_repel(aes(label = level, color = factor),
                       show.legend = FALSE) +
  scale_color_brewer(palette = "Dark2") +
  scale_size_area(guide = "none") +
  labs(color = "Factor level", shape = "Factor level")

ordr documentation built on Oct. 21, 2022, 1:07 a.m.