plot_observation.pseudobeta function

plot_pseudobeta.newObservation

Generates a visual representation comparing the pseudobeta values derived from the Coxmos model with the values of a new observation. This function provides insights into how the new observation aligns with the established model, offering a graphical comparison of the pseudobeta directions.

plot_observation.pseudobeta(
  model,
  observation,
  error.bar = TRUE,
  onlySig = TRUE,
  alpha = 0.05,
  zero.rm = TRUE,
  txt.x.angle = 0,
  title = NULL,
  title_size_text = 15,
  subtitle = NULL,
  subtitle_size_text = 12,
  legend.position = "right",
  legend_size_text = 12,
  x_axis_size_text = 10,
  y_axis_size_text = 10,
  label_x_axis_size = 10,
  label_y_axis_size = 10,
  top = NULL,
  auto.limits = TRUE,
  show.betas = FALSE
)

Arguments

• model: Coxmos model.
• observation: Numeric matrix or data.frame. New explanatory variables (raw data) for one observation. Qualitative variables must be transform into binary variables.
• error.bar: Logical. Show error bar (default: TRUE).
• onlySig: Logical. Compute pseudobetas using only significant components (default: TRUE).
• alpha: Numeric. Numerical values are regarded as significant if they fall below the threshold (default: 0.05).
• zero.rm: Logical. Remove variables with a pseudobeta equal to 0 (default: TRUE).
• txt.x.angle: Numeric. Angle of X text (default: 0).
• title: Character. Plot title (default: NULL).
• title_size_text: Numeric. Text size for title (default: 15).
• subtitle: Character. Plot subtitle (default: NULL).
• subtitle_size_text: Numeric. Text size for subtitle (default: 12).
• legend.position: Character. Legend position. Must be one of the following: "top", "bottom", "right" or "left (default: "right").
• legend_size_text: Numeric. Text size for legend title (default: 12).
• x_axis_size_text: Numeric. Text size for x axis (default: 10).
• y_axis_size_text: Numeric. Text size for y axis (default: 10).
• label_x_axis_size: Numeric. Text size for x label axis (default: 10).
• label_y_axis_size: Numeric. Text size for y label axis (default: 10).
• top: Numeric. Show "top" first variables with the higher pseudobetas in absolute value. If top = NULL, all variables are shown (default: NULL).
• auto.limits: Logical. If "auto.limits" = TRUE, limits are detected automatically (default: TRUE).
• show.betas: Logical. Show original betas (default: FALSE).

Returns

A list of four elements: plot: Linear prediction per variable. lp.var: Value of each linear prediction per variable. norm_observation: Observation normalized using the model information. observation: Observation used.

Details

The function plot_pseudobeta.newObservation is designed to visually compare the pseudobeta values from the Coxmos model with those of a new observation. The generated plot is based on the ggplot2 framework and offers a comprehensive view of the relationship between the model's pseudobeta values and the new observation's values.

The function first checks the validity of the provided model and ensures that it belongs to the appropriate class. Depending on the type of the model (either PLS or MB Coxmos methods).

For the actual plotting, the function computes the linear predictor values for the new observation and juxtaposes them with the pseudobeta values from the model. If the show.betas parameter is set to TRUE, the original beta values are also displayed on the plot. Error bars can be included to represent the variability in the pseudobeta values, providing a more comprehensive view of the data's distribution.

The resulting plot serves as a valuable tool for researchers and statisticians to visually assess the alignment of a new observation with an established Coxmos model, facilitating better interpretation and understanding of the data in the context of the model.

Examples

data("X_proteomic")
data("Y_proteomic")
set.seed(123)
index_train <- caret::createDataPartition(Y_proteomic$event, p = .5, list = FALSE, times = 1)
X_train <- X_proteomic[index_train,1:50]
Y_train <- Y_proteomic[index_train,]
X_test <- X_proteomic[-index_train,1:50]
Y_test <- Y_proteomic[-index_train,]
splsicox.model <- splsicox(X_train, Y_train, n.comp = 2, penalty = 0.5, x.center = TRUE,
x.scale = TRUE)
plot_observation.pseudobeta(model = splsicox.model, observation = X_test[1,,drop=FALSE])

Author(s)

Pedro Salguero Garcia. Maintainer: pedsalga@upv.edu.es