Coxmos (version 1.1.2)

plot_cox.event: plot_cox.event

Description

Visualizes the distribution of events based on a Coxmos model's predictions. The function provides both density and histogram plots to elucidate the event distribution, which can be instrumental in understanding the model's behavior across different prediction types.

Usage

plot_cox.event(model, type = "lp", n.breaks = 20)

Value

A list containing three elements: df: A data.frame with the computed predictions based on the specified type and the corresponding event status. plot.density: A ggplot object representing the density plot of the event distribution, with separate curves for censored and occurred events. plot.histogram: A ggplot object representing the histogram of the event distribution, with bins stacked by event type.

Arguments

model

Coxmos model.

type

Character. Prediction type: "lp", "risk", "expected" or "survival" (default: "lp").

n.breaks

Numeric. If BREAKTIME is NULL, "n.breaks" is the number of time-break points to compute (default: 20).

Author

Pedro Salguero Garcia. Maintainer: [e-mail]

Details

The function takes in a Coxmos model and, based on the specified prediction type (lp, risk, expected, or survival), computes the respective predictions. The lp (linear predictor) is the default prediction type. The density and histogram plots are then generated to represent the distribution of events (censored or occurred) concerning these predictions.

The density plot provides a smoothed representation of the event distribution, with separate curves for censored and occurred events. This visualization can be particularly useful to discern the overall distribution and overlap between the two event types.

The histogram, on the other hand, offers a binned representation of the event distribution. Each bin's height represents the count of observations falling within that prediction range, stacked by event type. This visualization provides a more granular view of the event distribution across different prediction values.

It's imperative to note that the models should be run with the returnData = TRUE option to ensure the necessary data is available for plotting.

Examples

data("X_proteomic")
data("Y_proteomic")
X <- X_proteomic[,1:50]
Y <- Y_proteomic
splsicox.model <- splsicox(X, Y, n.comp = 2, penalty = 0.5, x.center = TRUE, x.scale = TRUE)
plot_cox.event(splsicox.model)