model_analysis: Find Accepted Model From ICP Object
In Laksafoss/ICPSurv: Invariant Causal Prediction for Survival Data

Description Usage Arguments Details Value See Also Examples

View source: R/ICP-variable_analysis.R

The model_analysis function takes an ICP object and a significance level and outputs the accepted model at this level.

1	model_analysis(x, level = 0.05, gof = 0.01)

`x`	An ICP object
`level`	The significance level required for a model to be considered invariant. The higher the significance `level` the stronger the requirements for godness of fit to attain 'invariance' status.
`gof`	If no set of variables (including the empty set) leads to a p-value larger than the goodness-of-fit cutoff `gof`, the whole model will be rejected. If the model is correct, this will happen with a probability of gof and this option protects again making statements when the model is obviously not suitable for the data.

The function model_analysis takes an ICP object and a significance level and outputs the accepted model at this level:

Accepted X columns = ∩_{{S: H_0,S accepted}} S. See ICP for more details on the hypotheses (H_0,S).

The gof parameter protects against making statements when the model is obviously not suitable for the data. If no model reaches the threshold gof significance level, i.e. the p-values for (H_0,S) are all smaller then gof, we report that there is no evidence for an invariant set.

This function is also used internally in the ICP function itself if ICP is called with level specified.

model_analysis returns an object of class "model_analysis" containing the following components:

`gof`	goodness-of-fit cufoff.
`level`	significance level of hypothesis tests.
`accepted.model`	the accepted model.
`empty.message`	if the empty set is returned as `accepted.model` then `empty.message` will give detailes.
`call`	the matched call.

The model_analysis function is also used internally in the ICP function itself if ICP is called with level specified.

variable_analysis is another function for summarizing ICP objects.

n <- 100
E <- sample(5L, n, replace = TRUE)
X <- data.frame(X1 = rnorm(n, E, 1), X2 = rnorm(n, 3, 1))
Y <- rnorm(n, X$X1, 1)

obj <- ICP(Y, X, E, fullAnalysis = TRUE)
model_analysis(obj, level = 0.05, gof = 0.15)