Fit the declared model with rms — cp

Builds the formula from the project, fits it with rms::lrm(), and keeps everything a later step needs: the fit, its datadist, the formula it was actually given, a prediction schema and a fingerprint of the coefficients.

Usage

cp_model(project, cohort, nonlinear = NULL, interactions = NULL, knots = 4L)

Arguments

project: A cp_project() configuration.
cohort: The development data. When the project declares a split, only rows below split_at are used, and the held-out rows are returned untouched for later scoring.
nonlinear: Character vector of continuous predictors to fit with restricted cubic splines.
interactions: List of length-two character vectors naming prespecified interactions. Exploratory discovery is not this argument.
knots: Knots for each spline term.

Value

An object of class cp_model.

Details

x and y are kept on the fit, because validation and calibration need them and a fit without them fails later for reasons that do not name this decision.

Strong hierarchy is enforced rather than assumed: an interaction is refused unless both of its main effects are in the project's predictors. The specification requires that an interaction only be usable with its constituent main effects, and a formula is the last place to find out.

Examples

cohort <- cp_synthetic_cohort(n = 300, seed = 1)
project <- cp_project("uds", "event",
                      c("age", "bmi", "sex", "prior_uti"),
                      cohort = cohort)
fit <- cp_model(project, cohort, nonlinear = "age",
                interactions = list(c("prior_uti", "sex")))
fit
#> <cp_model: uds>
#>   formula    .cp_y ~ rms::rcs(age, 4) + bmi + sex + prior_uti + prior_uti:sex
#>   developed  300 rows, 28 events
#>   parameters 7 non-intercept
#>   apparent C 0.7126
#>   fingerprint 97af98a72772f7d7