create_fp_terms {mfp2}

Helper to create overview table of fp terms

Description

To be used in fit_mfp().

Usage

create_fp_terms(fp_powers, acdx, df, select, alpha, criterion)

Arguments

fp_powers

powers of the created FP terms.

acdx

a logical vector of length nvars indicating which continuous variables should undergo the approximate cumulative distribution (ACD) transformation.

df

a numeric vector of length nvars of degrees of freedom.

select

a numeric vector of length nvars indicating significance levels for backward elimination.

alpha

a numeric vector of length nvars indicating significance levels for tests between FP models of different degrees.

criterion

a character string defining the criterion used to select variables and FP models of different degrees.

Value

Dataframe with overview of all fp terms. Each row represents a variable, with rownames giving the name of the variable. Variables with acd transformation are prefixed by A_ by the print and summary methods. The dataframe comprises the following columns:

• df_initial: initial degrees of freedom.

• select: significance level for backward elimination.

• alpha: significance level for fractional polyomial terms.

• selected: logical value encoding presence in the model.

• df_final: final estimated degrees of freedom.

• acd: logical value encoding use of ACD transformation.

• powerN: one or more columns with the final estimated fp powers (numbered 1 to N).