rms Specifications for Models

Prints the design specifications, e.g., number of parameters for each factor, levels of categorical factors, knot locations in splines, pre-transformations, etc.

specs(fit, ...)
# S3 method for class 'rms'
specs(fit, long=FALSE, ...)

# S3 method for class 'specs.rms'
print(x, ...)

Arguments

fit

a fit object created with the rms library in effect

x

an object returned by specs

long

if TRUE, causes the plotting and estimation limits to be printed for each factor

...

ignored

Value

a list containing information about the fit and the predictors as elements

Author

Frank Harrell
Department of Biostatistics, Vanderbilt University
fh@fharrell.com

See also

rms, rms.trans, latexrms, datadist

Examples

set.seed(1)
blood.pressure <- rnorm(200, 120, 15)
dd <- datadist(blood.pressure)
options(datadist='dd')
L <- .03*(blood.pressure-120)
sick <- ifelse(runif(200) <= plogis(L), 1, 0)
f <- lrm(sick ~ rcs(blood.pressure,5))
#> Error in Design(data, formula = formula): dataset dd not found for options(datadist=)
specs(f)    # find out where 5 knots are placed
#> Error: object 'f' not found
g <- Glm(sick ~ rcs(blood.pressure,5), family=binomial)
#> Error in Design(mf, formula = formula): dataset dd not found for options(datadist=)
specs(g,long=TRUE)
#> Error: object 'g' not found
options(datadist=NULL)