Greg (version 1.4.1)

forestplotCombineRegrObj: Compares different scores in different regression objects.

Description

Creates a composite from different regression objects into one forestplot where you can choose the variables of interest to get an overview and easier comparison.

Usage

forestplotCombineRegrObj(
  regr.obj,
  variablesOfInterest.regexp,
  reference.names,
  rowname.fn,
  estimate.txt,
  exp = xlog,
  add_first_as_ref = FALSE,
  ref_txt = "ref.",
  ref_labels = c(),
  digits = 1,
  is.summary,
  xlab,
  zero,
  xlog,
  ...
)

Arguments

regr.obj

A list with all the fits that have variables that are to be identified through the regular expression

variablesOfInterest.regexp

A regular expression identifying the variables that are of interest of comparing. For instance it can be "(score|index|measure)" that finds scores in different models that should be compared.

reference.names

Additional reference names to be added to each model

rowname.fn

A function that takes a row name and sees if it needs beautifying. The function has only one parameter the coefficients name and should return a string or expression.

estimate.txt

The text of the estimate, usually HR for hazard ratio, OR for odds ratio

exp

Report in exponential form. Default true since the function was built for use with survival models.

add_first_as_ref

If you want that the first variable should be reference for that group of variables. The ref is a variable with the estimate 1 or 0 depending if exp() and the confidence interval 0.

ref_txt

Text instead of estimate number

ref_labels

If add_first_as_ref is TRUE then this vector is used for the model fits.

digits

Number of digits to use for the estimate output

is.summary

A vector indicating by TRUE/FALSE if the value is a summary value which means that it will have a different font-style

xlab

x-axis label

zero

Indicates what is zero effect. For survival/logistic fits the zero is 1 while in most other cases it's 0.

xlog

If TRUE, x-axis tick marks are to follow a logarithmic scale, e.g. for logistic regressoin (OR), survival estimates (HR), Poisson regression etc. Note: This is an intentional break with the original forestplot function as I've found that exponentiated ticks/clips/zero effect are more difficult to for non-statisticians and there are sometimes issues with rounding the tick marks properly.

...

Passed to forestplot()

See Also

Other forestplot wrappers: forestplotRegrObj()

Examples

org.par <- par("ask" = TRUE)

# simulated data to test
set.seed(10)
ftime <- rexp(200)
fstatus <- sample(0:1, 200, replace = TRUE)
cov <- data.frame(
  x1 = runif(200),
  x2 = runif(200),
  x3 = runif(200)
)

library(rms)
ddist <- datadist(cov)
options(datadist = "ddist")

fit1 <- cph(Surv(ftime, fstatus) ~ x1 + x2, data = cov)
fit2 <- cph(Surv(ftime, fstatus) ~ x1 + x3, data = cov)

forestplotCombineRegrObj(
  regr.obj = list(fit1, fit2),
  variablesOfInterest.regexp = "(x2|x3)",
  reference.names = c("First model", "Second model"),
  new_page = TRUE
)

modifyNameFunction <- function(x) {
  if (x == "x1") {
    return("Covariate A")
  }

  if (x == "x2") {
    return(expression(paste("My ", beta[2])))
  }

  return(x)
}

forestplotCombineRegrObj(
  regr.obj = list(fit1, fit2),
  variablesOfInterest.regexp = "(x2|x3)",
  reference.names = c("First model", "Second model"),
  rowname.fn = modifyNameFunction,
  new_page = TRUE
)

par(org.par)