SimpleRmsAnova: A simpler latex output of the latex.anova.rms

In gforge/Greg: Regression Helper Functions

A simpler latex output of the latex.anova.rms

Description

The original problem is that the anova default function output is very detailed and cause a complaint in Sweave/knitr that \hbox is overfull. It basically changes capitalized TOTAL, TOTAL INTERACTION and TOTAL NONLINEAR INTERACTION into lower case letters. It also deletes the (Factor + Higher Order Factors).

Usage

simpleRmsAnova(
  anova_output,
  subregexps,
  digits = 4,
  pval_lim.sig = 10^-4,
  rowlabel = "",
  ...
)

## S3 method for class 'simpleRmsAnova'
print(x, html = TRUE, ...)

Arguments

anova_output	An object from the anova() function
subregexps	A 2 column matrix with sub() regular expressions to search for and their substitutions. The regular expression should be located in column 1 and the substitution in column 2.
digits	Number of digits in using the round
pval_lim.sig	The threshold before setting "<", default is < 0.0001
rowlabel	The label of the rows
...	Passed on to latex() or htmlTable
x	The output object from the SimpleRmsAnova function
html	If HTML output through the htmlTable should be used instead of traditional latex() function

Value

void See the latex() function

Examples

# ** Borrowed code from the lrm example **

# Fit a logistic model containing predictors age, blood.pressure, sex
# and cholesterol, with age fitted with a smooth 5-knot restricted cubic
# spline function and a different shape of the age relationship for males
# and females.

library(rms)
n <- 1000 # define sample size
set.seed(17) # so can reproduce the results
age <- rnorm(n, 50, 10)
blood.pressure <- rnorm(n, 120, 15)
cholesterol <- rnorm(n, 200, 25)
sex <- factor(sample(c("female", "male"), n, TRUE))
label(age) <- "Age" # label is in Hmisc
label(cholesterol) <- "Total Cholesterol"
label(blood.pressure) <- "Systolic Blood Pressure"
label(sex) <- "Sex"
units(cholesterol) <- "mg/dl" # uses units.default in Hmisc
units(blood.pressure) <- "mmHg"

# To use prop. odds model, avoid using a huge number of intercepts by
# grouping cholesterol into 40-tiles

# Specify population model for log odds that Y = 1
L <- .4 * (sex == "male") + .045 * (age - 50) +
     (log(cholesterol - 10) - 5.2) * (-2 * (sex == "female") + 2 * (sex == "male"))
# Simulate binary y to have Prob(y = 1) = 1/[1+exp(-L)]
y <- ifelse(runif(n) < plogis(L), 1, 0)
cholesterol[1:3] <- NA # 3 missings, at random

ddist <- datadist(age, blood.pressure, cholesterol, sex)
options(datadist = "ddist")

fit_lrm <- lrm(y ~ blood.pressure + sex * (age + rcs(cholesterol, 4)),
     x = TRUE, y = TRUE
)

a_out <- anova(fit_lrm,
     dec.F = 1,
     ss = FALSE
)

simpleRmsAnova(a_out,
     subregexps = rbind(
          c("age", "Age"),
          c("cholesterol", "Cholesterol"),
          c("sex", "Sex")
     ),
     caption = "Anova output for a logistic regression model"
)

gforge/Greg documentation built on Feb. 3, 2024, 5:37 a.m.