RVAideMemoire (version 0.9-7)

reg.slpcomp: Comparison of simple linear regression slopes

Description

Test for equality of slopes of several simple regression lines. The function returns the confidence interval of each slope and perfoms pairwise comparisons.

Usage

reg.slpcomp(formula, data=NULL, conf.level = 0.95, p.method = "fdr")

Arguments

formula

a formula of the form y ~ x | f, where y and x give the dependent and independent variable, respectively, and f is a factor giving levels to be compared.

data

an optional data frame containing the variables in the formula formula. By default the variables are taken from environment(formula).

conf.level

confidence level.

p.method

method for p-values correction. See help of the p.adjust() function.

Value

• data
  variables name.
• conf.level
  confidence level.
• coeffs
  slope of each regression line.
• coeffs.tab
  slope and confidence interval of each regression line.
• p.method
  method for p-value correction.
• df
  degrees of freedom of each comparison.
• t
  test statistics.
• p.value
  corrected p-values.
• multcomp
  data frame of results.

See Also

lm

Examples

covariable<-rep(1:30,3)
variable<-c(seq(1,10,9/29)+rnorm(30,0,3),seq(1,30,1)+rnorm(30,0,3),seq(-1,-80,-79/29)+rnorm(30,0,3))
factor<-factor(rep(LETTERS[1:3],each=30))
reg.slpcomp(variable~covariable|factor)