RVAideMemoire (version 0.9-7)

reg.intcomp: Common slope and comparison of simple linear regression intercepts

Description

Compute the common slope of parallel linear regression lines and test for equality of intercepts. The function returns the common slope and its confidence interval, the intercept of each regression line and its confidence interval, test for equality of each intercept to a given value and performs pairwise comparisons between intercepts.

Usage

reg.intcomp(formula, data=NULL, conf.level = 0.95, theo = 0, 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.

theo

numeric vector: theoretical value of each intercept.

p.method

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

Value

• data
  variables name.
• conf.level
  confidence level.
• slope.comm
  common slope and confidence interval.
• intercepts
  intercept of each regression line.
• intercepts.ci
  confidence interval of intercepts.
• intercepts.theo
  theoretical intercepts.
• intercepts.t
  test statistics for equality to theoretical values.
• intercepts.p
  corrected p-values for equality to theoretical values.
• intercepts.tab
  data frame of results of tests for equality to theoretical value.
• p.method
  method for p-values correction.
• df.multcomp
  degrees of freedom of pairwise comparisons.
• t.multcomp
  test statistics of pairwise comparisons.
• p.multcomp
  corrected p-values of pairwise comparisons.
• multcomp
  data frame of results of pairwise comparisons.

See Also

lm

Examples

covariable<-rep(1:30,3)
variable<-c(1:30+rnorm(30,0,3),seq(10,35,25/29)+rnorm(30,0,3),seq(-27,0,27/29)+rnorm(30,0,3))
factor<-as.factor(rep(LETTERS[1:3],each=30))
reg.intcomp(variable~covariable|factor)