onewayComp: Simultaneous Confidence Intervals and Hypothesis Tests for...

In DataScienceUWL/DS705data: Data sets for use in the University of Wisconsin DS705 course

Description

Generates Studentized confidence intervals and/or hypothesis tests for one-way designs. P-values can be adjusted ...

Usage

onewayComp(formula,data,alpha=.05,var.equal=TRUE,con=NA,nboot=0,adjust='one.step')

Arguments

formula	e.g. x~group, this would the same formula you would supply to lm for a one-way ANOVA
data	data frame containing x and group
alpha	significance level of the test, 1-alpha is the overall confidence level
var.equal	Defaults to TRUE, if FALSE, then Welch type corrections are used for the Studentized test statistics. FALSE along with adjust='one.step' gives the Games-Howell procedure.
con	optional contrast matrix. If con=NA, then all pairwise comparisons are made.
nboot	if nboot=0, then t-distributions are used for P-values and critical values (including Tukey max t), but if nboot>0 then resampling is used to approximate the critical values and P-values. For the bootstrap resampling separate samples are used and each sample is recentered so that the null hypothesis is true.
adjust	possible values are 'one.step' for Tukey Kramer or Games Howell procedures that give both hypothesis tests and confidence intervals (cannot be used with custom contrast matrix). 'bonferroni', 'none', 'holm', or any other adjustment that can be passed to p.adjust()

Value

call	Shows the details of the function call.
comp	A matrix, with names columns. 'diff' is the sample mean difference or sample mean contrast value. 'lwr' and 'upr' are the confidence interval limits (if available). 't' is the value of the Studentized test statistic. 'p' is the unadjusted p-value as would be computed by a single t-test. 'p adj' is the adjusted p-value as determined by the selected adjust method. 'Rej H_0' is 1 if p adj is less than alpha
pairw	Matrix showing pairwise comparisons and P-values.

Author(s)

Jeff Baggett, University of Wisconsin - La Crosse.

Examples

##---- Should be DIRECTLY executable !! ----
##-- ==>  Define data, use random,
##--	or do  help(data=index)  for the standard data sets.

## The function is currently defined as
function (x) 
{
  }

DataScienceUWL/DS705data documentation built on Jan. 15, 2022, 3:43 a.m.