Movatterモバイル変換


[0]ホーム

URL:


t.test {stats}R Documentation

Student's t-Test

Description

Performs one and two sample t-tests on vectors of data.

Usage

t.test(x, ...)## Default S3 method:t.test(x, y = NULL,       alternative = c("two.sided", "less", "greater"),       mu = 0, paired = FALSE, var.equal = FALSE,       conf.level = 0.95, ...)## S3 method for class 'formula't.test(formula, data, subset, na.action = na.pass, ...)

Arguments

x

a (non-empty) numeric vector of data values.

y

an optional (non-empty) numeric vector of data values.

alternative

a character string specifying the alternativehypothesis, must be one of"two.sided" (default),"greater" or"less". You can specify just the initialletter.

mu

a number indicating the true value of the mean (ordifference in means if you are performing a two sample test).

paired

a logical indicating whether you want a pairedt-test.

var.equal

a logical variable indicating whether to treat thetwo variances as being equal. IfTRUE then the pooledvariance is used to estimate the variance otherwise the Welch(or Satterthwaite) approximation to the degrees of freedom is used.

conf.level

confidence level of the interval.

formula

a formula of the formlhs ~ rhs wherelhsis a numeric variable giving the data values andrhs either1 for a one-sample or paired test or a factorwith two levels giving the corresponding groups. Iflhs is of class"Pair" andrhs is1, a paired testis done, see Examples.

data

an optional matrix or data frame (or similar: seemodel.frame) containing the variables in theformulaformula. By default the variables are taken fromenvironment(formula).

subset

an optional vector specifying a subset of observationsto be used.

na.action

a function which indicates what should happen whenthe data containNAs.

...

further arguments to be passed to or from methods.For theformula method, this includes arguments of thedefault method, but notpaired.

Details

alternative = "greater" is the alternative thatx has alarger mean thany. For the one-sample case: that the mean is positive.

Ifpaired isTRUE then bothx andy mustbe specified and they must be the same length. Missing values aresilently removed (in pairs ifpaired isTRUE). Ifvar.equal isTRUE then the pooled estimate of thevariance is used. By default, ifvar.equal isFALSEthen the variance is estimated separately for both groups and theWelch modification to the degrees of freedom is used.

If the input data are effectively constant (compared to the larger of thetwo means) an error is generated.

If the data contain infinite values,t.test() no longer errors andreturns a still not very useful result. Note thatwilcox.test() isrobust against outliers and hencedeals more usefully with suchInf values inx ory.

Value

A list with class"htest" containing the following components:

statistic

the value of the t-statistic.

parameter

the degrees of freedom for the t-statistic.

p.value

the p-value for the test.

conf.int

a confidence interval for the mean appropriate to thespecified alternative hypothesis.

estimate

the estimated mean or difference in means depending onwhether it was a one-sample test or a two-sample test.

null.value

the specified hypothesized value of the mean or meandifference depending on whether it was a one-sample test or atwo-sample test.

stderr

the standard error of the mean (difference), used asdenominator in the t-statistic formula.

alternative

a character string describing the alternativehypothesis.

method

a character string indicating what type of t-test wasperformed.

data.name

a character string giving the name(s) of the data.

See Also

prop.test

Examples

## Two-sample t-testt.test(1:10, y = c(7:20))      # P = .00001855t.test(1:10, y = c(7:20, 200)) # P = .1245    -- NOT significant anymore## Traditional interfacewith(mtcars, t.test(mpg[am == 0], mpg[am == 1]))## Formula interfacet.test(mpg ~ am, data = mtcars)## One-sample t-test## Traditional interfacet.test(sleep$extra)## Formula interfacet.test(extra ~ 1, data = sleep)## Paired t-test## The sleep data is actually paired, so could have been in wide format:sleep2 <- reshape(sleep, direction = "wide",                  idvar = "ID", timevar = "group")## Traditional interfacet.test(sleep2$extra.1, sleep2$extra.2, paired = TRUE)## Formula interfacet.test(Pair(extra.1, extra.2) ~ 1, data = sleep2)

[Packagestats version 4.6.0Index]

[8]ページ先頭

©2009-2026 Movatter.jp