safeTTest: Safe Student's T-Test.

In safestats: Safe Anytime-Valid Inference

Safe Student's T-Test.

Description

A safe t-test adapted from t.test() to perform one and two sample t-tests on vectors of data.

Usage

safeTTest(
  x,
  y = NULL,
  designObj = NULL,
  paired = FALSE,
  varEqual = TRUE,
  pilot = FALSE,
  alpha = NULL,
  alternative = NULL,
  ciValue = NULL,
  na.rm = FALSE,
  ...
)

safe.t.test(
  x,
  y = NULL,
  designObj = NULL,
  paired = FALSE,
  var.equal = TRUE,
  pilot = FALSE,
  alpha = NULL,
  alternative = NULL,
  ...
)

Arguments

x	a (non-empty) numeric vector of data values.
y	an optional (non-empty) numeric vector of data values.
designObj	an object obtained from designSafeT(), or NULL, when pilot equals TRUE.
paired	a logical indicating whether you want a paired t-test.
varEqual	a logical variable indicating whether to treat the two variances as being equal. For the moment, this is always TRUE.
pilot	a logical indicating whether a pilot study is run. If TRUE, it is assumed that the number of samples is exactly as planned.
alpha	numeric > 0 only used if pilot equals TRUE. If pilot equals FALSE, then the alpha of the design object is used instead in constructing the decision rule S > 1/alpha.
alternative	a character only used if pilot equals TRUE. If pilot equals FALSE, then the alternative specified by the design object is used instead.
ciValue	numeric is the ciValue-level of the confidence sequence. Default ciValue=NULL, and ciValue = 1 - alpha
na.rm	a logical value indicating whether NA values should be stripped before the computation proceeds.
...	further arguments to be passed to or from methods.
var.equal	a logical variable indicating whether to treat the two variances as being equal. For the moment, this is always TRUE.

Value

Returns an object of class "safeTest". An object of class "safeTest" is a list containing at least the following components:

statistic

the value of the t-statistic.

n

The realised sample size(s).

eValue

the realised e-value from the safe test.

confSeq

A safe confidence interval for the mean appropriate to the specific alternative hypothesis.

estimate

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

stderr

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

testType

any of "oneSample", "paired", "twoSample" provided by the user.

dataName

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

designObj

an object of class "safeTDesign" obtained from designSafeT().

call

the expression with which this function is called.

Examples

designObj <- designSafeT(deltaMin=0.6, alpha=0.008, alternative="greater",
                         testType="twoSample", ratio=1.2)

set.seed(1)
x <- rnorm(100)
y <- rnorm(100)
safeTTest(x, y, designObj=designObj)      #0.2959334

safeTTest(1:10, y = c(7:20), pilot=TRUE)      # s = 658.69 > 1/alpha
designObj <- designSafeT(deltaMin=0.6, alpha=0.008, alternative="greater",
                         testType="twoSample", ratio=1.2)

set.seed(1)
x <- rnorm(100)
y <- rnorm(100)
safe.t.test(x, y, alternative="greater", designObj=designObj)      #0.2959334

safe.t.test(1:10, y = c(7:20), pilot=TRUE)      # s = 658.69 > 1/alpha

safestats documentation built on Nov. 24, 2022, 5:07 p.m.