The TH package provides educational functions for teaching and performing hypothesis tests in R. Each function combines numerical inference with an optional graphical representation of the hypotheses, significance level, critical values, rejection and non-rejection regions, calculated statistic, and decision.

Version 1.0.0 introduces a self-contained interface, input validation, p-values, structured invisible results, executable examples, automated tests, corrected statistical logic, and restoration of graphical parameters.

Installation

After publication on CRAN:

install.packages("TH")

From a source archive built locally:

install.packages("TH_1.0.0.tar.gz", repos = NULL, type = "source")
library(TH)

Available functions

Function	Procedure
`tz1()`	One-sample Z test
`tz2()`	Two-sample Z test
`tt1()`	One-sample t test
`tt2i()`	Two-sample t test with equal variances
`tt2d()`	Welch two-sample t test
`tt2p()`	Paired t test
`tf2()`	F test for two variances
`tq2a()`	Chi-square goodness-of-fit test
`tq2i()`	Chi-square test of independence
`tq2h()`	Chi-square test of homogeneity

Basic example

X <- c(11, 12, 13, 12, 14, 13, 12, 15)
result <- tt1(X, mp = 10, alfa = 0.05, Ha = "greater", unidade = " units", plot = FALSE)
result

Numeric alternatives remain available for backward compatibility:

Ha = 1: "two.sided"
Ha = 2: "greater"
Ha = 3: "less"

The F test supports "two.sided" and "greater". The three chi-square procedures use the standard upper-tail omnibus test and therefore accept only Ha = 2 or Ha = "greater".

Documentation

help(package = "TH")
?tz1
browseVignettes("TH")
citation("TH")

Development checks

From the project root:

source("development/build_and_check.R")

The final CRAN archive must be generated by R CMD build and checked with R CMD check --as-cran on the resulting TH_1.0.0.tar.gz file.

Author

Willian Silva Barros
Federal University of Pelotas
Email: willian.barros@ufpel.edu.br