Skip to contents

sprtt

Overview

The sprtt package is a sequential probability ratio tests toolbox (sprtt).

The package contains:

Installation

Release version from CRAN

This is the recommended version for a normal user.

# installs the package
install.packages("sprtt")

Development version from GitHub

To get a bug fix or to use a feature from the development version, you can install the latest version from GitHub.

# the installation requires the "devtools" package
# install.packages("devtools")
# stable GitHub version
devtools::install_github("MeikeSteinhilber/sprtt")

# development version, may not be stable
devtools::install_github("MeikeSteinhilber/sprtt", ref="develop")

Documentation

Detailed documentation can be found on the home page. There are several articles covering the usage of the package, the theoretical background of the test, and also an extended use case.

Short examples can be found in the following paragraph.

Quick Examples

Note

In the R code sections:

# comment: is a comment

function(): is R code

#> results of function(): is console output

# set seed --------------------------------------------------------------------
set.seed(333)

# load library ----------------------------------------------------------------
library(sprtt)
#> Note: Sample size planning functions require simulation data (~70 MB).
#> Data will download automatically on first use.
#> See ?download_sample_size_data for more information.

# t-TEST ----------------------------------------------------------------------
# one sample: numeric input ---------------------------------------------------
treatment_group <- rnorm(20, mean = 0, sd = 1)
results <- seq_ttest(treatment_group, mu = 1, d = 0.6)

# get access to the slots -----------------------------------------------------
# @ Operator
results@likelihood_ratio
#> [1] 323.9051

# [] Operator
results["likelihood_ratio"]
#> [1] 323.9051

# ANOVA -----------------------------------------------------------------------
# simulate data ---------------------------------------------------------------
set.seed(333)
data <- sprtt::draw_sample_normal(k_groups = 3,
                                  f = 0.25,
                                  sd = c(1, 1, 1),
                                  max_n = 22)

# calculate sequential ANOVA --------------------------------------------------
results <- sprtt::seq_anova(y ~ x, f = 0.25, data = data, plot = TRUE)
# test decision
results@decision
#> [1] "accept H1"
# test results
results
#> 
#> *****  Sequential ANOVA *****
#> 
#> formula: y ~ x
#> test statistic:
#>  log-likelihood ratio = 3.153, decision = accept H1
#> SPRT thresholds:
#>  lower log(B) = -2.944, upper log(A) = 2.944
#> Log-Likelihood of the:
#>  alternative hypothesis = -3.293
#>  null hypothesis = -6.447
#> alternative hypothesis: true difference in means is not equal to 0.
#> specified effect size: Cohen's f = 0.25
#> empirical Cohen's f = 0.4684039, 95% CI[0.1741801, 0.6969498]
#> Cohen's f adjusted = 0.415
#> degrees of freedom: df1 = 2, df2 = 63
#> SS effect = 12.63455, SS residual = 57.58624, SS total = 70.22079
#> *Note: to get access to the object of the results use the @ or [] instead of the $ operator.

# plot results -----------------------------------------------------------------
sprtt::plot_anova(results, position_lr_x = 60)

Sample Size Planning

The sample size planning function requires simulation data (~70 MB). On first use, this data will be downloaded and chached automatically:

sprtt::plan_sample_size(f_expected = 0.25, k_groups = 3, power = 0.9, decision_rate = 0.9)

The package contains functions to help managing the cached data, if necessary.

Managing cached data

# Check cache status
cache_info()

# Force re-download (if data was updated)
download_sample_size_data(force = TRUE)

# Clear cache
cache_clear()

If you need to use the package offline, download the data while connected beforehand.