Statistical Comparisons using R: Glossary

Understand the terminology variables that will be referenced in this workshop

Understand how to calculate measures of central tendency and variability

Understand that box plots and histograms can be used to visualise data spread

Understand the normal distribution and why normality tests are an important step in conducting statistical comparisons

Select appropriate and testable null and alternative hypotheses

Interpret p-values and statistical significance correctly

Open a data file in a text editor or RStudio file viewer

Use read.table or read.csv to import data

Review a dataframe using str and summary

Convert columns from factors to string using as.character

Distinguish a continuous variable

Review data using plot and ggplot

Test for normality of a dataset using shapiro.test

Calculate correlation coefficient using cor and cor.test

Convert dataframe columns to factors using as.factor

Draw barcharts using plot and ggplot

Select an appropriate statistical test for a categorical dataset

Analyse categorical data using chisq.test and fisher.test

Use hist and boxplots to review distribution of variables for a group

Summarise grouped data using the by command

Distinguish paired and non-paired samples

Correctly use the t.test and wilcox.test functions

Identify situations needing multiple sample tests and choose the relevant test using the decision tree

Perform multi-group testing using aov and kruskal.test

Perform and interpret post hoc tests using TukeyHSD and dunnTest

Study interactions using interaction.plot and aov

Check model assumptions using plot

Understand the impact of multiple testing on p-values

Use p.adjust to correct multiple-testing p-values