Article published in:How to do Linguistics with R: Data exploration and statistical analysis
[Not in series 195] 2015
► pp. 87–114
Chapter 5. Comparing two groups
t-test and Wilcoxon and Mann-Whitney tests for independent and dependent samples
Do language learners who are taught by an innovative method show better results than those who are taught traditionally? Do speakers of one language variety speak faster than speakers of another variety? Do people of one gender use more hedging constructions than people of another? In this chapter, you will learn how to make such comparisons using the parametric t-test and the non-parametric Wilcoxon and Mann-Whitney tests for dependent and independent samples. You will learn how to compute the standard error and confidence intervals for the mean. The case studies will involve differences between high- and low-frequency nouns with regard to the number of associations that they trigger and their abstractness/concreteness scores.