Pohnpei

What to do with categorical data? Categorical data can be challenging to analyze quantitatively In language research we often have data that are purely categorical In today’s presentation we will deal with a specific type of categorical data found in questionnaires Questionnaire Data Questionnaires are frequently used in a variety of language research scenarios They often ask people to rate something (likert scales) or select the most appropriate response Example: select the language that is most appropriate to use in a given domain Example: rate level of agreement with several statements Research Question How do the questionnaire respondents relate to each other based on their responses?

What to do with categorical data? Categorical data can be challenging to analyze quantitatively In language research we often have data that are purely categorical In today’s presentation we will deal with a specific type of categorical data found in questionnaires Questionnaire Data Questionnaires are frequently used in a variety of language research scenarios They often ask people to rate something (likert scales) or select the most appropriate response There are often multiple questions that have the same answer scale (same choices) Example: select the language that is most appropriate to use in a given domain Example: rate level of agreement with several statements Research Question Often we are interested in how the questions relate to each other in terms of their answers as well as how the answers relate to each other based on the questions they were most used with Correspondence Analysis CA is statistical technique that shows how the questions and answers of multiple questions relate to each other Requires the data to have the same scale (all questions must have some possible answers) CA is a descriptive tool and doesn’t give p-values per se How does CA work?

Studying how people talk about language

Researching linguistic phenomena on the island of Pohnpei in the Federated States of Micronesia