- BU Course Number: GRS LX790*
- Prerequisites: LX795; or consent of instructor.
- Offered at the graduate level only.
* This is the general course number for Topics in Linguistics; official number of this course is pending.
Course Description. [Sample Syllabus]. Numeracy is no longer an optional feature of a linguist’s intellectual toolkit. Recognizing this, many linguists have labored – often outside of the context of their formal training – to build foundational knowledge in statistics, computation, and data science. Graduate programs in linguistics, ours included, have responded to the growing demand for training in quantitative methods by creating courses tailored to linguistic questions and data. However, because many students come to such courses with varied experience, there are restrictions on how much can be taught and learned in a single semester. In addition, even for linguists who have already built a strong base of understanding, the sheer volume and pace of ongoing developments in data science can be overwhelming.
The purpose of this course is to provide students who already have a foundation in statistical analysis as well as basic skills in R (the open-source statistical environment) with a deeper understanding of a range of topics and techniques, including: data-wrangling and visualization, the logic of Null-Hypothesis Significance Testing, mixed effects modeling, vowel normalization, principal components analysis, model selection, discriminant analysis, power analysis, partitioning algorithms, and other topics. We will also explore strategies for streamlining workflow in linguistic research, presenting a model for writing reports and journal articles in the RStudio workspace.