LING 214/414 Fall 2026

Statistical Methods in Linguistics

University of Rochester · Department of Linguistics

Overview

Instructor Aaron Steven White
Office 511A Lattimore Hall
Meetings Monday & Wednesday, 12:30 PM to 1:45 PM
Location Lattimore 513
Communication Zulip
Course Notes View notes
Office Hours By appointment

This course provides an introduction to probability and statistics for linguistics, serving as an essential foundation for linguistics students who aim to analyze experimental and corpus linguistic data. The course covers elementary probability theory, descriptive and inferential statistics, fixed and mixed effects models, model evaluation and comparison, analysis of corpus data, analysis of judgment data, analysis of reading time data, and analysis of acoustic measures.

Prerequisites: LING 110 with a grade of C- or better

Learning Objectives

  1. Master fundamental concepts in probability and statistics
  2. Apply statistical methods to linguistic data analysis
  3. Design and analyze linguistic experiments
  4. Interpret statistical results in linguistics research
  5. Implement analyses using R programming
  6. Construct mixed effects models for complex datasets

Materials

Textbooks

An Introduction to Bayesian Data Analysis for Cognitive Science Bruno Nicenboim, Daniel Schad, and Shravan Vasishth Statistics for Linguists: An Introduction Using R Bodo Winter Doing Bayesian Data Analysis: A Tutorial with R, JAGS, and Stan John K. Kruschke, second edition (2015)

Software

RRStudioVisual Studio Code

Readings

Zipf's word frequency law in natural language: A critical review and future directions Steven T. Piantadosi Population samples Isabelle Buchstaller and Ghada Khattab Acoustic characteristics of American English vowels James Hillenbrand, Laura A. Getty, Michael J. Clark, and Kimberlee Wheeler Cross-validation Bruno Nicenboim, Daniel Schad, and Shravan Vasishth The Natural Stories Corpus Richard Futrell, Edward Gibson, Harry Tily, Idan Blank, Anastasia Vishnevetskaya, Steven T. Piantadosi, and Evelina Fedorenko Limits on lexical prediction during reading Steven G. Luke and Kiel Christianson The Provo Corpus Steven G. Luke and Kiel Christianson Analyzing linguistic diversity using Poisson regression; adding exposure variables Bodo Winter French liaison is allomorphy, not allophony: Evidence from lexical statistics Enrico Storme Factivity, presupposition projection, and the role of discrete knowledge in gradient inference judgments Julian Grove and Aaron Steven White The independence assumption; dealing with non-independence via experimental design and averaging Bodo Winter Predicting the Dative Alternation Joan Bresnan, Anna Cueni, Tatiana Nikitina, and R. Harald Baayen The CommitmentBank: Investigating projection in naturally occurring discourse Marie-Catherine de Marneffe, Mandy Simons, and Judith Tonhauser Final devoicing before it happens: A large-scale study of word-final obstruents in French Adèle Jatteau et al. Aspectual similarity predicts sense similarity Aaron Steven White, Scott Grimm, and Lelia Glass Control methods used in a study of the vowels Gordon E. Peterson and Harold L. Barney Frequency, acceptability, and selection: A case study of clause-embedding Aaron Steven White and Kyle Rawlins Decomposing and recomposing event structure William Gantt, Lelia Glass, and Aaron Steven White

Assessment

Component LING 214LING 414
Problem Sets 65%40%
Midterm Exam 25%20%
Participation 10%N/A
Final Project N/A40%

Final project rubric

Schedule

Week Dates Topic Due
1 Aug. 31, Sep. 2 Linguistic data and representation; probability spaces
2 Sep. 7, 9 Labor Day; events and probability measures
3 Sep. 14, 16 Random variables; discrete distributions
4 Sep. 21, 23 Continuous and joint distributions; dependence
5 Sep. 28, 30 Populations, samples, estimands, and uncertainty
6 Oct. 5, 7 Paired inference; conditional means and regression PS1 (Oct. 7)
7 Oct. 12, 14 Fall Break; multiple regression and model criticism
8 Oct. 19, 21 Out-of-sample prediction, loss, and grouped validation PS2 (Oct. 21)
9 Oct. 26, 28 Review; midterm Proposal (414)
10 Nov. 2, 4 GLMs: binary, count, and bounded responses
11 Nov. 9, 11 Experimental design, dependence, and generalization PS3 (Nov. 11)
12 Nov. 16, 18 Mixed models: ordinal and bounded responses
13 Nov. 23, 25 Clustering and mixture models; Thanksgiving recess PS4 (Nov. 23)
14 Nov. 30, Dec. 2 Factorization and missing-data validation; custom model design
15 Dec. 7, 9 Presentations (414) PS5 (Dec. 7)
16 Dec. 14 Presentations (414) Paper & code (414)
Dec. 18 to 23 Oral assessments (414)

Policies

Late Work

Problem sets: 10% deduction per day (max 3 days). Project components (414 only): No late submissions without prior approval. Extensions require 48-hour advance notice (except emergencies).

Academic Integrity

Collaboration on problem sets with classmates is encouraged, but each student must write their own solutions. See the generative AI policy and the University of Rochester's Academic Honesty Policy at http://www.rochester.edu/college/honesty/

Ai Policy

Students may use generative AI tools (e.g., ChatGPT, Claude, GitHub Copilot) for coding assistance on problem sets and projects. However, students must fully understand and be able to explain all generated code (assessed during in-class presentations and oral assessments), cite in code comments any AI tools used including the specific prompts, and not use AI tools for written assignments.

Accessibility

The University of Rochester welcomes students with disabilities. Students seeking accommodations must request them through the Office of Disability Resources: https://www.rochester.edu/disability/

Exceptions

Title Ix

All faculty are mandatory reporters for Title IX issues. Students can contact the Title IX Office directly at titleix@rochester.edu or 585-275-1654. More information: www.rochester.edu/sexualmisconduct

Credit Hour

This 4-credit course includes 150 minutes per week of direct instruction (two 75-minute sessions) and a minimum of 480 minutes per week of out-of-class student work, including reading assignments, problem sets, data analysis, and project work. This aligns with the University of Rochester's credit hour policy, where each credit hour requires 50 minutes of instruction and 120 minutes of supplementary work. As a cross-listed course, LING414 students are expected to demonstrate advanced content mastery, rigor, and requirements beyond the LING214 level. Graduate students will complete a comprehensive final project that demonstrates independent research capabilities consistent with graduate-level scholarship.

Communication

All communication must be done through the Fall 2026 course Zulip. Post general questions to appropriate Zulip channels. Use Zulip DMs for grade questions, course absence notifications, etc. Response time: 1-2 business days during work hours. No monitoring after 5 PM or weekends.

Office Hours

By appointment. Please schedule using the form linked above. I am available to meet if and only if a time is listed as available on the scheduling form.