Developments in experimental semantics and pragmatics have led to experiments testing increasingly subtle theoretical predictions. Unfortunately, simple mappings from relevant semantic factors to experimental factors are not always possible, making interpretation of the experimental results often indirect. This issue is somewhat specific to semantics and pragmatics, and is rarely discussed in the methodological literature. In this course I introduce methods to build statistical models in R that immediately encode semantic theories, and thereby allow direct interpretation of the results.
In the last session, we discuss the possibilities offered by more powerful methods and how they can further close the gap between theory and experimental results. While a background in statistics and knowledge of R might be necessary to fully implement the ideas discussed in class, the course itself will not presuppose such knowledge. The discussion is illustrated with concrete examples and data sets from recent studies.
- Class 1: Informal introduction with a toy example [slides]
- Class 2: Introducing linear regression and Formalizing the problem [slides]
- Class 3: Example (Cremers, Roelofsen, Uegaki 2019) [slides] [R script]
- Class 4: In class discussion of more examples
- Class 5: Addressing bimodal distributions of participants [slides]
References:
Barr, D. J., Levy, R., Scheepers, C., & Tily, H. J. (2013). Random effects structure for confirmatory hypothesis testing: Keep it maximal. Journal of memory and language, 68(3), 255-278.
Bates, D., Kliegl, R., Vasishth, S., & Baayen, H. (2015). Parsimonious mixed models. arXiv preprint arXiv:1506.04967.
Cremers, A., & Chemla, E. (2014). A psycholinguistic study of the exhaustive readings of embedded questions. Journal of Semantics, 33(1), 49-85.
Cremers, A., Roelofsen, F., & Uegaki, W. Distributive ignorance inferences with wonder and believe. To appear in Semantics & Pragmatics.
Gelman, A., Lee, D., & Guo, J. (2015). Stan: A probabilistic programming language for Bayesian inference and optimization. Journal of Educational and Behavioral Statistics, 40(5), 530-543.
Levy, R. (2014). Using R formulae to test for main effects in the presence of higher-order interactions. arXiv preprint arXiv:1405.2094.
Matuschek, H., Kliegl, R., Vasishth, S., Baayen, H., & Bates, D. (2017). Balancing Type I error and power in linear mixed models. Journal of Memory and Language, 94, 305-315.
Tieu, L., Yatsushiro, K., Cremers, A., Romoli, J., Sauerland, U., & Chemla, E. (2016). On the role of alternatives in the acquisition of simple and complex disjunctions in French and Japanese. Journal of Semantics, 34(1), 127-152.