@article{VasishthNicenboim2016,
  author    = {Vasishth, Shravan and Nicenboim, Bruno},
  title     = {Statistical Methods for Linguistic Research: Foundational Ideas - Part I},
  series = {Language and linguistics compass},
  volume    = {10},
  journal   = {Language and linguistics compass},
  publisher = {Wiley-Blackwell},
  address   = {Hoboken},
  issn      = {1749-818X},
  doi       = {10.1111/lnc3.12201},
  pages     = {349 -- 369},
  year      = {2016},
  abstract  = {We present the fundamental ideas underlying statistical hypothesis testing using the frequentist framework. We start with a simple example that builds up the one-sample t-test from the beginning, explaining important concepts such as the sampling distribution of the sample mean, and the iid assumption. Then, we examine the meaning of the p-value in detail and discuss several important misconceptions about what a p-value does and does not tell us. This leads to a discussion of Type I, II error and power, and Type S and M error. An important conclusion from this discussion is that one should aim to carry out appropriately powered studies. Next, we discuss two common issues that we have encountered in psycholinguistics and linguistics: running experiments until significance is reached and the 'garden-of-forking-paths' problem discussed by Gelman and others. The best way to use frequentist methods is to run appropriately powered studies, check model assumptions, clearly separate exploratory data analysis from planned comparisons decided upon before the study was run, and always attempt to replicate results.},
  language  = {en}
}
@article{NicenboimVasishth2016,
  author    = {Nicenboim, Bruno and Vasishth, Shravan},
  title     = {Statistical methods for linguistic research: Foundational Ideas-Part II},
  series = {Language and linguistics compass},
  volume    = {10},
  journal   = {Language and linguistics compass},
  publisher = {Wiley-Blackwell},
  address   = {Hoboken},
  issn      = {1749-818X},
  doi       = {10.1111/lnc3.12207},
  pages     = {591 -- 613},
  year      = {2016},
  abstract  = {We provide an introductory review of Bayesian data analytical methods, with a focus on applications for linguistics, psychology, psycholinguistics, and cognitive science. The empirically oriented researcher will benefit from making Bayesian methods part of their statistical toolkit due to the many advantages of this framework, among them easier interpretation of results relative to research hypotheses and flexible model specification. We present an informal introduction to the foundational ideas behind Bayesian data analysis, using, as an example, a linear mixed models analysis of data from a typical psycholinguistics experiment. We discuss hypothesis testing using the Bayes factor and model selection using cross-validation. We close with some examples illustrating the flexibility of model specification in the Bayesian framework. Suggestions for further reading are also provided.},
  language  = {en}
}
@misc{NicenboimLogacevGatteietal.2016,
  author    = {Nicenboim, Bruno and Logacev, Pavel and Gattei, Carolina and Vasishth, Shravan},
  title     = {When High-Capacity Readers Slow Down and Low-Capacity Readers Speed Up},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-90663},
  pages     = {1 -- 24},
  year      = {2016},
  abstract  = {We examined the effects of argument-head distance in SVO and SOV languages (Spanish and German), while taking into account readers' working memory capacity and controlling for expectation (Levy, 2008) and other factors. We predicted only locality effects, that is, a slowdown produced by increased dependency distance (Gibson, 2000; Lewis and Vasishth, 2005). Furthermore, we expected stronger locality effects for readers with low working memory capacity. Contrary to our predictions, low-capacity readers showed faster reading with increased distance, while high-capacity readers showed locality effects. We suggest that while the locality effects are compatible with memory-based explanations, the speedup of low-capacity readers can be explained by an increased probability of retrieval failure. We present a computational model based on ACT-R built under the previous assumptions, which is able to give a qualitative account for the present data and can be tested in future research. Our results suggest that in some cases, interpreting longer RTs as indexing increased processing difficulty and shorter RTs as facilitation may be too simplistic: The same increase in processing difficulty may lead to slowdowns in high-capacity readers and speedups in low-capacity ones. Ignoring individual level capacity differences when investigating locality effects may lead to misleading conclusions.},
  language  = {en}
}
@article{NicenboimLogacevGatteietal.2016,
  author    = {Nicenboim, Bruno and Logacev, Pavel and Gattei, Carolina and Vasishth, Shravan},
  title     = {When High-Capacity Readers Slow Down and Low-Capacity Readers Speed Up},
  series = {Frontiers in psychology},
  volume    = {7},
  journal   = {Frontiers in psychology},
  publisher = {Frontiers Research Foundation},
  address   = {Lausanne},
  issn      = {1664-1078},
  doi       = {10.3389/fpsyg.2016.00280},
  pages     = {1 -- 24},
  year      = {2016},
  abstract  = {We examined the effects of argument-head distance in SVO and SOV languages (Spanish and German), while taking into account readers' working memory capacity and controlling for expectation (Levy, 2008) and other factors. We predicted only locality effects, that is, a slowdown produced by increased dependency distance (Gibson, 2000; Lewis and Vasishth, 2005). Furthermore, we expected stronger locality effects for readers with low working memory capacity. Contrary to our predictions, low-capacity readers showed faster reading with increased distance, while high-capacity readers showed locality effects. We suggest that while the locality effects are compatible with memory-based explanations, the speedup of low-capacity readers can be explained by an increased probability of retrieval failure. We present a computational model based on ACT-R built under the previous assumptions, which is able to give a qualitative account for the present data and can be tested in future research. Our results suggest that in some cases, interpreting longer RTs as indexing increased processing difficulty and shorter RTs as facilitation may be too simplistic: The same increase in processing difficulty may lead to slowdowns in high-capacity readers and speedups in low-capacity ones. Ignoring individual level capacity differences when investigating locality effects may lead to misleading conclusions.},
  language  = {en}
}
@phdthesis{Nicenboim2016,
  author    = {Nicenboim, Bruno},
  title     = {Dependency resolution as a retrieval process},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xiv, 209},
  year      = {2016},
  abstract  = {My thesis focused on the predictions of the activation-based model of Lewis and Vasishth (2005) to investigate the evidence for the use of the memory system in the formation of non-local dependencies in sentence comprehension. The activation-based model, which follows the Adaptive Control of Thought-Rational framework (ACT-R; Anderson et al., 2004), has been used to explain locality effects and similarity-based interference by assuming that dependencies are resolved by a cue-based retrieval mechanism, and that the retrieval mechanism is affected by decay and interference. Both locality effects and (inhibitory) similarity-based interference cause increased difficulty (e.g., longer reading times) at the site of the dependency completion where a retrieval is assumed: (I) Locality effects are attributed to the increased difficulty in the retrieval of a dependent when the distance from its retrieval site is increased. (II) Similarity-based interference is attributed to the retrieval being affected by the presence of items which have similar features as the dependent that needs to be retrieved. In this dissertation, I investigated some findings problematic to the activation-based model, namely, facilitation where locality effects are expected (e.g., Levy, 2008), and the lack of similarity-based interference from the number feature in grammatical sentences (e.g., Wagers et al., 2009). In addition, I used individual differences in working memory capacity and reading fluency as a way to validate the theories investigated (Underwood, 1975), and computational modeling to achieve a more precise account of the phenomena. Regarding locality effects, by using self-paced reading and eye-tracking-while reading methods with Spanish and German data, this dissertation yielded two main findings: (I) Locality effects seem to be modulated by working memory capacity, with high-capacity participants showing expectation-driven facilitation. (II) Once expectations and other potential confounds are controlled using baselines, with increased distance, high-capacity readers can show a slow-down (i.e., locality effects) and low-capacity readers can show a speedup. While the locality effects are compatible with the activation-based model, simulations show that the speedup of low-capacity readers can only be accounted for by changing some of the assumptions of the activation-based model. Regarding similarity-based interference, two relatively high-powered self-paced reading experiments in German using grammatical sentences yielded a slowdown at the verb as predicted by the activation-based model. This provides evidence in favor of dependency creation via cue-based retrieval, and in contrast with the view that cue-based retrieval is a reanalysis mechanism (Wagers et al., 2009). Finally, the same experimental results that showed inhibitory interference from the number feature are used for a finer grain evaluation of the retrieval process. Besides Lewis and Vasishth's (2005) activation-based model, also McElree's (2000) direct-access model can account for inhibitory interference. These two models assume a cue-based retrieval mechanism to build dependencies, but they are based on different assumptions. I present a computational evaluation of the predictions of these two theories of retrieval. The models were compared by implementing them in a Bayesian hierarchical framework. The evaluation of the models reveals that some aspects of the data fit better under the direct access model than under the activation-based model. However, a simple extension of the activation-based model provides a comparable fit to the direct access model. This serves as a proof of concept showing potential ways to improve the original activation-based model. In conclusion, this thesis adds to the body of evidence that argues for the use of the general memory system in dependency resolution, and in particular for a cue-based retrieval mechanism. However, it also shows that some of the default assumptions inherited from ACT-R in the activation-based model need to be revised.},
  language  = {en}
}