Out of the Cage of Shadows

摘要: Unlike molecules or plots of barley, subjects in psycholinguistic experiments are intelligent beings that depend for their survival on constant adaptation to environment. This study presents three data sets documenting the presence adaptive processes psychological experiments. These leave a statistical footprint form autocorrelations residual error associated with by-subject time series trial-to-trial responses. Generalized additive mixed models (GAMMs) provide unified framework within which both factorial predictors and covariates given experimental design, as well non-linear random effects interactions can be uncovered evaluated. GAMMs not only substantially improved fits structure, but also insight into theoretical interest, more refined window structure. Our results challenge standard advocated by Barr et al. (2013). The analytical cage maximal linear model this confines analyst is motivated simulation studies presuppose sterile, free any processes. However, when present real data, no longer informative. For such method analysis cannot purely design-driven, must part driven data.