A hierarchical process-dissociation model.

Abstract

In fitting the process-dissociation model (L. L. Jacoby, 1991) to observed data, researchers aggregate outcomes across participant, items, or both. T. Curran and D. L. Hintzman (1995) demonstrated how biases from aggregation may lead to artifactual support for the model. The authors develop a hierarchical process-dissociation model that does not require aggregation for analysis. Most importantly, the Curran and Hintzman critique does not hold for this model. Model analysis provides for support of process dissociation--selective influence holds, and there is a dissociation in correlation patterns among participants and items. Items that are better recollected also elicit higher automatic activation. There is no correlation, however, across participants; that is, participants with higher recollection have no increased tendency toward automatic activation. The critique of aggregation is not limited to process dissociation. Aggregation distorts analysis in many nonlinear models, including signal detection, multinomial processing tree models, and strength models. Hierarchical modeling serves as a general solution for accurately fitting these psychological-processing models to data.

Bayesian hypothesis testing for psychologists: A tutorial on the Savage–Dickey method

“…For the Zeelenberg experiment, this assumption is certainly incorrect, as the difference between two proportions is constrained to lie between À1 and 1 (see Example 1). Second, the analysis from Zeelenberg et al ignores the fact that the experimental design is nested (i.e., trials are nested within participants), a situation that calls for a hierarchical or multi-level analysis (e.g., Gelman & Hill, 2007;Rouder, Lu, Morey, Sun, & Speckman, 2008). In other words, it is unlikely that the bothprimed benefit is a fixed effect, in the sense that it is the same for each and every participant-it is more reasonable to assume that the both-primed benefit is a random effect (cf.…”

How to quantify support for and against the null hypothesis: A flexible WinBUGS implementation of a default Bayesian t test

“…Nevertheless, the SD idea is quite general, and it can facilitate Bayesian hypothesis testing for a wide range of relatively complex mathematical process models, such as the expectancy valence model for the Iowa gambling task (Busemeyer & Stout, 2002;Wetzels, Vandekerckhove, Tuerlinckx, & Wagenmakers, in press), the Ratcliff diffusion model for response times and accuracy (Vandekerckhove, Tuerlinckx, & Lee, 2008;Wagenmakers, 2009), models of categorization such as ALCOVE (Kruschke, 1992) or GCM (Nosofsky, 1986), multinomial processing trees (Batchelder & Riefer, 1999), the ACT-R model (Weaver, 2008), and many more. Another exciting possibility is to apply the SD method to facilitate Bayesian hypothesis testing in hierarchical models (i.e., models with random effects for subjects or items) such as those advocated by Rouder and others (Rouder & Lu, 2005;Rouder, Lu, Morey, Sun, & Speckman, 2008;Rouder et al, 2007;Shiffrin, Lee, Kim, & Wagenmakers, 2008).…”

Using Bayesian hierarchical parameter estimation to assess the generalizability of cognitive models of choice

“…This advantage is well justified on theoretical grounds (Gelman & Hill, 2007;Rouder & Lu, 2005), and the hierarchical approach has also proved successful when applied to empirical data (e.g., Rouder, Lu, Morey, Sun, & Speckman, 2008;Scheibehenne & Studer, 2014).…”