Informal versus formal judgment of statistical models: The case of normality assumptions

Researchers sometimes use informal judgment for statistical model diagnostics and assumption checking. Informal judgment might seem more desirable than formal judgment because of a paradox: Formal hypothesis tests of assumptions appear to become less useful as sample size increases. We suggest that this paradox can be resolved by evaluating both formal and informal statistical judgment via a simplified signal detection framework. In 4 studies, we used this approach to compare informal judgments of normality diagnostic graphs (histograms, Q-Q plots, and P-P plots) to the performance of several formal tests (Shapiro-Wilk test, Kolmogorov-Smirnov test, etc.). Participants judged whether or not graphs of sample data came from a normal population (Experiments 1-2) or whether or not from a population close enough to normal for a parametric test to be more powerful than a nonparametric one (Experiments 3-4). Across all experiments, participants' informal judgments showed lower discriminability than did formal hypothesis tests. This pattern occurred even after participants were given 400 training trials with feedback, a financial incentive, and ecologically valid distribution shapes. The discriminability advantage of formal normality tests led to slightly more powerful follow-up tests (parametric vs. nonparametric). Overall, the framework used here suggests that formal model diagnostics may be more desirable than informal ones.

A procedural analogue of prey detection and applied signal detection

Researchers have employed a variety of laboratory analogues of cryptic prey detection and applied signal detection to study factors influencing learning and performance in these ethological and applied scenarios. However, these procedural analogues do not appear to map closely onto their "real-world" counterparts, particularly with respect to the role of the "yes" (i.e., "attack") response and the payoff for this response (or its absence) on signal-present and signal-absent trials. Using domestic hens, we developed a procedural analogue in which a "yes" response requires some time to emit; such responses were reinforced only in the presence of a signal. In Experiment 1, we evaluated the influence of the "yes" response requirement by manipulating the number of responses required to qualify as a "yes" response. As the "yes" response requirement was increased, bias toward responding "no" increased, revealing that this is a critical factor controlling accuracy in this procedure. In Experiment 2, we evaluated the influence of signal probability and reinforcement rate on signal detection accuracy and found that neither of these factors significantly influenced accuracy or bias. These findings suggest that this procedural analogue may represent a valuable alternative for studying behaviour in relevant signal detection scenarios.

A novel, unbiased approach to evaluating subsequent search misses in dual target visual search

Research in radiology and visual cognition suggest that finding one target during visual search may result in increased misses for a second target, an effect known as subsequent search misses (SSM). Here, we demonstrate that the common method of calculating second-target detection performance is biased and could produce spurious SSM effects. We describe the source of that bias and document factors that influence its magnitude. We use a modification of signal-detection theory to develop a novel, unbiased method of calculating the expected value for dual-target performance under the null hypothesis. We then apply our novel method to two of our data sets that showed modest SSM effects when calculated in the traditional manner. Our correction reduced the effect size to the point that there was no longer a significant SSM effect. We then applied our method to a published data set that had a larger effect size when calculated using the traditional calculation as well as when using an alternative calculation that was recently proposed to account for biases in the traditional method. We find that both the traditional method and the recently proposed alternative substantially overestimate the magnitude of the SSM effect in these data, but a significant SSM effect persisted even with our calculation. We recommend that future SSM studies use our method to ensure accurate effect-size estimates, and suggest that the method be applied to reanalyze published results, particularly those with small effect sizes, to rule out the possibility that they were spurious.

Surgical face masks impair human face matching performance for familiar and unfamiliar faces

In response to the COVID-19 pandemic, many governments around the world now recommend, or require, that their citizens cover the lower half of their face in public. Consequently, many people now wear surgical face masks in public. We investigated whether surgical face masks affected the performance of human observers, and a state-of-the-art face recognition system, on tasks of perceptual face matching. Participants judged whether two simultaneously presented face photographs showed the same person or two different people. We superimposed images of surgical masks over the faces, creating three different mask conditions: control (no masks), mixed (one face wearing a mask), and masked (both faces wearing masks). We found that surgical face masks have a large detrimental effect on human face matching performance, and that the degree of impairment is the same regardless of whether one or both faces in each pair are masked. Surprisingly, this impairment is similar in size for both familiar and unfamiliar faces. When matching masked faces, human observers are biased to reject unfamiliar faces as "mismatches" and to accept familiar faces as "matches". Finally, the face recognition system showed very high classification accuracy for control and masked stimuli, even though it had not been trained to recognise masked faces. However, accuracy fell markedly when one face was masked and the other was not. Our findings demonstrate that surgical face masks impair the ability of humans, and naïve face recognition systems, to perform perceptual face matching tasks. Identification decisions for masked faces should be treated with caution.

Optimal templates for signal extraction by noisy ideal detectors and human observers

The optimal template for signal detection in white additive noise is the signal itself: the ideal observer matches each stimulus against this template and selects the stimulus associated with largest match. In the noisy ideal observer, internal noise is added to the decision variable returned by the template. While the ideal observer represents an unrealistic approximation to the human visual process, the noisy ideal observer may be applicable under certain experimental conditions. For template values constrained to lie within a specified range, theory predicts that the template associated with a noisy ideal observer should be a clipped image of the signal, a result which we demonstrate analytically using variational calculus. It is currently unknown whether the human process conforms to theory. We report a targeted analysis of the theoretical prediction for an experimental protocol that maximizes template-matching on the part of human participants. We find indicative evidence to support the theoretical expectation when internal noise is compared across participants, but not within each participant. Our results indicate that implicit knowledge about internal variability in different individuals is reflected by their detection templates; no implicit knowledge is retained for internal-noise fluctuations experienced by a given participant during data collection. The results also indicate that template encoding is constrained by the dynamic range of weight specification, rather than the range of output values transduced by the template-matching process.

Discrete-state versus continuous models of the confidence-accuracy relationship in recognition memory

The relationship between confidence and accuracy in recognition memory is important in real-world settings (e.g., eyewitness identification) and is also important to understand at a theoretical level. Signal detection theory assumes that recognition decisions are based on continuous underlying memory signals and therefore inherently predicts that the relationship between confidence and accuracy will be continuous. Almost invariably, the empirical data accord with this prediction. Threshold models instead assume that recognition decisions are based on discrete-state memory signals. As a result, these models do not inherently predict a continuous confidence-accuracy relationship. However, they can accommodate that result by adding hypothetical mapping relationships between discrete states and the confidence rating scale. These mapping relationships are thought to arise from a variety of factors, including demand characteristics (e.g., instructing participants to distribute their responses across the confidence scale). However, until such possibilities are experimentally investigated in the context of a recognition memory experiment, there is no sense in which threshold models adequately explain confidence ratings at a theoretical level. Here, we tested whether demand characteristics might account for the mapping relationships required by threshold models and found that confidence was continuously related to accuracy (almost identically so) both in the presence of strong experimenter demands and in their absence. We conclude that confidence ratings likely reflect the strength of a continuous underlying memory signal, not an attempt to use the confidence scale in a manner that accords with the perceived expectations of the experimenter.

Thinking in a foreign language distorts allocation of cognitive effort: Evidence from reasoning

Bilinguals, in their foreign language, are spared from several decision-making biases. We examined this "Foreign Language Effect" in the context of logical reasoning, in which reasoners are required to track the logical status of a syllogism, ignoring its believability. Across three experiments, we found the reverse Foreign Language Effect; foreign language reasoners are less able to evaluate the logical structure of syllogisms, but no less biased by their believability. One path to succeeding in reasoning tasks is always engaging in reflective processing. A more efficient strategy is metacognitively tracking whether belief-based intuitions conflict with logic-based intuitions and only reflecting when such conflict is present. We provide evidence that foreign language reasoners are less accurate because they struggle to detect belief-logic conflict, and in turn fail to engage in reflective processing when necessary to override the incorrect, intuitive response. We propose that foreign language reasoners are less able to detect belief-logic conflict either due to weakened intuitions or due to a more conservative threshold for the detection of conflict between multiple competing intuitions. Data for the experiments can be accessed publicly at https://osf.io/phbuq/.

Oxytocin alters the effect of payoff but not base rate in emotion perception

Emotion perception, inferring the emotional state of another person, can be formalized as decision under uncertainty: another person's scowling face may indicate anger or concentration and the optimal inference is contingent on the decision consequences (payoff) and how likely real anger is encountered (base rate). Although emerging evidence suggests that the neuropeptide oxytocin influences human perception of emotional facial expressions, whether such effect relates to the alternated process of payoff or base rate still remains unclear. In addition, little is known about oxytocin's effect on metacognitive process involved in emotion perception. One hundred and twenty-two healthy male adults (sixty-two in Experiment 1 and sixty in Experiment 2, respectively) received 24 international units (IU) of intranasal oxytocin or placebo (between-subjects) in a randomized and double-blind study. We independently and systematically manipulated the payoff and base rate levels in an emotion categorization task and measured participants' response bias via categorization choice and metacognitive sensitivity via confidence report. Compared to the placebo group, oxytocin specifically induced a categorization bias under the payoff, but not base rate manipulation. In contrast, oxytocin had no effect on subjects' confidence rating, indicating that the metacognitive sensitivity can be dissociated from emotion perception. Our results pinpoint the specific role of oxytocin in payoff evaluation, but not target likelihood estimation and provide a potential theoretical framework to bridge oxytocin research in emotion perception, social cognition and value-based decisions.

The bhsdtr package: a general-purpose method of Bayesian inference for signal detection theory models

We describe a novel method of Bayesian inference for hierarchical or non-hierarchical equal variance normal signal detection theory models with one or more criteria. The method is implemented as an open-source R package that uses the state-of-the-art Stan platform for sampling from posterior distributions. Our method can accommodate binary responses as well as additional ratings and an arbitrary number of nested or crossed random grouping factors. The SDT parameters can be regressed on additional predictors within the same model via intermediate unconstrained parameters, and the model can be extended by using automatically generated human-readable Stan code as a template. In the paper, we explain how our method improves on other similar available methods, give an overview of the package, demonstrate its use by providing a real-study data analysis walk-through, and show that the model successfully recovers known parameter values when fitted to simulated data. We also demonstrate that ignoring a hierarchical data structure may lead to severely biased estimates when fitting signal detection theory models.

A test of two processes: The effect of training on deductive and inductive reasoning

Dual-process theories posit that separate kinds of intuitive (Type 1) and reflective (Type 2) processes contribute to reasoning. Under this view, inductive judgments are more heavily influenced by Type 1 processing, and deductive judgments are more strongly influenced by Type 2 processing. Alternatively, single-process theories propose that both types of judgments are based on a common form of assessment. The competing accounts were respectively instantiated as two-dimensional and one-dimensional signal detection models, and their predictions were tested against specifically targeted novel data using signed difference analysis. In two experiments, participants evaluated valid and invalid arguments, under induction or deduction instructions. Arguments varied in believability and type of conditional argument structure. Additionally, we used logic training to strengthen Type 2 processing in deduction (Experiments 1 & 2) and belief training to strengthen Type 1 processing in induction (Experiment 2). The logic training successfully improved validity-discrimination, and differential effects on induction and deduction judgments were evident in Experiment 2. While such effects are consistent with popular dual-process accounts, crucially, a one-dimensional model successfully accounted for the results. We also demonstrate that the one-dimensional model is psychologically interpretable, with the model parameters varying sensibly across conditions. We argue that single-process accounts have been prematurely discounted, and formal modeling approaches are important for theoretical progress in the reasoning field.

Targeting separate specific learning parameters underlying cognitive behavioral therapy can improve perceptual judgments of anger

BACKGROUND AND OBJECTIVES

Anxiety disorders are characterized by biased perceptual judgment. An experimental model using simple verbal instruction to target specific decision parameters that influence perceptual judgment was developed to test if it could influence anger perception, and to examine differences between individuals with social anxiety disorder (SAD) relative to generalized anxiety disorder (GAD) or non-psychiatric controls.

METHODS

Anger perception was decomposed into three decision parameters (perceptual similarity of angry vs. not-angry facial expressions, base rate of encountering angry vs. not-angry expressions, payoff for correct vs. incorrect categorization of face stimuli) using a signal detection framework. Participants with SAD (n = 97), GAD (n = 90), and controls (n = 98) were assigned an instruction condition emphasizing one of the three decision parameters. Anger perception pre-vs. post-instruction and its interaction with diagnosis were examined.

RESULTS

For all participants, base rate instructions impacted response bias over and above practice effects, supporting the validity of this instructional task-based approach to altering response bias. We failed to find a similarity or payoff instruction effect, nor a diagnosis interaction.

LIMITATIONS

Future instructional tasks may need to more closely target core cognitive and perceptual biases in anxiety disorders to identify specific deficits and how to optimally influence them.

CONCLUSIONS

This study demonstrates that specific decision parameters underlying perceptual judgment can be experimentally manipulated. Although our study failed to show diagnosis specific effects, it suggests that individual parameter "estimation" deficits may be experimentally isolated and potentially targeted, with the ultimate goal of developing an objective approach to personalized intervention targeting biased perceptual judgments in anxiety disorders.

Detection measures for visual inspection of X-ray images of passenger baggage

In visual inspection tasks, such as airport security and medical screening, researchers often use the detection measures d' or A' to analyze detection performance independent of response tendency. However, recent studies that manipulated the frequency of targets (target prevalence) indicate that d_a with a slope parameter of 0.6 is more valid for such tasks than d' or A'. We investigated the validity of detection measures (d', A', and d_a) using two experiments. In the first experiment, 31 security officers completed a simulated X-ray baggage inspection task while response tendency was manipulated directly through instruction. The participants knew half of the prohibited items used in the study from training, whereas the other half were novel, thereby establishing two levels of task difficulty. The results demonstrated that for both levels, d' and A' decreased when the criterion became more liberal, whereas d_a with a slope parameter of 0.6 remained constant. Eye-tracking data indicated that manipulating response tendency affected the decision component of the inspection task rather than search errors. In the second experiment, 124 security officers completed another simulated X-ray baggage inspection task. Receiver operating characteristic (ROC) curves based on confidence ratings provided further support for d_a, and the estimated slope parameter was 0.5. Consistent with previous findings, our results imply that d' and A' are not valid measures of detection performance in X-ray image inspection. We recommend always calculating d_a with a slope parameter of 0.5 in addition to d' to avoid potentially wrong conclusions if ROC curves are not available.

Perceptual sensitivity is modulated by what others can see

Previous work has established that social cues such as the direction of others' gaze or their perspective on a scene may influence one's own perceptual judgments. However, up until now it has remained unclear whether such influences are exerted at a perceptual or decisional locus, as most previous studies have used response times as their primary dependent measure. Here, we asked whether perceptual sensitivity is also dependent on social cognition. To test this hypothesis, we asked participants to evaluate whether low-contrast Gabor patterns embedded in noise were visible from either their own or an avatar's perspective. Across three experiments, we found that observers' detection performance was increased if an avatar also shared perception of the stimulus location. By leveraging signal detection modelling, we show that this effect is driven by a change in perceptual sensitivity (d'), independent of decisional or response interference. Furthermore, by "blindfolding" the avatar, we show that the boosting effect of shared perception on detection sensitivity is only obtained when the participant believes the avatar can also see the stimulus, ruling out an influence of low-level directional cues. We interpret these results within a framework in which the avatar's perspective boosts top-down spatial attention by prioritising particular spatial locations at which perception is shared. In summary, we reveal that perceptual sensitivity is modulated by the perspective of others.

Predictive cues reduce but do not eliminate intrinsic response bias

Predictive cues induce large changes in people's choices by biasing responses towards the expected stimulus category. At the same time, even in the absence of predictive cues, humans often exhibit substantial intrinsic response biases. Despite the ubiquity of both of these biasing effects, it remains unclear how predictive cues interact with intrinsic bias. To understand the nature of this interaction, we examined data across three previous experiments that featured a combination of neutral cues (revealing intrinsic biases) and predictive cues. We found that predictive cues decreased the intrinsic bias to about half of its original size. This result held both when bias was quantified as the criterion location estimated using signal detection theory and as the probability of choosing a particular stimulus category. Our findings demonstrate that predictive cues reduce but do not eliminate intrinsic response bias, testifying to both the malleability and rigidity of intrinsic biases.

Parsimonious estimation of signal detection models from confidence ratings

Signal detection theory (SDT) is used to quantify people’s ability and bias in discriminating stimuli. The ability to detect a stimulus is often measured through confidence ratings. In SDT models, the use of confidence ratings necessitates the estimation of confidence category thresholds, a requirement that can easily result in models that are overly complex. As a parsimonious alternative, we propose a threshold SDT model that estimates these category thresholds using only two parameters. We fit the model to data from Pratte et al. (Journal of Experimental Psychology: Learning, Memory, and Cognition, 36, 224–232 2010) and illustrate its benefits over previous threshold SDT models.

Deficits in auditory sensory discrimination among children with attention-deficit/hyperactivity disorder

Research into children with attention-deficit/hyperactivity disorder (ADHD) has focused on complex cognitive dysfunction, but less attention has been paid to sensory perception processes underlying the symptoms of ADHD. Based on signal detection theory, the present study compared the sensory discrimination ability and decision bias of children with and without ADHD. It also investigated the differences between ADHD with predominantly inattentive (ADHDi) and combined presentations (ADHDc). The sample of 75 children and adolescents with ADHD (24 ADHDi, 51 ADHDc) (16 females and 59 males) and 22 typical developing controls (TD) (8 females and 14 males) completed an auditory signal detection task. Participants were asked to detect signals against levels of transient background noise (35, 45, 55, and 65 dB). The results showed that with the increase of noise levels, both the ADHD and TD groups demonstrated decreased sensory discrimination. Although both groups successfully detected signal against noise levels from 35 to 55 dB, the ADHD group showed lower discrimination ability than that of the TD group. For decision bias, no group difference was found. Further comparisons regarding the predominant symptom presentation of ADHD sub-groups showed no differences. Current research has suggested that the deficit in ADHD people's signal detection performance can be attributed to sensory discrimination rather than decision bias. We suggest that background noise should be taken into account when using auditory stimuli to investigate cognitive functions in people with ADHD.

Endogenous visuospatial attention increases visual awareness independent of visual discrimination sensitivity

Visuospatial attention often improves task performance by increasing signal gain at attended locations and decreasing noise at unattended locations. Attention is also believed to be the mechanism that allows information to enter awareness. In this experiment, we assessed whether orienting endogenous visuospatial attention with cues differentially affects visual discrimination sensitivity (an objective task performance) and visual awareness (the subjective feeling of perceiving) during the same discrimination task. Gabor patch targets were presented laterally, either at low contrast (contrast stimuli) or at high contrast embedded in noise (noise stimuli). Participants reported their orientation either in a 3-alternative choice task (clockwise, counterclockwise, unknown) that allowed for both objective and subjective reports, or in a 2-alternative choice task (clockwise, counterclockwise) that provided a control for objective reports. Signal detection theory models were fit to the experimental data: estimated perceptual sensitivity reflected objective performance; decision criteria, or subjective biases, were a proxy for visual awareness. Attention increased sensitivity (i.e., improved objective performance) for the contrast, but not for the noise stimuli. Indeed, with the latter, attention did not further enhance the already high target signal or reduce the already low uncertainty on its position. Interestingly, for both contrast and noise stimuli, attention resulted in more liberal criteria, i.e., awareness increased. The noise condition is thus an experimental configuration where people think they see the targets they attend to better, even if they do not. This could be explained by an internal representation of their attentional state, which influences awareness independent of objective visual signals.

An investigation of detection biases in the unattended periphery during simulated driving

While people often think they veridically perceive much of the visual surround, recent findings indicate that when asked to detect targets such as gratings embedded in visual noise, observers make more false alarms in the unattended periphery. Do these results from psychophysics studies generalize to more ecologically valid settings? We used a modern game engine to create a simulated driving environment where participants (as drivers) had to make judgments about the colors of pedestrians' clothing in the periphery. Confirming our hypothesis based on previous psychophysics studies, we found that subjects showed liberal biases for unattended locations when detecting specific colors of pedestrians' clothing. A second experiment showed that this finding was not simply due to a confirmation bias in decision-making when subjects were uncertain. Together, these results support the idea that in everyday visual experience, there is subjective inflation of experienced detail in the periphery, which may happen at the decisional level.

Optimal go/no-go ratios to maximize false alarms

Despite the ubiquity of go/no-go tasks in the study of behavioral inhibition, there is a lack of evidence regarding the impact of key design characteristics, including the go/no-go ratio, intertrial interval, and number of types of go stimuli, on the production of different response classes of central interest. In the present study we sought to empirically determine the optimal conditions to maximize the production of a rare outcome of considerable interest to researchers: false alarms. As predicted, the shortest intertrial intervals (450 ms), intermediate go/no-go ratios (2:1 to 4:1), and the use of multiple types of go stimuli produced the greatest numbers of false alarms. These results are placed within the context of behavioral changes during learning.

Lightness/pitch and elevation/pitch crossmodal correspondences are low-level sensory effects

We tested the sensory versus decisional origins of two established audiovisual crossmodal correspondences (CMCs; lightness/pitch and elevation/pitch), applying a signal discrimination paradigm to low-level stimulus features and controlling for attentional cueing. An audiovisual stimulus randomly varied along two visual dimensions (lightness: black/white; elevation: high/low) and one auditory dimension (pitch: high/low), and participants discriminated either only lightness, only elevation, or both lightness and elevation. The discrimination task and the stimulus duration varied between subjects. To investigate the influence of crossmodal congruency, we considered the effect of each CMC (lightness/pitch and elevation/pitch) on the sensitivity and criterion of each discrimination as a function of stimulus duration. There were three main findings. First, discrimination sensitivity was significantly higher for visual targets paired congruently (compared with incongruently) with tones while criterion was unaffected. Second, the sensitivity increase occurred for all stimulus durations, ruling out attentional cueing effects. Third, the sensitivity increase was feature specific such that only the CMC that related to the feature being discriminated influenced sensitivity (i.e. lightness congruency only influenced lightness discrimination and elevation congruency only influenced elevation discrimination in the single and dual task conditions). We suggest that these congruency effects reflect low-level sensory processes.

Atomoxetine modulates the relationship between perceptual abilities and response bias

Elucidation of how neuromodulators influence motivated behaviors is a major challenge of neuroscience research. It has been proposed that the locus-cœruleus-norepinephrine system promotes behavioral flexibility and provides resources required to face challenges in a wide range of cognitive processes. Both theoretical models and computational models suggest that the locus-cœruleus-norepinephrine system tunes neural gain in brain circuits to optimize behavior. However, to the best of our knowledge, empirical proof demonstrating the role of norepinephrine in performance optimization is scarce. Here, we modulated norepinephrine transmission in monkeys performing a Go/No-Go discrimination task using atomoxetine, a norepinephrine-reuptake inhibitor. We tested the optimization hypothesis by assessing perceptual sensitivity, response bias, and their functional relationship within the framework of the signal detection theory. We also manipulated the contingencies of the task (level of stimulus discriminability, target stimulus frequency, and decision outcome values) to modulate the relationship between sensitivity and response bias. We found that atomoxetine increased the subject's perceptual sensitivity to discriminate target stimuli regardless of the task contingency. Atomoxetine also improved the functional relationship between sensitivity and response bias, leading to a closer fit with the optimal strategy in different contexts. In addition, atomoxetine tended to reduce reaction time variability. Taken together, these findings support a role of norepinephrine transmission in optimizing response strategy.

Transcranial alternating current stimulation at 10 Hz modulates response bias in the Somatic Signal Detection Task

Ongoing, pre-stimulus oscillatory activity in the 8-13 Hz alpha range has been shown to correlate with both true and false reports of peri-threshold somatosensory stimuli. However, to directly test the role of such oscillatory activity in behaviour, it is necessary to manipulate it. Transcranial alternating current stimulation (tACS) offers a method of directly manipulating oscillatory brain activity using a sinusoidal current passed to the scalp. We tested whether alpha tACS would change somatosensory sensitivity or response bias in a signal detection task in order to test whether alpha oscillations have a causal role in behaviour. Active 10 Hz tACS or sham stimulation was applied using electrodes placed bilaterally at positions CP3 and CP4 of the 10-20 electrode placement system. Participants performed the Somatic Signal Detection Task (SSDT), in which they must detect brief somatosensory targets delivered at their detection threshold. These targets are sometimes accompanied by a light flash, which could also occur alone. Active tACS did not modulate sensitivity to targets but did modulate response criterion. Specifically, we found that active stimulation generally increased touch reporting rates, but particularly increased responding on light trials. Stimulation did not interact with the presence of touch, and thus increased both hits and false alarms. TACS stimulation increased reports of touch in a manner consistent with our observational reports, changing response bias, and consistent with a role for alpha activity in somatosensory detection.

Characterizing belief bias in syllogistic reasoning: A hierarchical Bayesian meta-analysis of ROC data

The belief-bias effect is one of the most-studied biases in reasoning. A recent study of the phenomenon using the signal detection theory (SDT) model called into question all theoretical accounts of belief bias by demonstrating that belief-based differences in the ability to discriminate between valid and invalid syllogisms may be an artifact stemming from the use of inappropriate linear measurement models such as analysis of variance (Dube et al., Psychological Review, 117(3), 831-863, 2010). The discrepancy between Dube et al.'s, Psychological Review, 117(3), 831-863 (2010) results and the previous three decades of work, together with former's methodological criticisms suggests the need to revisit earlier results, this time collecting confidence-rating responses. Using a hierarchical Bayesian meta-analysis, we reanalyzed a corpus of 22 confidence-rating studies (N = 993). The results indicated that extensive replications using confidence-rating data are unnecessary as the observed receiver operating characteristic functions are not systematically asymmetric. These results were subsequently corroborated by a novel experimental design based on SDT's generalized area theorem. Although the meta-analysis confirms that believability does not influence discriminability unconditionally, it also confirmed previous results that factors such as individual differences mediate the effect. The main point is that data from previous and future studies can be safely analyzed using appropriate hierarchical methods that do not require confidence ratings. More generally, our results set a new standard for analyzing data and evaluating theories in reasoning. Important methodological and theoretical considerations for future work on belief bias and related domains are discussed.

Sustained conscious access to incidental memories in RSVP

In visual search of natural scenes, differentiation of briefly fixated but task-irrelevant distractor items from incidental memory is often comparable to explicit memorization. However, many characteristics of incidental memory remain unclear, including the capacity for its conscious retrieval. Here, we examined incidental memory for faces in either upright or inverted orientation using Rapid Serial Visual Presentation (RSVP). Subjects were instructed to detect a target face in a sequence of 8-15 faces cropped from natural scene photographs (Experiment 1). If the target face was identified within a brief time window, the subject proceeded to an incidental memory task. Here, subjects used incidental memory to discriminate between a probe face (a distractor in the RSVP stream) and a novel, foil face. In Experiment 2 we reduced scene-related semantic coherency by intermixing faces from multiple scenes and contrasted incidental memory with explicit memory, a condition where subjects actively memorized each face from the sequence without searching for a target. In both experiments, we measured objective performance (Type 1 AUC) and metacognitive accuracy (Type 2 AUC), revealing sustained and consciously accessible incidental memory for upright and inverted faces. In novel analyses of face categories, we examined whether accuracy or metacognitive judgments are affected by shared semantic features (i.e., similarity in gender, race, age). Similarity enhanced the accuracy of incidental memory discriminations but did not influence metacognition. We conclude that incidental memory is sustained and consciously accessible, is not reliant on scene contexts, and is not enhanced by explicit memorization.

One mirror effect: The regularities of recognition memory

The mirror effect is a pattern of results generally found in two-condition recognition memory experiments that is consistent with normative signal detection theory as a model of recognition. However, the claim has been made that there is a distinct mirror effect, the "strength mirror effect," that differs from the normative one. This claim is based on experiments on recognition memory in which repetition or study time is varied to produce differences in accuracy, where typically the ordinary mirror effect pattern is absent. If this claim is correct, it has major implications for theories of recognition memory. Therefore, a full examination of the data that support the claim was called for. To do that, we replicated the basic demonstration of the no-mirror-effect data and analyzed it further in a series of experiments. The analysis showed the following: (1) Whether or not the mirror effect occurs is determined by whether the experimenter furnishes effective discriminanda that distinguish the weak and strong conditions for the participant. (2) Once Finding 1 is taken into account, no adjustments of or additions to the normative signal detection theory explanations are necessary. (3) There is only one mirror effect, and no separate "strength mirror effect."