Constrained classification: The use of a priori information in cluster analysis

In many classification problems, one often possesses external and/or internal information concerning the objects or units to be analyzed which makes it appropriate to impose constraints on the set of allowable classifications and their characteristics. CONCLUS, or CONstrained CLUStering, is a new methodology devised to perform constrained classification in either an overlapping or nonoverlapping (hierarchical or nonhierarchial) manner. This paper initially reviews the related classification literature. A discussion of the use of constraints in clustering problems is then presented. The CONCLUS model and algorithm are described in detail, as well as their flexibility for use in various applications. Monte Carlo results are presented for two synthetic data sets with appropriate discussion of the resulting implications. An illustration of CONCLUS is presented with respect to a sales territory design problem where the objects classified are various Forbes-500 companies. Finally, the discussion section highlights the main contribution of the paper and offers some areas for future research.We wish to thank C. Mallows and J. D. Carroll for some helpful technical discussion and L. Clark and D. Art for their valuable computer assistance. We also wish to thank H. Pollak, R. Gnanadesikan, and J. Kettenring for their thorough reviews of a previous draft of this paper. Finally, we acknowledge helpful comments of the editor and two anonymous reviewers.     

Increased sensitivity to differentially diagnostic answers using familiar materials: Implications for confirmation bias

Researchers have recently pointed out that neither biased testing nor biased evaluation of hypotheses necessitates confirmation bias--defined here as systematic overconfidence in a focal hypothesis--but certain testing/evaluation combinations do. One such combination is (1) a tendency to ask about features that are either very likely or very unlikely under the focal hypothesis (extremity bias) and (2) a tendency to treat confirming and disconfirming answers as more similar in terms of their diagnosticity (or informativeness) than they really are. However, in previous research showing the second tendency, materials that are highly abstract and unfamiliar have been used. Two experiments demonstrated that using familiar materials led participants to distinguish much better between the differential diagnosticity of confirming and disconfirming answers. The conditions under which confirmation bias is a serious concern might be quite limited.     

Estimating sensitivity and bias in a yes/no task

The estimation of sensitivity and bias from data collected in a yes/no detection‐theoretic experiment is complicated by the possibility of proportions of 0 or 1 appearing in the resulting contingency table. Inverse normal transforms of these probabilities result in mathematically intractable infinities. Typically, some transformation of the data must be applied prior to parameter estimation. Several transformations have been reviewed in the literature, in terms of both the bias and the variance of the estimates they produce. We propose three generalized transformations, which contain the two most reported transformations as special cases, and consider their performance in terms of the mean square error of the estimates they produce. Results indicate that the ‘1/N ’ and the adaptive log‐linear transformations outperform the others. Guidelines for the application of these transformations are presented.     

From acclaim to blame: evidence of a person sensitivity decision bias

In a series of studies, the authors established empirical support for a general decision-making bias that they termed a person sensitvity bias. Specifically, a person sensitivity bias consists of a person positivity bias (D. O. Sears, 1983) under positive performance conditions and a person negativity bias under negative performance conditions. The authors conducted the first empirical studies of a direct comparison between individuals and objects performing the same task under both positive and negative performance conditions. Two additional studies tested the boundaries of the sensitivity bias within negatively framed decision dilemmas. The results are discussed in terms of their relevance toward a more comprehensive theory of person-object evaluation differences.     

Publication bias and the failure of replication in experimental psychology

Replication of empirical findings plays a fundamental role in science. Among experimental psychologists, successful replication enhances belief in a finding, while a failure to replicate is often interpreted to mean that one of the experiments is flawed. This view is wrong. Because experimental psychology uses statistics, empirical findings should appear with predictable probabilities. In a misguided effort to demonstrate successful replication of empirical findings and avoid failures to replicate, experimental psychologists sometimes report too many positive results. Rather than strengthen confidence in an effect, too much successful replication actually indicates publication bias, which invalidates entire sets of experimental findings. Researchers cannot judge the validity of a set of biased experiments because the experiment set may consist entirely of type I errors. This article shows how an investigation of the effect sizes from reported experiments can test for publication bias by looking for too much successful replication. Simulated experiments demonstrate that the publication bias test is able to discriminate biased experiment sets from unbiased experiment sets, but it is conservative about reporting bias. The test is then applied to several studies of prominent phenomena that highlight how publication bias contaminates some findings in experimental psychology. Additional simulated experiments demonstrate that using Bayesian methods of data analysis can reduce (and in some cases, eliminate) the occurrence of publication bias. Such methods should be part of a systematic process to remove publication bias from experimental psychology and reinstate the important role of replication as a final arbiter of scientific findings.     

Partial matching in the Moses illusion: Response bias not sensitivity

Previous research has demonstrated that people have enormous difficulty in detecting distortions in such questions as, “How many animals of each kind did Moses take in the Ark?” Reder and Kusbit (1991) argued that the locus of the effect must be the existence of a partial-match process. Other research has suggested that this partial-match process operates at the word level and that, with adequate focus on the relevant word, the Moses illusion is greatly diminished. The present experimental results argue that those conclusions were based on a shift in response criterion with no concomitant change in ability to detect distortions. Furthermore, the data suggest that the matching process operates below the word level, at the level of distinctive features.     

Publication bias in psychological science: comment on Ferguson and Brannick (2012)

It is well documented that studies reporting statistically significant results are more likely to be published than are studies reporting nonsignificant results--a phenomenon called publication bias. Publication bias in meta-analytic reviews should be identified and reduced when possible. Ferguson and Brannick (2012) argued that the inclusion of unpublished articles is ineffective and possibly counterproductive as a means of reducing publication bias in meta-analyses. We show how idiosyncratic choices on the part of Ferguson and Brannick led to an erroneous conclusion. We demonstrate that their key finding--that publication bias was more likely when unpublished studies were included--may be an artifact of the way they assessed publication bias. We also point out how the lack of transparency about key choices and the absence of information about critical features of Ferguson and Brannick's sample and procedures might have obscured readers' ability to assess the validity of their claims. Furthermore, we demonstrate that many of the claims they made are without empirical support, even though they could have tested these claims empirically, and that these claims may be misleading. With their claim that addressing publication bias introduces subjectivity and bias into meta-analysis, they ignored a large body of evidence showing that including unpublished studies that meet the inclusion criteria of a meta-analysis decreases (rather than increases) publication bias. Rather than exclude unpublished studies, we recommend that meta-analysts code study characteristics related to methodological quality (e.g., experimental vs. nonexperimental design) and test whether these factors influence the meta-analytic results.     

hate crimes against the Amish: a qualitative analysis of bias motivation using routine activities theory

Research on hate crime has largely been limited to official statistics collected by the Federal Bureau of Investigation and some independent scholarly research of hate crime victims. Few, however, have studied hate crime offenders. Offender narratives of hate crime participation are the focus of this study. Further, few have studied hate crimes against the Amish and their offenders. This study examines hate crime against the Amish with a particular focus on the bias motivation that generates anti-Amish hate crime. To accomplish this task, non-Amish hate crime offenders were enlisted to share their experiences and stories about anti-Amish hate crime. A total of eight subjects were interviewed; the subjects supplied over 16 hours of audiotaped narrative describing acts of "Claping" they had committed against Old Order Amish. The data were transcribed and an analysis of the interview data revealed that themes emerged from offender narratives within each element of routine activities theory. The data support that the subjects were motivated offenders, the Amish were perceived as suitable targets, and there was a perception that guardians were lacking within the community to discourage anti-Amish hate crime. However, it is important to consider the themes that emerged within each dimension of routine activities when applying the theory to anti-Amish bias crime.     

Contrast sensitivity during horizontal visual pursuit: dynamic sensitivity functions.

The contrast sensitivity functions of college students for grating targets presented at angular velocities of 0, 30, 60, and 90 deg s-1 were determined for target durations of 200 and 600 ms. The most pronounced effects of target movement were evident at the mid to high spatial frequencies in which sensitivity was markedly reduced as velocity increased. These adverse effects were greatest in the 200 ms condition, in which performance was largely limited to the saccadic eye movement system. In the 600 ms condition, in which both saccadic and smooth pursuit eye movements were possible, contrast sensitivity for the low-frequency target actually improved significantly for the 30 and 60 deg s-1 targets, whereas only adverse effects of target motion were found for targets of mid and high spatial frequencies. The results are discussed in terms of the limitations of traditional visual assessment procedures and the practical and theoretical benefits of conceptualizing the joint effects of target composition and target movement.     

Too good to be true: Publication bias in two prominent studies from experimental psychology

Empirical replication has long been considered the final arbiter of phenomena in science, but replication is undermined when there is evidence for publication bias. Evidence for publication bias in a set of experiments can be found when the observed number of rejections of the null hypothesis exceeds the expected number of rejections. Application of this test reveals evidence of publication bias in two prominent investigations from experimental psychology that have purported to reveal evidence of extrasensory perception and to indicate severe limitations of the scientific method. The presence of publication bias suggests that those investigations cannot be taken as proper scientific studies of such phenomena, because critical data are not available to the field. Publication bias could partly be avoided if experimental psychologists started using Bayesian data analysis techniques.     

Avoiding heterosexist bias in psychological research

The authors describe various ways that heterosexist bias can occur in scientific research and suggest ways that social and behavioral scientists can avoid it. Heterosexist bias is defined as conceptualizing human experience in strictly heterosexual terms and consequently ignoring, invalidating, or derogating homosexual behaviors and sexual orientation, and lesbian, gay male, and bisexual relationships and lifestyles. The deleterious scientific, social, and ethical consequences of such biases are discussed. Questions are provided for researchers to use in evaluating how heterosexist bias might affect their own selection of research questions, sampling, operationalization of variables, data collection, protection of participants, and dissemination of results. Suggestions also are offered for reducing heterosexist bias in academic journals, in textbooks, and in colleges and universities.     

Affective bias in complex decision making: Modulating sensitivity to aversive feedback

The present study investigated the conflict between well-developed attitudes and incentive rewards using the Iowa Gambling Task. In particular, the incorporation of emotional labels allowed us to model the role of affective biases and their impact on complex decision making over time. Two experiments manipulated the class of deck label (emotional pictures and racial faces) using both congruent and incongruent association to the deck incentives. Both experiments demonstrated that an incongruent association can lead to striking and persistent decision making biases. Thus, a common theme was a general inability to tolerate conflict between rewards and goal-irrelevant labels. Notably, Experiment 2 demonstrated that this ‘incongruency’ effect appeared to result from positive labels interfering with aversive experiences from bad decks. More generally, sensitivity to accumulating losses from punishing decks was primarily associated with successful performance on these Gambling Task variants. These results suggest emotional biases are readily harmful in complex decision making, and that flexibility in the extent to which we permit emotional influences to guide our decisions is crucial.     

Confirmation bias in a simulated research environment: An experimental study of scientific inference

Numerous authors (e.g., Popper, 1959) argue that scientists should try to falsify rather than confirm theories. However, recent empirical work (Wason and Johnson-Laird, 1972) suggests the existence of a confirmation bias, at least on abstract problems. Using a more realistic, computer controlled environment modeled after a real research setting, subjects in this study first formulated hypotheses about the laws governing events occurring in the environment. They then chose between pairs of environments in which they could: (I) make observations which would probably confirm these hypotheses, or (2) test alternative hypotheses. Strong evidence for a confirmation bias involving failure to choose environments allowing tests of alternative hypotheses was found. However, when subjects did obtain explicit falsifying information, they used this information to reject incorrect hypotheses.     

Separating bias and sensitivity in judgments of associative memory

Ratings of the degree of association between words are linearly related to normed associative strengths, but the intercept is high, and the slope is shallow (the judgments of associative memory [JAM] function). Two experiments included manipulations intended to decrease the intercept and increase the slope. Discrimination training on many pairs of words and constraining ratings to sum to a constant both reduced the intercept but failed to change the slope. The intercept of the JAM function appears to contain a bias component that can be manipulated independently of the slope, which reflects sensitivity to associative strengths.