An Efficient MCMC Algorithm to Sample Binary Matrices with Fixed Marginals

Uniform sampling of binary matrices with fixed margins is known as a difficult problem. Two classes of algorithms to sample from a distribution not too different from the uniform are studied in the literature: importance sampling and Markov chain Monte Carlo (MCMC). Existing MCMC algorithms converge slowly, require a long burn-in period and yield highly dependent samples. Chen et al. developed an importance sampling algorithm that is highly efficient for relatively small tables. For larger but still moderate sized tables (300×30) Chen et al.’s algorithm is less efficient. This article develops a new MCMC algorithm that converges much faster than the existing ones and that is more efficient than Chen’s algorithm for large problems. Its stationary distribution is uniform. The algorithm is extended to the case of square matrices with fixed diagonal for applications in social network theory. I am indebted to my colleague Gunter Maris for his suggestion to add a Metropolis–Hastings step as the finishing touch of the algorithm.     

A neuropsychological dimension for anchoring effects

Previous research has shown that strength of handedness predicts differences in sensory illusions, Stroop interference, episodic memory, and beliefs about body image and the origin of species. Recent evidence also suggests handedness differences in the susceptibility to information framing and persuasion. The present paper extends this line of work to decision anchoring effects. In Experiment 1, 131 introductory psychology students responded to 12 real‐world knowledge questions after being given random, uninformative high or low anchors. Results indicated that “strong‐handers” showed larger anchoring effects than “mixed‐handers.” In Experiment 2, 89 introductory psychology students responded to 6 real‐world knowledge questions in a modified, two‐step anchoring task in which participants were given a credible source for the anchored information and asked to give pre‐ and post‐anchor estimates. In contrast to Experiment 1, results revealed that mixed‐ and strong‐handers were affected similarly by anchoring. In Experiment 3, 158 students were asked to estimate the answer to one of two versions of 8! (8 × 7 × 6 × 5 × 4 × 3 × 2 × 1 or 1 × 2 × 3 × 4 × 5 × 6 × 7 × 8)—a multiplication problem in which the high and low anchors are inherently informative. Here, mixed‐handers showed larger anchoring effects than strong‐handers. A theory centered around the notion of hemispheric specialization and the communication between the two halves of the brain as well as arguments about the informativeness of anchors, metacognition, and recent theorizing in the anchoring literature are used to account for these data. Copyright © 2005 John Wiley & Sons, Ltd.     

Effects of Test Order and Modality on Sustained Attention in Children With Epilepsy

Neurological conditions affect sustained attention, but the effects of modality and interactions with test order have not been examined. In a 2?×?2 (Order?×?Modality) design using 54 children with chronic epilepsy, performance was compared on an auditory measure (modified Seashore Rhythm Test) versus a visual measure of attention (modified Conners’ Continuous Performance Test). Auditory scores were worse than visual, F(1,?52)?=?98.93, p<.001, but there was no order effect or interaction (p>.05). Implications for assessment and intervention are discussed.     

The Higher Structural Phases of Concept Formation of Children

By means of a 2 × 2 × 4 way analysis of variance, modified when needed, the self-disclosing ability (as measured by the Jourard Self-Disclosure Questionnaire) of freshman college students from divorce and nondivorce homes was analyzed. The results of the study provide evidence that, generally, a person from a female-based home of the divorce type does not disclose the self any more or any less than a person from a nondivorce home situation. Also, the father does not play a major role in determining or directing the self-disclosure process of his children.     

Judgment Processes Relevant to Drunk Driving1

The present study uses psychological theories of judgment and decision making in analyzing cognitions relevant to drunk driving decisions. Four groups of individuals were examined: (a) those having multiple convictions for drunk driving, (b) those having one conviction for drunk driving, (c) those never having been convicted of drunk driving but, who admit to having driven while intoxicated, and (d) those who drive, but claim to not have driven while intoxicated. Cognitions examined included perceived drunkenness relative to legally allowable blood alcohol levels for driving, perceived probabilities for being stopped and arrested and being involved in an automobile accident if driving drunk, and drunk driving tendencies. Perceived probabilities of being stopped and arrested and being involved in an accident were evaluated as a function of manipulations of 4 cues in a 2 × 2 × 4 × 3 factorial design (Distance to Destination × Weather and Road Conditions × Number of Drinks × Time to Consume). Perceived drunkenness was evaluated as a function of the manipulations of two cues in a 4 × 3 factorial design (Number of Drinks Consumed × Time to Consume). Results indicated the presence of several misperceptions and inappropriate response tendencies that potentially can be modified with educational efforts. These results are discussed in terms of the differential impact of previous arrest for DWI on different DWI-related judgments.     

Olfactory adaptation and recovery in man as measured by two psychophysical techniques

Olfactory adaptation and recovery was investigated in man, using two psychophysical procedures: modified category scaling and threshold detection. Both procedures yielded similar qualitative information regarding loss and recovery of olfactory sensitivity as a function of time and concentration of adapting stimuli. However, quantitative differences were observed that could be partially attributed to artifacts inherent in each procedure. Often more than 50% adaptation (and recovery) occurred within the first 2 min with either test procedure. In all experiments the rate of adaptation and recovery was greater at the higher of two adapting concentrations (10 × and 20 × the detection threshold I_t). Recovery occurred more rapidly than adaptation. The usefulness of both techniques is discussed in terms of the overall problem of characterizing the olfactory adaptation and recovery process in man.     

高校教师教学水平评价概化理论预算限制下最佳样本量估计

使用“高校教师教学水平评价问卷”,要求566名学生对19名教师进行评价,对收集到的数据作不同的概化设计,包括t×i、（s：t）×i、（s：t）×（i：v）和（s：t）×（i：v）×o四种设计。基于概化理论,结合预算限制,统一LaGrange乘法公式,自行推导不同设计的最佳样本量公式,联合估计的方差分量,计算出不同设计的最佳样本量。结果表明：（1）LaGrange乘法统一公式表现出较强的通用性,能够适用于预算限制下各种概化设计;（2）评价场合是影响高校教师教学水平评价一个相当重要的因素;（3）（s：t）×（i：v）×o是高校教师教学水平评价概化理论预算限制下最优概化设计;（4）高校教师教学水平评价概化理论预算限制下,每位教师最佳评价学生人数为20人,每个维度最佳评价题目数为3题。     

LOCUS OF CONTROL IN INTELLECTUAL SITUATIONS IN AMERICAN AND CHINESE SCHOOL CHILDREN

The Intellectual Achievement Responsibility (IAR) Questionnaire, developed by Crandall et al., was administered to 720 children, 360 from the United States and 360 from Taiwan. The subjects were equally distributed in the sixth and eighth grades, and also by sex. A 2 × 2 × 2 (culture, grade, sex) analysis of variance was performed separately on scores of the subscale of success experiences (I +) and subscale of failure experiences (I -). The results showed that: (a) American children obtained significantly higher I + but lower I - scores than Chinese children. (b) Sixth graders obtained significantly higher scores on both I + and I - subscales than eighth graders. (c) Boys scored significantly higher than girls on I +, but sex differences in I - were not significant. It was also found that American children were more internal in success than in failure situations, while the reverse was true for Chinese children.     

Search for multiple targets: Evidence for memory-based control of attention

There are two opposing models with regard to the function of memory in visual search: a memorydriven model and a memory-free model. Recently, Horowitz and Wolfe (2001) investigated a multipletarget search task. Participants were required to decide whether or not there were at leastn targets present. They demonstrated that the reaction time ×n function has a positive and accelerated curve. They argued that the memory-free model predicts this curve, whereas the memory-driven model predicts a linear function. In this study, I varied the total set sizes of a multiple-target search task and fitted the models separately for eachn condition. The model fit indicated that the memory-driven model is more appropriate than the memory-free model in eachn condition. These results suggest that an amnesic process does not cause the positive accelerated curve of the reaction time ×n function but that it is the result of the time needed to examine each additionaln item.     

HDC: A subroutine library for image processing using Burt’s hierarchical discrete correlation

This paper describes a library of subroutines that efficiently implement Burt’s (1981) hierarchical discrete correlation (HDC). The subroutines are written in Professional FORTRAN for IBM PCs or compatibles. Subroutines are included for both even and odd forms of the HDC, as well as for the corresponding algorithms for pyramid processing. Odd width kernels of up to 7×7 pixels and even width kernels of up to 6×8 pixels can be programmed easily with these subroutines. Thus, this library contains the forms of HDC that are most widely used in image processing and visual modeling. I show the efficiency of this implementation by reporting the execution time of each subroutine for several image sizes. I also present a method that simulates rotation of the kernel in order to allow applying kernels without circular symmetry at the desired orientation.     

The dimensional salience solution to the expectancy-value muddle: An extension

The theory of reasoned action (TRA) specifies a set of expectancy-value, belief-based frameworks that underpin attitude (behavioural beliefs × outcome evaluations) and subjective norm (normative beliefs × motivation to comply). Unfortunately, the most common method for analysing these frameworks generates statistically uninterpretable findings, resulting in what has been termed the ‘expectancy-value muddle’. Recently, however, a dimensional salience approach was found to resolve this muddle for the belief-based framework underpinning attitude. An online survey of 262 participants was therefore conducted to determine whether the dimensional salience approach could also be applied to the belief-based framework underpinning subjective norm. Results revealed that motivations to comply were greater for salient, as opposed to non-salient, social referents. The belief-based framework underpinning subjective norm was therefore represented by evaluating normative belief ratings for salient social referents. This modified framework was found to predict subjective norm, although predictions were greater when participants were forced to select five salient social referents rather than being free to select any number of social referents. These findings validate the use of the dimensional salience approach for examining the belief-based frameworks underpinning subjective norm. As such, this approach provides a complete solution to addressing the expectancy-value muddle in the TRA.     

Ethnicity,Idiocentrism–Allocentrism,and Intergroup Attitudes1

The study examined the relationships among ethnicity, idiocentrism–allocentrism and intergroup attitudes in Singapore. Thirty Malay and 30 Chinese students completed questionnaires which measured in-group and out-group attitudes and attitudes toward ethnic-based community development groups. Intergroup attitudes were analyzed by a 2 × 2 × 2 (Subject Ethnicity × Target Group Ethnicity × Idiocentrism–Allocentrism) analysis of variance. A 2 × 2 interaction revealed that both Malay and Chinese subjects expressed ethnocentric biases; however, planned comparisons indicated that this was due to the responses of allocentrics. A separate 2 × 2 (Subject Ethnicity × Idiocentrism-Allocentrism) ANOVA further revealed that allocentrics had more favorable attitudes toward ethnic-based community development groups than did idiocentrics.     

Crowding Effects of Density and Personal Space Requirements Among Older People: The Impact of Self-Control and Social Support

Abstract

The authors examined the effects of self-control and social support among a representative sample of 300 older people, 150 in high-density and 150 in low-density households in India. The Self-Control Schedule (M. Rosenbaum, 1980), the Comfortable Interpersonal Distance Test (M. Duke & S. Nowicki, 1972), the Social Support Questionnaire, and the Judgement of Environmental Quality Scale (I. G. Sarason, H. M. Levine, R. B. Basham, & B. R. Sarason, 1983) were the measures. A 2 × 2 × 2 (Density × Social Support × Self-Control) analysis of variance for perceptions of home environment and personal space requirements revealed that the Self-Control x Social Support interaction moderated the crowding effects of density: The participants in high-density households evaluated their home environments more positively and reduced their personal space requirements.     

The typical rank of tall three-way arrays

The rank of a three-way array refers to the smallest number of rank-one arrays (outer products of three vectors) that generate the array as their sum. It is also the number of components required for a full decomposition of a three-way array by CANDECOMP/PARAFAC. The typical rank of a three-way array refers to the rank a three-way array has almost surely. The present paper deals with typical rank, and generalizes existing results on the typical rank ofI × J × K arrays withK = 2 to a particular class of arrays withK ≥ 2. It is shown that the typical rank isI when the array is tall in the sense thatJK − J < I < JK. In addition, typical rank results are given for the case whereI equalsJK − J. The author is obliged to Henk Kiers, Tom Snijders, and Philip Thijsse for helpful comments.     

Cross‐Situational Learning of Phonologically Overlapping Words Across Degrees of Ambiguity

Cross‐situational word learning (XSWL) tasks present multiple words and candidate referents within a learning trial such that word–referent pairings can be inferred only across trials. Adults encode fine phonological detail when two words and candidate referents are presented in each learning trial (2 × 2 scenario; Escudero, Mulak, & Vlach, 2016a ). To test the relationship between XSWL task difficulty and phonological encoding, we examined XSWL of words differing by one vowel or consonant across degrees of within‐learning trial ambiguity (1 × 1 to 4 × 4). Word identification was assessed alongside three distractors. Adults finely encoded words via XSWL: Learning occurred in all conditions, though accuracy decreased across the 1 × 1 to 3 × 3 conditions. Accuracy was highest for the 1 × 1 condition, suggesting fast‐mapping is a stronger learning strategy here. Accuracy was higher for consonant than vowel set targets, and having more distractors from the same set mitigated identification of vowel set targets only, suggesting possible stronger encoding of consonants than vowels.     

Axiomatizing hybrid products: How can we reason many-dimensionally in hybrid logic?

The aim of this paper is to propose a two-dimensional hybrid logic in order to formalize inferences containing both spatial and temporal propositions. The semantic idea behind the proposal is to name both horizontal and vertical lines in a 2D-plane by two kinds of nominals. This is a generalization of the idea of naming a point in one-dimensional hybrid logic. I give an axiomatization of the proposed two-dimensional hybrid logic and show that it enjoys a general completeness result (called pure completeness) with respect to product Kripke frames. Moreover, in order to capture $T\times W$-frames studied by R.H. Thomason (1984), I introduce the notion of a dependent product frame, which enables us to represent the dependence of space over time. I also give a complete axiomatization of this dependent two-dimensional hybrid logic, and, as a corollary, reveal that a hybridization of $T\times W$-logic enjoys strong completeness.     

Extending the 3 × 2 achievement goal model to the sport domain: The 3 × 2 Achievement Goal Questionnaire for Sport

In the present research, we sought to extend the 3 × 2 achievement goal model recently proffered in the school domain to the sport domain. We did so by conducting two studies focused on the development and initial validation of the 3 × 2 Achievement Goal Questionnaire for Sport (3 × 2 AGQ-S). Study 1 (n = 679), devised items for the questionnaire and demonstrated that data from the questionnaire nicely fit the proposed 3 × 2 model, showed a better fit to the 3 × 2 model than to alternative models, and indicated that each goal variable had good internal consistency. Study 2 again documented the strong psychometric properties of the measure, and additionally linked the goal variables to other constructs central to the achievement goal literature. The establishment of this measure allows extensive study of the 3 × 2 achievement goal model in the sport domain, and promises to yield deeper insights into the nature of achievement motivation in such contexts.     

Electrocutaneous stimulation: Psychometric functions and temporal integration

Psychometric functions and psychophysical strength-duration curves were obtained with rectangular electro-cutaneous pulses. The slopes of the psychometric functions were much steeper than corresponding functions in other modalities, with the standard deviation of the distribution only about 0.08 times the threshold. Precise monitoring of stimulus current showed that physiological rather than physical variability was involved. Psychophysical strength-duration curves support the contention that large A-fibers are directly stimulated. Data from this study. as well as from comparable I × t experiments in other senses, are well-fit throughout the range of durations by rectangular hyperbolas. The period over which complete temporal summation occurs is only about 0.5 msec.     

Nature,nurture, and capital punishment: How evidence of a genetic–environment interaction,future dangerousness,and deliberation affect sentencing decisions

Research has shown that the low‐activity MAOA genotype in conjunction with a history of childhood maltreatment increases the likelihood of violent behaviors. This genetic–environment (G × E) interaction has been introduced as mitigation during the sentencing phase of capital trials, yet there is scant data on its effectiveness. This study addressed that issue. In a factorial design that varied mitigating evidence offered by the defense [environmental (i.e., childhood maltreatment), genetic, G × E, or none] and the likelihood of the defendant's future dangerousness (low or high), 600 mock jurors read sentencing phase evidence in a capital murder trial, rendered individual verdicts, and half deliberated as members of a jury to decide a sentence of death or life imprisonment. The G × E evidence had little mitigating effect on sentencing preferences: participants who received the G × E evidence were no less likely to sentence the defendant to death than those who received evidence of childhood maltreatment or a control group that received neither genetic nor maltreatment evidence. Participants with evidence of a G × E interaction were more likely to sentence the defendant to death when there was a high risk of future dangerousness than when there was a low risk. Sentencing preferences were more lenient after deliberation than before. We discuss limitations and future directions.