Stopping rules for multi-category computerized classification testing

Computerized classification testing (CCT) aims to classify persons into one of two or more possible categories to make decisions such as mastery/non-mastery or meet most/meet all/exceed. A defining feature of CCT is its stopping criterion: the test terminates when there is enough confidence to make a decision. There is abundant research on CCT with a single cut-off, and two common stopping criteria are the sequential probability ratio test (SPRT) statistic and the generalized likelihood ratio statistic (GLR). However, there is a relative scarcity of research extending the SPRT to the multi-hypothesis case for when there is more than one cut-off. In this paper, we propose a new multi-category GLR (mGLR) statistic as well as a stochastically curtailed version of the CCT with three or more categories. A simulation study was conducted to show that the mGLR statistic outperformed the existing stopping rules by generating shorter average test length without sacrificing classification accuracy. Results also revealed that the stochastically curtailed mGLR successfully increased test efficiency in certain testing conditions.     

Things fall apart. The cultural complex in contemporary times1

These extraordinary months due to COVID-19 and the Black Lives Matter protests, set as they are against a backdrop of the increasingly worrying climate emergency, have brought fear, anxiety and discord across the globe. But we have also experienced a deepening of our understanding of our connectedness, protests against injustice, expressions of social concern and a demand for change. The concept of the cultural complex as developed by Singer & Kimbles (2004) offers a helpful means of connecting the psychology of the individual psyche and the political phenomena of power relations. Using a small example to illustrate how it might operate at a local level, I suggest that a fundamental shift is taking place raising profound levels of anxiety as we move from the known to the unknown. The bipolar nature of these complexes means the extremes are surfacing bringing fears of the very real possibility of more entrenched attacks on democracy from the far right and the hunkering down behind armed borders. But there is also hope that different ways of living together may be developing from the ground up, ways that are rooted in our sense of interdependence – with each other and our planetary home.     

Maternal Emotion Socialization of Adolescent Girls Engaging in Non-Suicidal Self-Injury

Research on Child and Adolescent Psychopathology - Non-suicidal self injury (NSSI) is a transdiagnostic maladaptive behavior that is highly prevalent in adolescence. A greater understanding of the...     

Using EM Algorithm for Finite Mixtures and Reformed Supplemented EM for MIRT Calibration

Psychometrika - This study revisits the parameter estimation issues in multidimensional item response theory more thoroughly and investigates some computation details that have seldom been...     

初中生亲子关系与抑郁:自尊和情绪弹性的中介作用

基于生态系统理论和认知易感性模型,本研究拟探讨初中生亲子关系对抑郁的影响及作用机制,采用问卷法对813名初中生进行调查。结果表明：（1）亲子关系、自尊、情绪弹性与抑郁之间呈两两显著相关,且亲子关系能显著负向预测抑郁;（2）自尊和情绪弹性在亲子关系与抑郁之间起显著的中介作用,具体包括三条路径：一是自尊的单独中介作用;二是情绪弹性的单独中介作用;三是自尊和情绪弹性的序列中介作用。本研究揭示了初中生亲子关系通过内在心理因素对抑郁水平产生影响的作用机制,为进一步提升初中生的心理健康提供了指导性建议。     

‘Believe in me,and I will too’: a study of how teachers’ expectations instilled confidence in Grade 10 students

Social Psychology of Education - Teacher expectation research has continued to establish an association between what teachers expect of their students and what students accomplish academically....     

Solitude in context: On the role of culture,immigration, and acculturation in the experience of time to oneself

Older adults spend much time in solitude (without social interaction), putting them at risk of loneliness, especially if aging outside their country of origin (e.g., Chinese immigrants to Canada). Yet, cultural contextual factors that may reduce loneliness in moments of solitude are poorly understood. This study sought to disentangle the roles of culture, immigration, and acculturation in solitude-loneliness associations across two countries. Community-dwelling adults aged 51–85 in Vancouver (N = 58 East Asian, N = 37 European/North American) and in Hong Kong (N = 56 East/Southeast Asian) completed approximately 30 ecological momentary assessments over 10 days on their current affect and social situations. Participants in Vancouver spent more time in solitude, desired solitude more, and felt less lonely overall than those in Hong Kong. Multilevel models revealed that moments of solitude felt lonelier than moments spent in social interaction, but only for individuals less acculturated to their host culture or not concurrently desiring solitude. Associations held regardless of host culture, cultural heritage, or immigration status. Findings suggest that solitude need not feel lonely if it happens by choice and if individuals feel connected with their host culture, for both immigrant older adults and those aging in their birth country.     

Psychological Flexibility at Work and Employees' Proactive Work Behaviour: Cross‐Level Moderating Role of Leader Need for Structure

How to promote employees to be proactive behaviourally is a significant issue in the literature because it would benefit organisations in several ways. Drawing on the acceptance and commitment model, we proposed a new antecedent, psychological flexibility that might contribute to employees' proactive work behaviour. Furthermore, we investigated how the contextual role of supervisor need for structure exhibits a cross‐level moderating effect on the relationship between employee psychological flexibility at work and proactive work behaviour based on interactionism. Data from 241 full‐time employees and their corresponding 45 managers indicated that employee psychological flexibility was positively associated with proactive work behaviour. More importantly, the supervisor need for structure played a moderating role, suggesting that employees would demonstrate greater proactive work behaviour especially when the supervisors have a high need for structure. Implications for psychological flexibility, proactivity, and person‐situation interactional research are discussed.     

Constraints have different concurrent effects and aftereffects on variability

Three experiments showed that constraints imposed early in learning have different effects on variability when they are in effect and after they are removed. Task constraints, which determine how something can be done, limited the number of possible responses in a computer game. Variability constraints, which specify how differently something must be done, required that each response differ from some number of prior responses. Less restrictive constraints (Experiments 1 and 2) produced higher variability during the constraints. More restrictive constraints (Experiments 2 and 3) led to higher variability after the constraints were relaxed. The authors discuss how these differences reflect strategies acquired during the constraints (default rules) and modified in closely related ways (exception rules) afterward.     

Lateralization of narrow-band noise by blind and sighted listeners

The effects of varying interaural time delay (ITD) and interaural intensity difference (IID) were measured in normal-hearing sighted and congenitally blind subjects as a function of eleven frequencies and at sound pressure levels of 70 and 90 dB, and at a sensation level of 25 dB (sensation level refers to the pressure level of the sound above its threshold for the individual subject). Using an 'acoustic' pointing paradigm, the subject varied the IID of a 500 Hz narrow-band (100 Hz) noise (the 'pointer') to coincide with the apparent lateral position of a 'target' ITD stimulus. ITDs of 0, +/-200, and +/-400 micros were obtained through total waveform delays of narrow-band noise, including envelope and fine structure. For both groups, the results of this experiment confirm the traditional view of binaural hearing for like stimuli: non-zero ITDs produce little perceived lateral displacement away from 0 IID at frequencies above 1250 Hz. To the extent that greater magnitude of lateralization for a given ITD, presentation level, and center frequency can be equated with superior localization abilities, blind listeners appear at least comparable and even somewhat better than sighted subjects, especially when attending to signals in the periphery. The present findings suggest that blind listeners are fully able to utilize the cues for spatial hearing, and that vision is not a mandatory prerequisite for the calibration of human spatial hearing.