认知诊断缺失数据处理方法的比较：零替换、多重插补与极大似然估计法

数据缺失在测验中经常发生, 认知诊断评估也不例外, 数据缺失会导致诊断结果的偏差。首先, 通过模拟研究在多种实验条件下比较了常用的缺失数据处理方法。结果表明：(1)缺失数据导致估计精确性下降, 随着人数与题目数量减少、缺失率增大、题目质量降低, 所有方法的PCCR均下降, Bias绝对值和RMSE均上升。(2)估计题目参数时, EM法表现最好, 其次是MI, FIML和ZR法表现不稳定。(3)估计被试知识状态时, EM和FIML表现最好, MI和ZR表现不稳定。其次, 在PISA2015实证数据中进一步探索了不同方法的表现。综合模拟和实证研究结果, 推荐选用EM或FIML法进行缺失数据处理。     

Multiple Religious Belonging among visitors of Dominican spiritual centers in the Netherlands

ABSTRACT

In the religiously pluralized Western world, a trend called ‘Multiple Religious Belonging’ (MRB) has been identified. Although it is a much theologically debated concept, empirical research on the practice of MRB is limited. The present research project therefore explores the phenomenon of MRB among visitors of Dominican spiritual centers in the Netherlands (n=472). It investigates to what extent and in which ways such visitors combine elements from more than one religious tradition in their lives and what they perceive to be the benefits of combining elements. It links this information to their views on religion, the resources they draw from, their (religiously diverse) networks, and their motivations for attending spiritual activities. The results indicate that respondents who combine elements from more than one religious tradition (‘combiners’) are more likely than ‘non-combiners’ to: a) see religion as something that is constantly changing during the life course; b) have networks which are religiously diverse; c) place importance on nature, in-depth conversations, personal rituals or practices, and theological, philosophical, and spiritual texts as resources; d) be motivated to attend spiritual centers because of a focus on self-exploration.     

Empirical underidentification in estimating random utility models: The role of choice sets and standardizations

A standard approach to distinguishing people’s risk preferences is to estimate a random utility model using a power utility function to characterize the preferences and a logit function to capture choice consistency. We demonstrate that with often-used choice situations, this model suffers from empirical underidentification, meaning that parameters cannot be estimated precisely. With simulations of estimation accuracy and Kullback–Leibler divergence measures we examined factors that potentially mitigate this problem. First, using a choice set that guarantees a switch in the utility order between two risky gambles in the range of plausible values leads to higher estimation accuracy than randomly created choice sets or the purpose-built choice sets common in the literature. Second, parameter estimates are regularly correlated, which contributes to empirical underidentification. Examining standardizations of the utility scale, we show that they mitigate this correlation and additionally improve the estimation accuracy for choice consistency. Yet, they can have detrimental effects on the estimation accuracy of risk preference. Finally, we also show how repeated versus distinct choice sets and an increase in observations affect estimation accuracy. Together, these results should help researchers make informed design choices to estimate parameters in the random utility model more precisely.     

Choice between single and multiple reinforcers in concurrent-chains schedules

Pigeons responded on concurrent-chains schedules with equal variable-interval schedules as initial links. One terminal link delivered a single reinforcer after a fixed delay, and the other terminal link delivered either three or five reinforcers, each preceded by a fixed delay. Some conditions included a postreinforcer delay after the single reinforcer to equate the total durations of the two terminal links, but other conditions did not include such a postreinforcer delay. With short initial links, preference for the single-reinforcer alternative decreased when a postreinforcer delay was present, but with long initial links, the postreinforcer delays had no significant effect on preference. In conditions with a postreinforcer delay, preference for the single-reinforcer alternative frequently switched from above 50% to below 50% as the initial links were lengthened. This pattern of results was consistent with delay-reduction theory (Squires & Fantino, 1971), but not with the contextual-choice model (Grace, 1994) or the hyperbolic value-added model (Mazur, 2001) as they have usually been applied. However, the hyperbolic value-added model could account for the results if its calculations were expanded to include reinforcers delivered in later terminal links. The implications of these findings for models of concurrent-chains performance are discussed.     

Distribution-free tests of stochastic dominance for small samples

One variable is said to “stochastically dominate” another if the probability of observations smaller than x is greater for one variable than the other, for all x. Inferring stochastic dominance from data samples is important for many applications of econometrics and experimental psychology, but little is known about the performance of existing inferential methods. Through simulation, we show that three of the most widely used inferential methods are inadequate for use in small samples of the size commonly encountered in many applications (up to 400 observations from each distribution). We develop two new inferential methods that perform very well in a limited, but practically important, case where the two variables are guaranteed not to be equal in distribution. We also show that extensions of these new methods, and an improved version of an existing method, perform quite well in the original, unlimited case.     

A Signal Detection Model for Multiple-Choice Exams

A model for multiple-choice exams is developed from a signal-detection perspective. A correct alternative in a multiple-choice exam can be viewed as being a signal embedded in noise (incorrect alternatives). Examinees are assumed to have perceptions of the plausibility of each alternative, and the decision process is to choose the most plausible alternative. It is also assumed that each examinee either knows or does not know each item. These assumptions together lead to a signal detection choice model for multiple-choice exams. The model can be viewed, statistically, as a mixture extension, with random mixing, of the traditional choice model, or similarly, as a grade-of-membership extension. A version of the model with extreme value distributions is developed, in which case the model simplifies to a mixture multinomial logit model with random mixing. The approach is shown to offer measures of item discrimination and difficulty, along with information about the relative plausibility of each of the alternatives. The model, parameters, and measures derived from the parameters are compared to those obtained with several commonly used item response theory models. An application of the model to an educational data set is presented.     

Boundary Issues in Academia: Student Perceptions of Faculty—Student Boundary Crossings

Boundary crossings in academia are rarely addressed by university policy despite the risk of problematic or unethical faculty—student interactions. This study contributes to an understanding of undergraduate college student perceptions of appropriateness of faculty—student nonsexual interactions by investigating the influence of gender and ethnicity on student judgments of the appropriateness of numerous hypothetical interactions. Overall, students deemed the majority of interactions as inappropriate. Female students judged a number of interactions as more inappropriate than did male students, and with a few exceptions, Mexican American and Anglo American students were similar in their ratings of the appropriateness of faculty—student interactions. These findings suggest that universities need to be proactive in establishing guidelines concerning faculty-student boundary crossings.     

Managing Nonsexual Multiple Relationships in University Counseling Centers: Recommendations for Graduate Assistants and Practicum Students

Graduate students typically serve in a wide variety of positions throughout their course of study in an academic setting. Because of the large number of roles assumed, graduate students may encounter several ethical dilemmas unique to the academic setting, particularly dilemmas regarding nonsexual multiple relationships. Although the topic of multiple relationships and psychologists has been extensively discussed in the literature, fewer articles have focused on the potential for nonsexual multiple relationships between graduate assistants, practicum students, and undergraduate students. This article focuses on the unique ethical dilemmas and challenges experienced by graduate assistants completing their practica at University Counseling Centers and provides recommendations for evaluating and managing nonsexual multiple relationships with undergraduate students.     

Intuitive Covariation Assessment of the Illusory Correlation

Most of the research concerned with the illusory correlation is modeled after the seminal work of D. L. Hamilton and R. K. Gifford (1976). However, S. A. Haslam and C. McGarty (1994) have voiced concerns over the dependent measures used within this paradigm. Therefore, in this study, the authors tested a new dependent variable that has high face validity. This measure was modeled after the work of J. R. McGahan and R. Wight (1989) and consisted of a set of propositional statements representing either the illusory correlation, the contingency opposite the illusory correlation, or the noncontingency. A second purpose of this study was to validate other studies that have used dependent measures modeled after the work of J. R. McGahan and R. Wight (1989). Demonstrating that this measure can be used to detect a well-documented phenomenon (i.e., the illusory correlation) would strengthen the results and conclusions from other studies. To this end, results from 2 experiments indicate that this measure does provide a valid alternative to those measures that are commonly used in illusory correlation studies. The results thereby give credence to other studies that have used similar dependent measures.     

The Prediction of Students' Satisfaction with Community College Vocational Training

The present study was conducted with 1,632 college vocational students in North Carolina to test the job satisfaction postulate of Rusbult's (1980a) investment model. The model postulate, that satisfaction is a function of perceived positive and negative outcomes, received support and proved to be defensible even after controlling for a broad array of situational variables. This postulate has also received empirical support from studies of satisfaction with business relationships, friendships, and romantic associations. The present study also introduced a new measure of outcomes: the Perceived Outcomes of College Life measure.