We develop a latent variable selection method for multidimensional item response theory models. The proposed method identifies latent traits probed by items of a multidimensional test. Its basic strategy is to impose an [Formula: see text] penalty term to the log-likelihood. The computation is carried out by the expectation-maximization algorithm combined with the coordinate descent algorithm. Simulation studies show that the resulting estimator provides an effective way in correctly identifying the latent structures. The method is applied to a real dataset involving the Eysenck Personality Questionnaire.

The purpose of this study was to evaluate the relationships between screen time (ST), nighttime sleep duration, and behavioural problems in a sample of preschool children in China. A sample of 8900 children aged 3-6 years was enrolled from 35 kindergartens, in four cities, in two provinces, in China to evaluate the relationships between ST, nighttime sleep duration, and behavioural problems. Children's ST and nighttime sleep duration were assessed by questionnaires completed by parents or guardians. Behavioural problems were assessed using the Strengths and Difficulties Questionnaire (SDQ), and the Clancy Autism Behaviour Scale (CABS). Multivariate analysis was used to assess the associations between ST, nighttime sleep duration, and behavioural problems. The total SDQ and CABS scores were higher in children with ST ≥2 h/day and sleep duration <9.15 h/day (a P < 0.001 for all). After adjusting for potential confounders, children with ST ≥2 h/day had a significantly increased risk of having total difficulties, emotional symptoms, conduct problems, hyperactivity, peer problems, and prosocial problems, as well as behavioural symptoms of autism spectrum disorder. Similar results were found in children with sleep duration <9.15 h/day. No significantly increased risk of emotional symptoms was observed for short sleep duration. Preschool children with more ST and short nighttime sleep duration were significantly more likely to have behavioural problems. These results may contribute to a better understanding of prevention and intervention for psychosocial problems in children.

Joint maximum likelihood (JML) estimation is one of the earliest approaches to fitting item response theory (IRT) models. This procedure treats both the item and person parameters as unknown but fixed model parameters, and estimates them simultaneously by solving an optimization problem. However, the JML estimator is known to be asymptotically inconsistent for many IRT models, when the sample size goes to infinity and the number of items keeps fixed. Consequently, in the psychometrics literature, this estimator is less preferred to the marginal maximum likelihood (MML) estimator. In this paper, we re-investigate the JML estimator for high-dimensional exploratory item factor analysis, from both statistical and computational perspectives.In particular, we establish a notion of statistical consistency for a constrained JML estimator, under an asymptotic setting that both the numbers of items and people grow to infinity and that many responses may be missing. A parallel computing algorithm is proposed for this estimator that can scale to very large datasets. Via simulation studies, we show that when the dimensionality is high, the proposed estimator yields 1 arXiv:1712.06748v2 [stat.ME] 14 Jun 2019 similar or even better results than those from the MML estimator, but can be obtained computationally much more efficiently. An illustrative real data example is provided based on the revised version of Eysenck's Personality Questionnaire (EPQ-R).

An adaptive learning system aims at providing instruction tailored to the current status of a learner, differing from the traditional classroom experience. The latest advances in technology make adaptive learning possible, which has the potential to provide students with high-quality learning benefit at a low cost. A key component of an adaptive learning system is a recommendation system, which recommends the next material (video lectures, practices, and so on, on different skills) to the learner, based on the psychometric assessment results and possibly other individual characteristics. An important question then follows: How should recommendations be made? To answer this question, a mathematical framework is proposed that characterizes the recommendation process as a Markov decision problem, for which decisions are made based on the current knowledge of the learner and that of the learning materials. In particular, two plain vanilla systems are introduced, for which the optimal recommendation at each stage can be obtained analytically.

Latent factor models are widely used to measure unobserved latent traits in social and behavioral sciences, including psychology, education, and marketing. When used in a confirmatory manner, design information is incorporated as zero constraints on corresponding parameters, yielding structured (confirmatory) latent factor models.In this paper, we study how such design information affects the identifiability and the estimation of a structured latent factor model. Insights are gained through both arXiv:1712.08966v2 [stat.ME] 13 Jun 2019 large-scale measurement in education and psychology and have important implications on measurement validity and reliability.KEY WORDS: High-dimensional latent factor model, confirmatory factor analysis, identifiability of latent factors, structured low-rank matrix, large-scale psychological measurement

BackgroundThe increase rates of cesarean section (CS) occurred at the same period as the dramatic increase of childhood overweight/obesity. In China, cesarean section rates have exponentially increased in the last 20 years and they now exceed World Health Organization (WHO) recommendation. Such high rates demand an understanding to the long-term consequences on child health. We aim to examine the association between CS and risk of overweight and obesity among preschool children.MethodWe recruited 9103 children from 35 kindergartens in 4 cities located in East China. Children anthropometric measurements were taken in person by trained personnel. The mode of delivery was classified as vaginal or CS, in sub-analyses we divided cesarean delivery into elective or non-elective. The mode of delivery and other parental information were self-reported by parents. Multivariate logistic regression analysis was used to examine the associations.ResultsIn our cross-sectional study of 8900 preschool children aged 3–6 years, 67.3 % were born via CS, of whom 15.7 % were obese. Cesarean delivery was significantly associated with the risk of overweight [OR 1.24; (95 % CI 1.07–1.44); p = 0.003], and the risk of obesity [OR 1.29; (95 % CI 1.13–1.49); p < 0.001] in preschool children. After adjusted for child characteristics, parental factors and family income, the odd of overweight was 1.35 and of obesity was 1.25 in children delivered by elective CS.ConclusionThe associations between CS and overweight/obesity in preschool children are influenced by potential confounders. Both children delivered by elective or non-elective CS are at increased risk of overweight/obesity. Potential consequences of CS on the health of the children should be discussed among both health care professionals and childbearing women.

Personalized learning refers to instruction in which the pace of learning and the instructional approach are optimized for the needs of each learner. With the latest advances in information technology and data science, personalized learning is becoming possible for anyone with a personal computer, supported by a data‐driven recommendation system that automatically schedules the learning sequence. The engine of such a recommendation system is a recommendation strategy that, based on data from other learners and the performance of the current learner, recommends suitable learning materials to optimize certain learning outcomes. A powerful engine achieves a balance between making the best possible recommendations based on the current knowledge and exploring new learning trajectories that may potentially pay off. Building such an engine is a challenging task. We formulate this problem within the Markov decision framework and propose a reinforcement learning approach to solving the problem.

Diagnostic classification models are confirmatory in the sense that the relationship between the latent attributes and responses to items is specified or parameterized. Such models are readily interpretable with each component of the model usually having a practical meaning. However; parameterized diagnostic classification models are sometimes too simple to capture all the data patterns, resulting in significant model lack of fit. In this paper, we attempt to obtain a compromise between interpretability and goodness of fit by regularizing a latent class model. Our approach starts with minimal assumptions on the data structure, followed by suitable regularization to reduce complexity, so that readily interpretable, yet flexible model is obtained. An expectation–maximization-type algorithm is developed for efficient computation. It is shown that the proposed approach enjoys good theoretical properties. Results from simulation studies and a real application are presented.